diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json index 557e68b..a730788 100644 --- a/.claude-plugin/marketplace.json +++ b/.claude-plugin/marketplace.json @@ -1,7 +1,7 @@ { "$schema": "https://anthropic.com/claude-code/marketplace.schema.json", "name": "context-engineering-kit", - "version": "2.0.1", + "version": "2.0.2", "description": "Hand-crafted collection of advanced context engineering techniques and patterns with minimal token footprint focused on improving agent result quality.", "owner": { "name": "NeoLabHQ", diff --git a/docs/SUMMARY.md b/docs/SUMMARY.md index 29634ef..a53ac92 100644 --- a/docs/SUMMARY.md +++ b/docs/SUMMARY.md @@ -95,6 +95,7 @@ * [implement](plugins/sdd/implement.md) * [brainstorm](plugins/sdd/brainstorm.md) * [create-ideas](plugins/sdd/create-ideas.md) + * [Refining Specifications and Code](plugins/sdd/refine.md) * [customization](plugins/sdd/customization.md) * [Usage Examples](plugins/sdd/usage-examples.md) * [Test-Driven Development](plugins/tdd/README.md) diff --git a/docs/guides/spec-driven-development.md b/docs/guides/spec-driven-development.md index 6132558..aa3fc5b 100644 --- a/docs/guides/spec-driven-development.md +++ b/docs/guides/spec-driven-development.md @@ -117,11 +117,11 @@ It will perform the following refinement process to update the task file with a It will output the updated task file to `.specs/tasks/todo/design-implement-authentication-middleware-with-jwt-support.feature.md` and create new skills if needed. It also produces scratchpads and verification reports along the way to properly evaluate each step of the process. You can safely ignore all of them. -At this point you can verify and adjust the specification, then run the `/plan --refine` command again for agents to update the rest of the specification where it doesn't align with your changes. It uses a top-to-bottom approach, meaning all sections below your changes will be rethought and updated accordingly. +At this point you can verify and adjust the specification, then run the `/plan --refine` command again for agents to update the rest of the specification where it doesn't align with your changes. It uses a top-to-bottom approach, meaning all sections below your changes will be rethought and updated accordingly. See the [Refining Specifications and Code](../plugins/sdd/refine.md) guide for details. ### Code Generation -Once you are happy with the specification, you can run the implementation process: +Once you are happy with the specification, run `/clear` (or re-open Claude Code) to clear context. Then you can start the implementation process: ```bash /implement diff --git a/docs/plugins/sdd/README.md b/docs/plugins/sdd/README.md index 9737e38..5353e27 100644 --- a/docs/plugins/sdd/README.md +++ b/docs/plugins/sdd/README.md @@ -38,7 +38,7 @@ Then run the following commands: # Moves the task to the .specs/tasks/todo/ folder ``` -Restart the Claude Code session to clear context and start fresh. Then run the following command: +Run `/clear` (or re-open Claude Code) to clear context and start fresh. Then run the following command: ```bash # Implement the task @@ -47,6 +47,7 @@ Restart the Claude Code session to clear context and start fresh. Then run the f ``` - [Detailed guide](../../guides/spec-driven-development.md) +- [Refining specifications and code](refine.md) - [Usage Examples](usage-examples.md) ## Overall Flow @@ -127,6 +128,20 @@ Even if you prefer a less hands-on approach, you can still use the plugin for co Learn more about available customization options in [Customization](customization.md). +## FAQ + +**Do I need to re-run `/plan` or `/implement` after context compaction (`/compact`)?** + +After compaction, close the terminal and resume with `/plan --continue` or `/implement --continue`. This produces more predictable results than continuing in a compacted context. Using `/model sonnet[1m]` reduces compaction frequency. + +**Do I need to prefix every prompt with `/plan` or `/implement`?** + +No. Run these commands once to start the workflow. The only time to invoke them again is when you change the specification or code and want agents to update misaligned sections — use `/plan --refine` or `/implement --refine`. + +**Should I clear context between `/plan` and `/implement`?** + +Yes. Run `/clear` (or re-open Claude Code) after `/plan` completes and before running `/implement`. The planning phase fills the context with analysis artifacts; a clean context gives implementation agents better results. + ## Theoretical Foundation The SDD plugin is based on established software engineering methodologies and research: diff --git a/docs/plugins/sdd/implement.md b/docs/plugins/sdd/implement.md index 4cb8810..34b0064 100644 --- a/docs/plugins/sdd/implement.md +++ b/docs/plugins/sdd/implement.md @@ -21,6 +21,11 @@ Execute task implementation steps using automated LLM-as-Judge quality verificat | `--continue` | flag | None | Resume from the last completed step | | `--refine` | flag | `false` | Detect changed project files and re-verify from the earliest affected step | +## Context Management + +If you ran `/plan` in the same session, run `/clear` (or re-open Claude Code) before `/implement`. The planning phase fills the context window with analysis artifacts; starting fresh gives the implementation agents a clean context for better results. + + ## Workflow Diagram ``` @@ -146,7 +151,10 @@ After all steps complete: 1. Move task from `in-progress/` to `done/` 2. All step titles are marked `[DONE]`, and subtasks are marked `[X]` 3. All DoD items are marked `[X]` -4. Generate a final implementation report +4. Stage all changed files with Git +5. Generate a final implementation report + +Staging at the end allows you to make manual edits on top and use `--refine`, so the agent can diff your changes against the staged state. ## Verification Levels @@ -170,7 +178,7 @@ Resumes implementation from the last completed step: Detects changes to **project files** (not the task file) and re-verifies from the earliest affected step: -1. Detects changed files via `git diff` +1. Compares local (unstaged) changes against staged changes by default. To compare against the last commit instead, specify it explicitly (e.g., `/implement --refine compare with last commit`). 2. Maps changed files to implementation steps using "Expected Output" and artifact paths 3. Determines the earliest affected step 4. Launches a judge for each affected step — if it passes, the user's fix is accepted; if it fails, the implementation agent aligns the rest of the code with the user's changes diff --git a/docs/plugins/sdd/plan.md b/docs/plugins/sdd/plan.md index d48b895..01d24fb 100644 --- a/docs/plugins/sdd/plan.md +++ b/docs/plugins/sdd/plan.md @@ -137,7 +137,7 @@ Each sub-phase is validated by a judge agent. All three must pass before proceed ### Phase 7: Promote Task -Moves the refined task file from `draft/` to `todo/` and stages all generated artifacts with Git. +Moves the refined task file from `draft/` to `todo/` and stages all generated artifacts with Git. Staging at the end allows you to make manual edits on top and use `--refine`, so the agent can diff your changes against the staged state. ## Quality Gates @@ -151,12 +151,14 @@ Every phase includes a judge validation step using LLM-as-Judge: After reviewing the generated specification, you can edit it directly and re-run the planning process with `--refine`: -1. Detects changes via `git diff HEAD -- ` +1. Compares local (unstaged) changes against staged changes by default. To compare against the last commit instead, specify it explicitly (e.g., `/plan --refine compare with last commit`). 2. Identifies the earliest modified section 3. Re-runs only stages from that point onward (top-to-bottom propagation) 4. Preserves earlier stages that are unaffected 5. Supports `//` comment markers for inline feedback +You can also pass a requirement change directly: `/plan --refine `. The agent incorporates your change and re-runs affected stages. + | Modified Section | Re-run From Stage | |------------------|-------------------| | Description / Acceptance Criteria | `business analysis` (Phase 2c) | diff --git a/docs/plugins/sdd/refine.md b/docs/plugins/sdd/refine.md new file mode 100644 index 0000000..c094a2b --- /dev/null +++ b/docs/plugins/sdd/refine.md @@ -0,0 +1,143 @@ +# Refining Specifications and Code + +Guide for handling requirement changes at different stages of the SDD workflow. + +## During Planning + +When the specification needs adjustment after `/plan` completes: + +### Option A: Pass the change directly + +```bash +/plan --refine +``` + +The agent incorporates your change and re-runs affected stages. + +**Examples:** + +```bash +# Change authentication strategy +/plan --refine Use session-based auth instead of JWT + +# Add a constraint the agent missed +/plan --refine The API must support pagination with cursor-based navigation, not offset + +# Narrow the scope +/plan --refine Remove the admin dashboard from this task, we will handle it separately +``` + +### Option B: Edit the spec, then refine + +1. Edit the task file in `.specs/tasks/todo/` +2. Add `//` comments to lines that need clarification +3. Run `/plan --refine` + +The agent detects your edits, identifies the earliest modified section, and re-runs all stages from that point onward. Earlier sections remain unchanged. + +**Example:** The agent planned a REST API, but you need GraphQL. Open the task file and edit: + +```markdown +## Architecture Overview + +// Change this to use GraphQL with Apollo Server instead of REST +- REST API with Express routes for CRUD operations +- PostgreSQL with Prisma ORM +``` + +Then run `/plan --refine`. The agent re-runs from architecture synthesis onward, producing new implementation steps for GraphQL while preserving the research and business analysis stages. + +### What `--refine` compares + +By default, `--refine` diffs local (unstaged) changes against staged changes. Both `/plan` and `/implement` stage their output at the end, so any manual edits you make afterward appear as unstaged changes. + +To compare against the last commit instead, specify it: `/plan --refine compare with last commit`. + +## After Implementation + +When requirements change after `/implement` completes, choose based on the scope of the change: + +### Small code adjustments + +Edit the code directly, then run: + +```bash +/implement --refine +``` + +The agent detects your changes, maps them to implementation steps, and aligns the rest of the codebase. If the judge passes your fix, it is accepted as-is. If it fails, the agent adjusts surrounding code to match your intent. + +**Examples:** + +```bash +# You fixed a validation bug in the controller — agent updates related tests and error messages +vi src/controllers/users.ts +/implement --refine + +# You replaced bcrypt with argon2 in the auth service — agent aligns password checks elsewhere +vi src/services/auth.ts +/implement --refine + +# You changed the database column name from `userName` to `username` — agent propagates across migrations, models, and queries +vi src/models/user.ts +/implement --refine +``` + +### Minor tweaks and polish + +If the implementation is done and you need small refinements — renaming, formatting, minor behavior changes — run `/clear` (or re-open Claude Code) and work with agent as usual. No need to re-enter the SDD workflow. + +**Examples:** + +- Adjusting log messages or error text +- Renaming a local variable for clarity +- Tweaking CSS spacing or colors +- Adding a missing `console.log` for debugging + +### Major requirement changes + +If requirements changed substantially, create a new task: + +```bash +/sdd:add-task "Refactor authentication implementation" +/sdd:plan +# /clear (or re-open Claude Code) +/sdd:implement +``` + +Re-running `/implement --refine` on large changes is less reliable than a fresh planning cycle. A new task produces a clean specification, proper architecture analysis, and accurate implementation steps. + +**Examples of changes that warrant a new task:** + +- Switching from a monolith to microservices +- Replacing the database engine (e.g., PostgreSQL to MongoDB) +- Changing the authentication model from API keys to OAuth2 with SSO +- Adding a real-time collaboration feature that was never in scope + +## Walkthrough: Iterating on an Authentication Feature + +A realistic sequence showing how refinement fits into the workflow: + +```bash +# 1. Create and plan the task +/sdd:add-task "Add JWT authentication middleware" +/sdd:plan + +# 2. Review the spec — agent chose HS256, but you need RS256 +/plan --refine Use RS256 with rotating key pairs instead of HS256 + +# 3. Clear context, then implement +/clear +/sdd:implement + +# 4. Review the code — token expiry is 1 hour, you want 15 minutes +vi src/config/auth.ts # change TOKEN_EXPIRY to 900 +/implement --refine # agent updates tests and documentation to match + +# 5. Product feedback: "Add refresh tokens" +# This is a significant scope addition — create a new task +/sdd:add-task "Add refresh token rotation for JWT auth" +/sdd:plan +/clear +/sdd:implement +``` diff --git a/plugins/code-review/skills/review-local-changes/SKILL.md b/plugins/code-review/skills/review-local-changes/SKILL.md index b230ee3..4483445 100644 --- a/plugins/code-review/skills/review-local-changes/SKILL.md +++ b/plugins/code-review/skills/review-local-changes/SKILL.md @@ -1,4 +1,5 @@ --- +name: code-review:review-local-changes description: Comprehensive review of local uncommitted changes using specialized agents with code improvement suggestions allowed-tools: ["Bash", "Glob", "Grep", "Read", "Task"] disable-model-invocation: false diff --git a/plugins/code-review/skills/review-pr/SKILL.md b/plugins/code-review/skills/review-pr/SKILL.md index 28d8822..4ffc464 100644 --- a/plugins/code-review/skills/review-pr/SKILL.md +++ b/plugins/code-review/skills/review-pr/SKILL.md @@ -1,4 +1,5 @@ --- +name: code-review:review-pr description: Comprehensive pull request review using specialized agents argument-hint: "[review-aspects]" --- diff --git a/plugins/customaize-agent/skills/agent-evaluation/SKILL.md b/plugins/customaize-agent/skills/agent-evaluation/SKILL.md index 25e8659..9c96e3b 100644 --- a/plugins/customaize-agent/skills/agent-evaluation/SKILL.md +++ b/plugins/customaize-agent/skills/agent-evaluation/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:agent-evaluation description: Evaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality. --- diff --git a/plugins/customaize-agent/skills/apply-anthropic-skill-best-practices/SKILL.md b/plugins/customaize-agent/skills/apply-anthropic-skill-best-practices/SKILL.md index 4f86ee9..69c949d 100644 --- a/plugins/customaize-agent/skills/apply-anthropic-skill-best-practices/SKILL.md +++ b/plugins/customaize-agent/skills/apply-anthropic-skill-best-practices/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:apply-anthropic-skill-best-practices description: Comprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structure argument-hint: Optional skill name or path to skill being reviewed --- diff --git a/plugins/customaize-agent/skills/context-engineering/SKILL.md b/plugins/customaize-agent/skills/context-engineering/SKILL.md index 98927a4..e6faf9b 100644 --- a/plugins/customaize-agent/skills/context-engineering/SKILL.md +++ b/plugins/customaize-agent/skills/context-engineering/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:context-engineering description: Understand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts. --- diff --git a/plugins/customaize-agent/skills/create-agent/SKILL.md b/plugins/customaize-agent/skills/create-agent/SKILL.md index 4b56c66..d306b65 100644 --- a/plugins/customaize-agent/skills/create-agent/SKILL.md +++ b/plugins/customaize-agent/skills/create-agent/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:create-agent description: Comprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patterns argument-hint: [agent-name] [optional description of agent purpose] allowed-tools: Read, Write, Glob, Grep, Bash(mkdir:*), Task diff --git a/plugins/customaize-agent/skills/create-command/SKILL.md b/plugins/customaize-agent/skills/create-command/SKILL.md index 8709989..0878de2 100644 --- a/plugins/customaize-agent/skills/create-command/SKILL.md +++ b/plugins/customaize-agent/skills/create-command/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:create-command description: Interactive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integration argument-hint: Optional command name or description of command purpose --- diff --git a/plugins/customaize-agent/skills/create-hook/SKILL.md b/plugins/customaize-agent/skills/create-hook/SKILL.md index e5de039..d721622 100644 --- a/plugins/customaize-agent/skills/create-hook/SKILL.md +++ b/plugins/customaize-agent/skills/create-hook/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:create-hook description: Create and configure git hooks with intelligent project analysis, suggestions, and automated testing argument-hint: Optional hook type or description of desired behavior --- diff --git a/plugins/customaize-agent/skills/create-skill/SKILL.md b/plugins/customaize-agent/skills/create-skill/SKILL.md index b073a10..efea363 100644 --- a/plugins/customaize-agent/skills/create-skill/SKILL.md +++ b/plugins/customaize-agent/skills/create-skill/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:create-skill description: Guide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization --- diff --git a/plugins/customaize-agent/skills/create-workflow-command/SKILL.md b/plugins/customaize-agent/skills/create-workflow-command/SKILL.md index 739b189..cf1ce6e 100644 --- a/plugins/customaize-agent/skills/create-workflow-command/SKILL.md +++ b/plugins/customaize-agent/skills/create-workflow-command/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:create-workflow-command description: Create a workflow command that orchestrates multi-step execution through sub-agents with file-based task prompts argument-hint: [workflow-name] [description] allowed-tools: Read, Write, Glob, Grep, Bash(mkdir:*) diff --git a/plugins/customaize-agent/skills/prompt-engineering/SKILL.md b/plugins/customaize-agent/skills/prompt-engineering/SKILL.md index d5b4cda..03ef45e 100644 --- a/plugins/customaize-agent/skills/prompt-engineering/SKILL.md +++ b/plugins/customaize-agent/skills/prompt-engineering/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:prompt-engineering description: Use this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production prompt templates. --- diff --git a/plugins/customaize-agent/skills/test-prompt/SKILL.md b/plugins/customaize-agent/skills/test-prompt/SKILL.md index 7fa9300..0f9598b 100644 --- a/plugins/customaize-agent/skills/test-prompt/SKILL.md +++ b/plugins/customaize-agent/skills/test-prompt/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:test-prompt description: Use when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagents for isolated testing --- diff --git a/plugins/customaize-agent/skills/test-skill/SKILL.md b/plugins/customaize-agent/skills/test-skill/SKILL.md index 79a3918..59f6d9f 100644 --- a/plugins/customaize-agent/skills/test-skill/SKILL.md +++ b/plugins/customaize-agent/skills/test-skill/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:test-skill description: Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes --- diff --git a/plugins/customaize-agent/skills/thought-based-reasoning/SKILL.md b/plugins/customaize-agent/skills/thought-based-reasoning/SKILL.md index 7ca17d8..7cb4dc1 100644 --- a/plugins/customaize-agent/skills/thought-based-reasoning/SKILL.md +++ b/plugins/customaize-agent/skills/thought-based-reasoning/SKILL.md @@ -1,4 +1,5 @@ --- +name: customaize-agent:thought-based-reasoning description: Use when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehensive guide to Chain-of-Thought and related prompting techniques (Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, Reflexion) with templates, decision matrices, and research-backed patterns --- diff --git a/plugins/ddd/skills/setup-code-formating/SKILL.md b/plugins/ddd/skills/setup-code-formating/SKILL.md index 12cc355..f52ef68 100644 --- a/plugins/ddd/skills/setup-code-formating/SKILL.md +++ b/plugins/ddd/skills/setup-code-formating/SKILL.md @@ -1,4 +1,5 @@ --- +name: ddd:setup-code-formating description: Sets up code formatting rules and style guidelines in CLAUDE.md argument-hint: None required - creates standard formatting configuration --- diff --git a/plugins/ddd/skills/software-architecture/SKILL.md b/plugins/ddd/skills/software-architecture/SKILL.md index 698dc2b..ee32f9b 100644 --- a/plugins/ddd/skills/software-architecture/SKILL.md +++ b/plugins/ddd/skills/software-architecture/SKILL.md @@ -1,4 +1,5 @@ --- +name: ddd:software-architecture description: Guide for quality focused software architecture. This skill should be used when users want to write code, design architecture, analyze code, in any case that relates to software development. --- diff --git a/plugins/docs/skills/update-docs/SKILL.md b/plugins/docs/skills/update-docs/SKILL.md index 8a93ff7..6571be7 100644 --- a/plugins/docs/skills/update-docs/SKILL.md +++ b/plugins/docs/skills/update-docs/SKILL.md @@ -1,4 +1,5 @@ --- +name: docs:update-docs description: Update and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API documentation. argument-hint: Optional target directory, documentation type (api, guides, readme, jsdoc), or specific focus area --- diff --git a/plugins/docs/skills/write-concisely/SKILL.md b/plugins/docs/skills/write-concisely/SKILL.md index efafbab..6b3e79f 100644 --- a/plugins/docs/skills/write-concisely/SKILL.md +++ b/plugins/docs/skills/write-concisely/SKILL.md @@ -1,4 +1,5 @@ --- +name: docs:write-concisely description: Apply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional. --- diff --git a/plugins/fpf/commands/actualize.md b/plugins/fpf/skills/actualize/SKILL.md similarity index 99% rename from plugins/fpf/commands/actualize.md rename to plugins/fpf/skills/actualize/SKILL.md index 2e54557..19dc2aa 100644 --- a/plugins/fpf/commands/actualize.md +++ b/plugins/fpf/skills/actualize/SKILL.md @@ -1,4 +1,5 @@ --- +name: fpf:actualize description: "Reconcile the project's FPF state with recent repository changes" --- diff --git a/plugins/fpf/commands/decay.md b/plugins/fpf/skills/decay/SKILL.md similarity index 99% rename from plugins/fpf/commands/decay.md rename to plugins/fpf/skills/decay/SKILL.md index 9cd78fb..74e15f3 100644 --- a/plugins/fpf/commands/decay.md +++ b/plugins/fpf/skills/decay/SKILL.md @@ -1,4 +1,5 @@ --- +name: fpf:decay description: "Manage evidence freshness by identifying stale decisions and providing governance actions" --- diff --git a/plugins/fpf/commands/propose-hypotheses.md b/plugins/fpf/skills/propose-hypotheses/SKILL.md similarity index 99% rename from plugins/fpf/commands/propose-hypotheses.md rename to plugins/fpf/skills/propose-hypotheses/SKILL.md index 726a663..d5492f1 100644 --- a/plugins/fpf/commands/propose-hypotheses.md +++ b/plugins/fpf/skills/propose-hypotheses/SKILL.md @@ -1,4 +1,5 @@ --- +name: fpf:propose-hypotheses description: Execute complete FPF cycle from hypothesis generation to decision argument-hint: "[problem-statement]" allowed-tools: Task, Read, Write, Bash, AskUserQuestion diff --git a/plugins/fpf/commands/query.md b/plugins/fpf/skills/query/SKILL.md similarity index 99% rename from plugins/fpf/commands/query.md rename to plugins/fpf/skills/query/SKILL.md index 7c55c76..952b5ca 100644 --- a/plugins/fpf/commands/query.md +++ b/plugins/fpf/skills/query/SKILL.md @@ -1,4 +1,5 @@ --- +name: fpf:query description: "Search the FPF knowledge base and display hypothesis details with assurance information" --- diff --git a/plugins/fpf/commands/reset.md b/plugins/fpf/skills/reset/SKILL.md similarity index 99% rename from plugins/fpf/commands/reset.md rename to plugins/fpf/skills/reset/SKILL.md index 27a963b..bd9e9df 100644 --- a/plugins/fpf/commands/reset.md +++ b/plugins/fpf/skills/reset/SKILL.md @@ -1,4 +1,5 @@ --- +name: fpf:reset description: "Reset the FPF reasoning cycle to start fresh" --- diff --git a/plugins/fpf/commands/status.md b/plugins/fpf/skills/status/SKILL.md similarity index 99% rename from plugins/fpf/commands/status.md rename to plugins/fpf/skills/status/SKILL.md index 93816c2..200e39b 100644 --- a/plugins/fpf/commands/status.md +++ b/plugins/fpf/skills/status/SKILL.md @@ -1,4 +1,5 @@ --- +name: fpf:status description: "Display the current state of the FPF knowledge base" --- diff --git a/plugins/git/skills/analyze-issue/SKILL.md b/plugins/git/skills/analyze-issue/SKILL.md index a73d0dd..706a392 100644 --- a/plugins/git/skills/analyze-issue/SKILL.md +++ b/plugins/git/skills/analyze-issue/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:analyze-issue description: Analyze a GitHub issue and create a detailed technical specification argument-hint: Issue number (e.g., 42) allowed-tools: Bash(gh issue:*), Read, Write, Glob, Grep diff --git a/plugins/git/skills/attach-review-to-pr/SKILL.md b/plugins/git/skills/attach-review-to-pr/SKILL.md index 7657583..eefc49c 100644 --- a/plugins/git/skills/attach-review-to-pr/SKILL.md +++ b/plugins/git/skills/attach-review-to-pr/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:attach-review-to-pr description: Add line-specific review comments to pull requests using GitHub CLI API argument-hint: PR number or URL (optional - can work with current branch) allowed-tools: Bash(gh api:*), Bash(gh auth:*), Bash(gh pr:*), mcp__github_inline_comment__create_inline_comment diff --git a/plugins/git/skills/commit/SKILL.md b/plugins/git/skills/commit/SKILL.md index 44b268c..94b9b87 100644 --- a/plugins/git/skills/commit/SKILL.md +++ b/plugins/git/skills/commit/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:commit description: Create well-formatted commits with conventional commit messages and emoji argument-hint: Optional flags like --no-verify to skip pre-commit checks model: haiku diff --git a/plugins/git/skills/compare-worktrees/SKILL.md b/plugins/git/skills/compare-worktrees/SKILL.md index 711148b..ab9b446 100644 --- a/plugins/git/skills/compare-worktrees/SKILL.md +++ b/plugins/git/skills/compare-worktrees/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:compare-worktrees description: Compare files and directories between git worktrees or worktree and current branch argument-hint: Path(s) to compare, worktree paths, branch names, or --stat for summary model: opus diff --git a/plugins/git/skills/create-pr/SKILL.md b/plugins/git/skills/create-pr/SKILL.md index f855701..dfc2a47 100644 --- a/plugins/git/skills/create-pr/SKILL.md +++ b/plugins/git/skills/create-pr/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:create-pr description: Create pull requests using GitHub CLI with proper templates and formatting argument-hint: None required - interactive guide for PR creation allowed-tools: Bash(gh pr:*), Bash(gh auth:*), Bash(git status:*), Bash(git push:*), Bash(git branch:*), Skill(git:commit) diff --git a/plugins/git/skills/create-worktree/SKILL.md b/plugins/git/skills/create-worktree/SKILL.md index dfcbad1..82daf0e 100644 --- a/plugins/git/skills/create-worktree/SKILL.md +++ b/plugins/git/skills/create-worktree/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:create-worktree description: Create and setup git worktrees for parallel development with automatic dependency installation argument-hint: (e.g., "refactor auth system" or "fix login") or --list to show existing worktrees model: opus diff --git a/plugins/git/skills/load-issues/SKILL.md b/plugins/git/skills/load-issues/SKILL.md index ea891c3..e616056 100644 --- a/plugins/git/skills/load-issues/SKILL.md +++ b/plugins/git/skills/load-issues/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:load-issues description: Load all open issues from GitHub and save them as markdown files argument-hint: None required - loads all open issues automatically allowed-tools: Bash(gh issue:*), Bash(mkdir:*), Write diff --git a/plugins/git/skills/merge-worktree/SKILL.md b/plugins/git/skills/merge-worktree/SKILL.md index c586cea..3c9e851 100644 --- a/plugins/git/skills/merge-worktree/SKILL.md +++ b/plugins/git/skills/merge-worktree/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:merge-worktree description: Merge changes from worktrees into current branch with selective file checkout, cherry-picking, interactive patch selection, or manual merge argument-hint: file/directory path, commit name, branch name, or --interactive for guided mode model: opus diff --git a/plugins/git/skills/notes/SKILL.md b/plugins/git/skills/notes/SKILL.md index db6acbf..a1fe2ac 100644 --- a/plugins/git/skills/notes/SKILL.md +++ b/plugins/git/skills/notes/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:notes description: Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands and patterns for attaching non-invasive metadata to Git objects. --- diff --git a/plugins/git/skills/worktrees/SKILL.md b/plugins/git/skills/worktrees/SKILL.md index 25b45f7..cea08e4 100644 --- a/plugins/git/skills/worktrees/SKILL.md +++ b/plugins/git/skills/worktrees/SKILL.md @@ -1,4 +1,5 @@ --- +name: git:worktrees description: Use when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides git worktree commands and workflow patterns for parallel development with multiple working directories. --- diff --git a/plugins/kaizen/skills/analyse-problem/SKILL.md b/plugins/kaizen/skills/analyse-problem/SKILL.md index 3f33dba..3c699e8 100644 --- a/plugins/kaizen/skills/analyse-problem/SKILL.md +++ b/plugins/kaizen/skills/analyse-problem/SKILL.md @@ -1,4 +1,5 @@ --- +name: kaizen:analyse-problem description: Comprehensive A3 one-page problem analysis with root cause and action plan argument-hint: Optional problem description to document --- diff --git a/plugins/kaizen/skills/analyse/SKILL.md b/plugins/kaizen/skills/analyse/SKILL.md index c17d755..c1cb4b9 100644 --- a/plugins/kaizen/skills/analyse/SKILL.md +++ b/plugins/kaizen/skills/analyse/SKILL.md @@ -1,4 +1,5 @@ --- +name: kaizen:analyse description: Auto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for target argument-hint: Optional target description (e.g., code, workflow, or inefficiencies) --- diff --git a/plugins/kaizen/skills/cause-and-effect/SKILL.md b/plugins/kaizen/skills/cause-and-effect/SKILL.md index 615c48e..419a0e1 100644 --- a/plugins/kaizen/skills/cause-and-effect/SKILL.md +++ b/plugins/kaizen/skills/cause-and-effect/SKILL.md @@ -1,4 +1,5 @@ --- +name: kaizen:cause-and-effect description: Systematic Fishbone analysis exploring problem causes across six categories argument-hint: Optional problem description to analyze --- diff --git a/plugins/kaizen/skills/kaizen/SKILL.md b/plugins/kaizen/skills/kaizen/SKILL.md index 728f39f..8fc3f1b 100644 --- a/plugins/kaizen/skills/kaizen/SKILL.md +++ b/plugins/kaizen/skills/kaizen/SKILL.md @@ -1,4 +1,5 @@ --- +name: kaizen:kaizen description: Use when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and apply iterative improvements. --- diff --git a/plugins/kaizen/skills/plan-do-check-act/SKILL.md b/plugins/kaizen/skills/plan-do-check-act/SKILL.md index aec1883..fd30d52 100644 --- a/plugins/kaizen/skills/plan-do-check-act/SKILL.md +++ b/plugins/kaizen/skills/plan-do-check-act/SKILL.md @@ -1,4 +1,5 @@ --- +name: kaizen:plan-do-check-act description: Iterative PDCA cycle for systematic experimentation and continuous improvement argument-hint: Optional improvement goal or problem to address --- diff --git a/plugins/kaizen/skills/root-cause-tracing/SKILL.md b/plugins/kaizen/skills/root-cause-tracing/SKILL.md index 345c3f3..2386850 100644 --- a/plugins/kaizen/skills/root-cause-tracing/SKILL.md +++ b/plugins/kaizen/skills/root-cause-tracing/SKILL.md @@ -1,4 +1,5 @@ --- +name: kaizen:root-cause-tracing description: Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior --- diff --git a/plugins/kaizen/skills/why/SKILL.md b/plugins/kaizen/skills/why/SKILL.md index a037af7..de350ac 100644 --- a/plugins/kaizen/skills/why/SKILL.md +++ b/plugins/kaizen/skills/why/SKILL.md @@ -1,4 +1,5 @@ --- +name: kaizen:why description: Iterative Five Whys root cause analysis drilling from symptoms to fundamentals argument-hint: Optional issue or symptom description --- diff --git a/plugins/mcp/skills/build-mcp/SKILL.md b/plugins/mcp/skills/build-mcp/SKILL.md index 03061e7..c67b0e2 100644 --- a/plugins/mcp/skills/build-mcp/SKILL.md +++ b/plugins/mcp/skills/build-mcp/SKILL.md @@ -1,4 +1,5 @@ --- +name: mcp:build-mcp description: Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). --- diff --git a/plugins/mcp/skills/setup-arxiv-mcp/SKILL.md b/plugins/mcp/skills/setup-arxiv-mcp/SKILL.md index df87455..14bfadf 100644 --- a/plugins/mcp/skills/setup-arxiv-mcp/SKILL.md +++ b/plugins/mcp/skills/setup-arxiv-mcp/SKILL.md @@ -1,4 +1,5 @@ --- +name: mcp:setup-arxiv-mcp description: Guide for setup arXiv paper search MCP server using Docker MCP argument-hint: Optional - specific research topics or paper sources to configure --- diff --git a/plugins/mcp/skills/setup-codemap-cli/SKILL.md b/plugins/mcp/skills/setup-codemap-cli/SKILL.md index 4a0ba20..acd8db3 100644 --- a/plugins/mcp/skills/setup-codemap-cli/SKILL.md +++ b/plugins/mcp/skills/setup-codemap-cli/SKILL.md @@ -1,4 +1,5 @@ --- +name: mcp:setup-codemap-cli description: Guide for setup Codemap CLI for intelligent codebase visualization and navigation argument-hint: Optional - specific configuration preferences or OS type --- diff --git a/plugins/mcp/skills/setup-context7-mcp/SKILL.md b/plugins/mcp/skills/setup-context7-mcp/SKILL.md index 5f64270..2bd1628 100644 --- a/plugins/mcp/skills/setup-context7-mcp/SKILL.md +++ b/plugins/mcp/skills/setup-context7-mcp/SKILL.md @@ -1,4 +1,5 @@ --- +name: mcp:setup-context7-mcp description: Guide for setup Context7 MCP server to load documentation for specific technologies. argument-hint: List of languages and frameworks to load documentation for --- diff --git a/plugins/mcp/skills/setup-serena-mcp/SKILL.md b/plugins/mcp/skills/setup-serena-mcp/SKILL.md index c21e61c..a638b14 100644 --- a/plugins/mcp/skills/setup-serena-mcp/SKILL.md +++ b/plugins/mcp/skills/setup-serena-mcp/SKILL.md @@ -1,4 +1,5 @@ --- +name: mcp:setup-serena-mcp description: Guide for setup Serena MCP server for semantic code retrieval and editing capabilities argument-hint: Optional - specific configuration preferences or client type --- diff --git a/plugins/reflexion/skills/critique/SKILL.md b/plugins/reflexion/skills/critique/SKILL.md index e9bfc06..6df383a 100644 --- a/plugins/reflexion/skills/critique/SKILL.md +++ b/plugins/reflexion/skills/critique/SKILL.md @@ -1,4 +1,5 @@ --- +name: reflexion:critique description: Comprehensive multi-perspective review using specialized judges with debate and consensus building argument-hint: Optional file paths, commits, or context to review (defaults to recent changes) --- diff --git a/plugins/reflexion/skills/memorize/SKILL.md b/plugins/reflexion/skills/memorize/SKILL.md index aac1768..434fe5d 100644 --- a/plugins/reflexion/skills/memorize/SKILL.md +++ b/plugins/reflexion/skills/memorize/SKILL.md @@ -1,4 +1,5 @@ --- +name: reflexion:memorize description: Curates insights from reflections and critiques into CLAUDE.md using Agentic Context Engineering argument-hint: Optional source specification (last, selection, chat:) or --dry-run for preview --- diff --git a/plugins/reflexion/skills/reflect/SKILL.md b/plugins/reflexion/skills/reflect/SKILL.md index 12c730c..a8438eb 100644 --- a/plugins/reflexion/skills/reflect/SKILL.md +++ b/plugins/reflexion/skills/reflect/SKILL.md @@ -1,4 +1,5 @@ --- +name: reflexion:reflect description: Reflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verification argument-hint: Optional focus area or confidence threshold to use, for example "security" or "deep reflect if less than 90% confidence" --- diff --git a/plugins/sadd/skills/do-and-judge/SKILL.md b/plugins/sadd/skills/do-and-judge/SKILL.md index 25060b1..febef59 100644 --- a/plugins/sadd/skills/do-and-judge/SKILL.md +++ b/plugins/sadd/skills/do-and-judge/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:do-and-judge description: Execute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loop argument-hint: Task description (e.g., "Refactor the UserService class to use dependency injection") --- diff --git a/plugins/sadd/skills/do-competitively/SKILL.md b/plugins/sadd/skills/do-competitively/SKILL.md index 8cc9e0c..554dee2 100644 --- a/plugins/sadd/skills/do-competitively/SKILL.md +++ b/plugins/sadd/skills/do-competitively/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:do-competitively description: Execute tasks through competitive multi-agent generation, multi-judge evaluation, and evidence-based synthesis argument-hint: Task description and optional output path/criteria --- diff --git a/plugins/sadd/skills/do-in-parallel/SKILL.md b/plugins/sadd/skills/do-in-parallel/SKILL.md index a73af5d..c7db215 100644 --- a/plugins/sadd/skills/do-in-parallel/SKILL.md +++ b/plugins/sadd/skills/do-in-parallel/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:do-in-parallel description: Launch multiple sub-agents in parallel to execute tasks across files or targets with intelligent model selection and quality-focused prompting argument-hint: Task description [--files "file1.ts,file2.ts,..."] [--targets "target1,target2,..."] [--model opus|sonnet|haiku] [--output ] --- diff --git a/plugins/sadd/skills/do-in-steps/SKILL.md b/plugins/sadd/skills/do-in-steps/SKILL.md index e95e1f7..e558820 100644 --- a/plugins/sadd/skills/do-in-steps/SKILL.md +++ b/plugins/sadd/skills/do-in-steps/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:do-in-steps description: Execute complex tasks through sequential sub-agent orchestration with intelligent model selection, and LLM-as-a-judge verification argument-hint: Task description (e.g., "Refactor UserService class and update all consumers") --- diff --git a/plugins/sadd/skills/judge-with-debate/SKILL.md b/plugins/sadd/skills/judge-with-debate/SKILL.md index c2ecaf4..970bffc 100644 --- a/plugins/sadd/skills/judge-with-debate/SKILL.md +++ b/plugins/sadd/skills/judge-with-debate/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:judge-with-debate description: Evaluate solutions through multi-round debate between independent judges until consensus argument-hint: Solution path(s) and evaluation criteria --- diff --git a/plugins/sadd/skills/judge/SKILL.md b/plugins/sadd/skills/judge/SKILL.md index 938b412..db03322 100644 --- a/plugins/sadd/skills/judge/SKILL.md +++ b/plugins/sadd/skills/judge/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:judge description: Launch a sub-agent judge to evaluate results produced in the current conversation argument-hint: "[evaluation-focus]" --- diff --git a/plugins/sadd/skills/launch-sub-agent/SKILL.md b/plugins/sadd/skills/launch-sub-agent/SKILL.md index ff9e58c..aa36a33 100644 --- a/plugins/sadd/skills/launch-sub-agent/SKILL.md +++ b/plugins/sadd/skills/launch-sub-agent/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:launch-sub-agent description: Launch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verification argument-hint: Task description (e.g., "Implement user authentication" or "Research caching strategies") [--model opus|sonnet|haiku] [--agent ] [--output ] --- diff --git a/plugins/sadd/skills/multi-agent-patterns/SKILL.md b/plugins/sadd/skills/multi-agent-patterns/SKILL.md index 49cffc2..00d576a 100644 --- a/plugins/sadd/skills/multi-agent-patterns/SKILL.md +++ b/plugins/sadd/skills/multi-agent-patterns/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:multi-agent-patterns description: Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality. --- diff --git a/plugins/sadd/skills/subagent-driven-development/SKILL.md b/plugins/sadd/skills/subagent-driven-development/SKILL.md index 3399abf..50da0f4 100644 --- a/plugins/sadd/skills/subagent-driven-development/SKILL.md +++ b/plugins/sadd/skills/subagent-driven-development/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:subagent-driven-development description: Use when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh subagent for each task with code review between tasks, enabling fast iteration with quality gates --- diff --git a/plugins/sadd/skills/tree-of-thoughts/SKILL.md b/plugins/sadd/skills/tree-of-thoughts/SKILL.md index 5aef11b..3885cef 100644 --- a/plugins/sadd/skills/tree-of-thoughts/SKILL.md +++ b/plugins/sadd/skills/tree-of-thoughts/SKILL.md @@ -1,4 +1,5 @@ --- +name: sadd:tree-of-thoughts description: Execute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with multi-agent evaluation argument-hint: Task description and optional output path/criteria --- diff --git a/plugins/sdd/skills/add-task/SKILL.md b/plugins/sdd/skills/add-task/SKILL.md index 795f5fb..0c75e37 100644 --- a/plugins/sdd/skills/add-task/SKILL.md +++ b/plugins/sdd/skills/add-task/SKILL.md @@ -1,4 +1,5 @@ --- +name: sdd:add-task description: creates draft task file in .specs/tasks/draft/ with original user intent argument-hint: Task title or description (e.g., "Add validation to form inputs") [list of task files that this task depends on] --- diff --git a/plugins/sdd/skills/brainstorm/SKILL.md b/plugins/sdd/skills/brainstorm/SKILL.md index f1732a0..0cf0c17 100644 --- a/plugins/sdd/skills/brainstorm/SKILL.md +++ b/plugins/sdd/skills/brainstorm/SKILL.md @@ -1,4 +1,5 @@ --- +name: sdd:brainstorm description: Use when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incremental validation. Don't use during clear 'mechanical' processes argument-hint: Optional initial feature concept or topic to brainstorm --- diff --git a/plugins/sdd/skills/create-ideas/SKILL.md b/plugins/sdd/skills/create-ideas/SKILL.md index 4593477..e9ab73f 100644 --- a/plugins/sdd/skills/create-ideas/SKILL.md +++ b/plugins/sdd/skills/create-ideas/SKILL.md @@ -1,4 +1,5 @@ --- +name: sdd:create-ideas description: Generate ideas in one shot using creative sampling argument-hint: Topic or problem to generate ideas for. Optional amount of ideas to generate. --- diff --git a/plugins/sdd/skills/implement/SKILL.md b/plugins/sdd/skills/implement/SKILL.md index 878cf88..030e911 100644 --- a/plugins/sdd/skills/implement/SKILL.md +++ b/plugins/sdd/skills/implement/SKILL.md @@ -1,5 +1,6 @@ --- -description: Implement a task with automated LLM-as-Judge verification for critical steps +name: sdd:implement +description: Implement a task with automated LLM-as-Judge verification for critical steps argument-hint: Task file [options] (e.g., "add-validation.feature.md --continue --human-in-the-loop") --- diff --git a/plugins/sdd/skills/plan/SKILL.md b/plugins/sdd/skills/plan/SKILL.md index 9f8d659..7fbe5ca 100644 --- a/plugins/sdd/skills/plan/SKILL.md +++ b/plugins/sdd/skills/plan/SKILL.md @@ -1,4 +1,5 @@ --- +name: sdd:plan description: Refine, parallelize, and verify a draft task specification into a fully planned implementation-ready task argument-hint: Path to draft task file (e.g., ".specs/tasks/draft/add-validation.feature.md") [options] --- diff --git a/plugins/tdd/skills/fix-tests/SKILL.md b/plugins/tdd/skills/fix-tests/SKILL.md index cac368a..e29e2f8 100644 --- a/plugins/tdd/skills/fix-tests/SKILL.md +++ b/plugins/tdd/skills/fix-tests/SKILL.md @@ -1,4 +1,5 @@ --- +name: tdd:fix-tests description: Systematically fix all failing tests after business logic changes or refactoring argument-hint: what tests or modules to focus on --- diff --git a/plugins/tdd/skills/test-driven-development/SKILL.md b/plugins/tdd/skills/test-driven-development/SKILL.md index 37149dd..3ee0c2c 100644 --- a/plugins/tdd/skills/test-driven-development/SKILL.md +++ b/plugins/tdd/skills/test-driven-development/SKILL.md @@ -1,4 +1,5 @@ --- +name: tdd:test-driven-development description: Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures tests actually verify behavior by requiring failure first --- diff --git a/plugins/tdd/skills/write-tests/SKILL.md b/plugins/tdd/skills/write-tests/SKILL.md index 0150ab4..4a0695b 100644 --- a/plugins/tdd/skills/write-tests/SKILL.md +++ b/plugins/tdd/skills/write-tests/SKILL.md @@ -1,4 +1,5 @@ --- +name: tdd:write-tests description: Systematically add test coverage for all local code changes using specialized review and development agents. Add tests for uncommitted changes (including untracked files), or if everything is commited, then will cover latest commit. argument-hint: what tests or modules to focus on --- diff --git a/plugins/tech-stack/skills/add-typescript-best-practices/SKILL.md b/plugins/tech-stack/skills/add-typescript-best-practices/SKILL.md index f19a474..8cebb39 100644 --- a/plugins/tech-stack/skills/add-typescript-best-practices/SKILL.md +++ b/plugins/tech-stack/skills/add-typescript-best-practices/SKILL.md @@ -1,4 +1,5 @@ --- +name: tech-stack:add-typescript-best-practices description: Setup TypeScript best practices and code style rules in CLAUDE.md argument-hint: Optional argument which practices to add or avoid ---