fix: add names to all skills

.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",

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)

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

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:

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

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 -- <TASK_FILE>`
+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 <requirement change>`. The agent incorporates your change and re-runs affected stages.
+
 | Modified Section | Re-run From Stage |
 |------------------|-------------------|
 | Description / Acceptance Criteria | `business analysis` (Phase 2c) |

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 <requirement change>
+```
+
+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
+```

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

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]"
 ---

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.
 ---
 

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
 ---

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.
 ---
 

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

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
 ---

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
 ---

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
 
 ---

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:*)

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.
 ---
 

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
 ---
 

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
 ---
 

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
 ---
 

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
 ---

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. 
 ---
 

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
 ---

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.
 ---
 

plugins/fpf/commands/actualize.md → plugins/fpf/skills/actualize/SKILL.md

@@ -1,4 +1,5 @@
 ---
+name: fpf:actualize
 description: "Reconcile the project's FPF state with recent repository changes"
 ---
 

plugins/fpf/commands/decay.md → 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"
 ---
 

plugins/fpf/commands/propose-hypotheses.md → 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