update eval-driven-dev skill

[yiouli]

Pull Request Checklist

• I have read and followed the CONTRIBUTING.md guidelines.
• I have read and followed the Guidance for submissions involving paid services.
• My contribution adds a new instruction, prompt, agent, skill, or workflow file in the correct directory.
• The file follows the required naming convention.
• The content is clearly structured and follows the example format.
• I have tested my instructions, prompt, agent, skill, or workflow with GitHub Copilot.
• I have run npm start and verified that README.md is up to date.
• I am targeting the staged branch for this pull request.

---

Description

Update eval-driven-dev skill: Adding comprehensive analysis step after evaluation runs.

---

Type of Contribution

• New instruction file.
• New prompt file.
• New agent file.
• New plugin.
• New skill file.
• New agentic workflow.
• Update to existing instruction, prompt, agent, plugin, skill, or workflow.
• Other (please specify):

---

Additional Notes

---

By submitting this pull request, I confirm that my contribution abides by the Code of Conduct and will be licensed under the MIT License.

[github-actions]

🔍 Skill Validator Results

⚠️ Warnings or advisories found

Scope	Checked
Skills	1
Agents	1
Total	2
Severity	Count
---	---:
❌ Errors	0
⚠️ Warnings	2
ℹ️ Advisories	0

Summary

Level	Finding
ℹ️	Found 1 skill(s)
ℹ️	[eval-driven-dev] 📊 eval-driven-dev: 3,768 BPE tokens [chars/4: 4,311] (standard ~), 16 sections, 1 code blocks
ℹ️	[eval-driven-dev] ⚠ Skill is 3,768 BPE tokens (chars/4 estimate: 4,311) — approaching "comprehensive" range where gains diminish.
ℹ️	[eval-driven-dev] ⚠ No numbered workflow steps — agents follow sequenced procedures more reliably.
ℹ️	✅ All checks passed (1 skill(s))

Full validator output

```text Found 1 skill(s) [eval-driven-dev] 📊 eval-driven-dev: 3,768 BPE tokens [chars/4: 4,311] (standard ~), 16 sections, 1 code blocks [eval-driven-dev] ⚠ Skill is 3,768 BPE tokens (chars/4 estimate: 4,311) — approaching "comprehensive" range where gains diminish. [eval-driven-dev] ⚠ No numbered workflow steps — agents follow sequenced procedures more reliably. ✅ All checks passed (1 skill(s)) ```

[Copilot]

Pull request overview

Updates the eval-driven-dev skill to align with newer pixie-qa concepts (notably input_data, agent evaluators, and structured post-run analysis) and expands the skill’s references to include a dedicated Step 6 analysis workflow and runnable implementation examples.

Changes:

• Updates the skill metadata and setup workflow to target pixie-qa >=0.8.1,<0.9.0 and revises setup/error-handling guidance.
• Refactors the skill’s step-by-step reference docs (new Step 1a project analysis, split Step 2, new Step 6 “Analyze Outcomes”, removal of older combined/iteration docs).
• Adds runnable examples (standalone function, FastAPI, CLI) and updates API reference docs to reflect the newer dataset shapes (input_data etc.).

Reviewed changes

Copilot reviewed 22 out of 22 changed files in this pull request and generated 12 comments.

Show a summary per file

File	Description
skills/eval-driven-dev/resources/setup.sh	Updates install/upgrade logic and adds stricter failure handling for pixie init/start.
skills/eval-driven-dev/references/wrap-api.md	Updates wrap API reference and CLI wording (including dataset field naming).
skills/eval-driven-dev/references/testing-api.md	Updates testing API reference to match new dataset schema and runner behavior.
skills/eval-driven-dev/references/evaluators.md	Adds create_agent_evaluator reference and updates evaluator selection guidance.
skills/eval-driven-dev/references/6-investigate.md	Removes prior Step 6 “investigate/iterate” reference.
skills/eval-driven-dev/references/6-analyze-outcomes.md	Adds new structured, multi-phase Step 6 analysis workflow and required outputs.
skills/eval-driven-dev/references/5-run-tests.md	Reframes Step 5 as “run tests and fix mechanical issues” and updates commands/content.
skills/eval-driven-dev/references/4-build-dataset.md	Updates dataset schema (input_data), adds realism audits, and expands capture guidance.
skills/eval-driven-dev/references/3-define-evaluators.md	Shifts evaluator strategy toward agent evaluators and updates mapping guidance.
skills/eval-driven-dev/references/2c-capture-and-verify-trace.md	Adds a dedicated sub-step doc for trace capture and verification.
skills/eval-driven-dev/references/2b-implement-runnable.md	Adds a dedicated sub-step doc for Runnable implementation and placement.
skills/eval-driven-dev/references/2a-instrumentation.md	Adds a dedicated sub-step doc for wrap() instrumentation practices.
skills/eval-driven-dev/references/2-wrap-and-trace.md	Removes older combined Step 2 reference.
skills/eval-driven-dev/references/1-c-eval-criteria.md	Adds updated eval criteria guidance tied to project analysis and failure modes.
skills/eval-driven-dev/references/1-b-eval-criteria.md	Removes older Step 1b eval criteria reference.
skills/eval-driven-dev/references/1-b-entry-point.md	Renumbers/updates entry-point documentation and emphasizes capability prioritization.
skills/eval-driven-dev/references/1-a-project-analysis.md	Adds new Step 1a project analysis reference and required outputs.
skills/eval-driven-dev/references/runnable-examples/standalone-function.md	Adds runnable example for direct function invocation.
skills/eval-driven-dev/references/runnable-examples/fastapi-web-server.md	Adds runnable example for FastAPI/ASGI in-process evaluation.
skills/eval-driven-dev/references/runnable-examples/cli-app.md	Adds runnable example for CLI subprocess execution.
skills/eval-driven-dev/SKILL.md	Updates skill description/versioning and rewrites the step flow to include analysis.
docs/README.skills.md	Updates the skills index entry for eval-driven-dev to match the new references list.