feat(skills): align YAML frontmatter to agentskills.io spec + add eva…#5
Merged
jazz127 merged 1 commit intojazz127:devfrom Apr 6, 2026
Merged
Conversation
…l framework Migrates all 34 skills across .squad/skills/, .copilot/skills/, and templates/skills/ to the agentskills.io specification schema: - name, description, license as top-level fields (spec required) - domain, confidence, source, triggers, roles, compatibility in metadata - tools arrays converted to allowed-tools strings - Skills without frontmatter get complete --- blocks added - Body content of all SKILL.md files unchanged (frontmatter only) Adds three-phase eval framework for skill trigger quality testing: - Phase 1 (run-evals.mjs): keyword matching, 88.9% baseline, CI-ready - Phase 2 (run-llm-evals.mjs): LLM trigger + execution evals via Copilot - Phase 3 (optimize-description.mjs): iterative description optimization - Schema validator, 31 trigger fixtures, 10 execution fixtures - CONTRIBUTING.md, skill-review-checklist, eval README Adds SPAN (Skill Curator) team member for skill quality gating. Spec: https://agentskills.io/specification Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
|
🛫 PR Readiness Check
PR Scope: 🔧 Infrastructure
|
| Status | Check | Details |
|---|---|---|
| ✅ | Single commit | 1 commit — clean history |
| ✅ | Not in draft | Ready for review |
| ❌ | Branch up to date | dev is 39 commit(s) ahead — rebase recommended |
| ❌ | Copilot review | No Copilot review yet — it may still be processing |
| ✅ | Changeset present | No source files changed — changeset not required |
| ✅ | Scope clean | |
| ✅ | No merge conflicts | No merge conflicts |
| ✅ | Copilot threads resolved | No Copilot review threads |
| ❌ | CI passing | 16 check(s) still running |
Files Changed (88 files, +6424 −1001)
| File | +/− |
|---|---|
.copilot/skills/agent-collaboration/SKILL.md |
+8 −3 |
.copilot/skills/agent-conduct/SKILL.md |
+8 −3 |
.copilot/skills/architectural-proposals/SKILL.md |
+9 −10 |
.copilot/skills/ci-validation-gates/SKILL.md |
+8 −3 |
.copilot/skills/cli-wiring/SKILL.md |
+13 −0 |
.copilot/skills/client-compatibility/SKILL.md |
+8 −3 |
.copilot/skills/distributed-mesh/SKILL.md |
+8 −3 |
.copilot/skills/git-workflow/SKILL.md |
+8 −3 |
.copilot/skills/github-multi-account/SKILL.md |
+11 −5 |
.copilot/skills/history-hygiene/SKILL.md |
+10 −5 |
.copilot/skills/init-mode/SKILL.md |
+9 −7 |
.copilot/skills/model-selection/SKILL.md |
+8 −3 |
.copilot/skills/release-process/SKILL.md |
+8 −3 |
.copilot/skills/reskill/SKILL.md |
+8 −3 |
.copilot/skills/reviewer-protocol/SKILL.md |
+8 −3 |
.copilot/skills/secret-handling/SKILL.md |
+10 −5 |
.copilot/skills/squad-conventions/SKILL.md |
+8 −3 |
.squad/agents/span/charter.md |
+38 −0 |
.squad/agents/span/history.md |
+23 −0 |
.squad/casting/registry.json |
+7 −0 |
.squad/routing.md |
+1 −0 |
.squad/skill.md |
+13 −9 |
.squad/skills/CONTRIBUTING.md |
+263 −0 |
.squad/skills/cross-machine-coordination/SKILL.md |
+13 −0 |
.squad/skills/cross-squad/SKILL.md |
+10 −11 |
.squad/skills/economy-mode/SKILL.md |
+9 −4 |
.squad/skills/evals/README.md |
+307 −0 |
.squad/skills/evals/agent-collaboration.eval.yaml |
+46 −0 |
.squad/skills/evals/agent-conduct.eval.yaml |
+46 −0 |
.squad/skills/evals/architectural-proposals.eval.yaml |
+46 −0 |
.squad/skills/evals/ci-validation-gates.eval.yaml |
+46 −0 |
.squad/skills/evals/ci-validation-gates.exec-eval.yaml |
+66 −0 |
.squad/skills/evals/cli-wiring.eval.yaml |
+46 −0 |
.squad/skills/evals/client-compatibility.eval.yaml |
+46 −0 |
.squad/skills/evals/cross-machine-coordination.eval.yaml |
+46 −0 |
.squad/skills/evals/cross-squad.eval.yaml |
+46 −0 |
.squad/skills/evals/distributed-mesh.eval.yaml |
+46 −0 |
.squad/skills/evals/economy-mode.eval.yaml |
+46 −0 |
.squad/skills/evals/economy-mode.exec-eval.yaml |
+63 −0 |
.squad/skills/evals/external-comms.eval.yaml |
+46 −0 |
.squad/skills/evals/external-comms.exec-eval.yaml |
+64 −0 |
.squad/skills/evals/fact-checking.eval.yaml |
+46 −0 |
.squad/skills/evals/gh-auth-isolation.eval.yaml |
+46 −0 |
.squad/skills/evals/gh-auth-isolation.exec-eval.yaml |
+51 −0 |
.squad/skills/evals/git-workflow.eval.yaml |
+46 −0 |
.squad/skills/evals/git-workflow.exec-eval.yaml |
+51 −0 |
.squad/skills/evals/github-multi-account.eval.yaml |
+46 −0 |
.squad/skills/evals/history-hygiene.eval.yaml |
+46 −0 |
.squad/skills/evals/humanizer.eval.yaml |
+46 −0 |
.squad/skills/evals/init-mode.eval.yaml |
+46 −0 |
| ... | +38 more files |
Total: +6424 −1001
This check runs automatically on every push. Fix any ❌ items and push again.
See CONTRIBUTING.md and PR Requirements for details.
🔴 Impact Analysis — PR #5Risk tier: 🔴 CRITICAL 📊 Summary
🎯 Risk Factors
📦 Modules Affectedcopilot-config (17 files)
root (3 files)
squad-state (68 files)
This report is generated automatically for every PR. See #733 for details. |
🏗️ Architectural Review
Automated architectural review — informational only. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
…l framework
Migrates all 34 skills across .squad/skills/, .copilot/skills/, and templates/skills/ to the agentskills.io specification schema:
Adds three-phase eval framework for skill trigger quality testing:
Adds SPAN (Skill Curator) team member for skill quality gating.
Spec: https://agentskills.io/specification
What
Why
How
npx changeset add/.changeset/*.md, directCHANGELOG.mdentry for maintainers, orskip-changeloglabel for no user-facing changes)PR Readiness Checklist
Branch & Commit
dev(notmain)dev(git fetch upstream && git rebase upstream/dev)git diff --cached --stat)Build & Test
npm run buildpassesnpm testpasses (all tests green)npm run lintpasses (type check clean)npm run lint:eslintpassesChangeset
npx changeset add(ifpackages/squad-sdk/src/orpackages/squad-cli/src/changed)CHANGELOG.mdentry (maintainers only — write-protected for external contributors)skip-changeloglabel applied (if no user-facing changes)Docs
Exports
Breaking Changes
Waivers