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, with streamlined workflow, and optimized instruction loading with optional reference files that only loads when needed.

---

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

2 resource(s) checked | ✅ All checks passed

Full output

Found 1 skill(s)
[eval-driven-dev] 📊 eval-driven-dev: 2,839 BPE tokens [chars/4: 3,135] (standard ~), 14 sections, 4 code blocks
[eval-driven-dev]    ⚠  Skill is 2,839 BPE tokens (chars/4 estimate: 3,135) — approaching "comprehensive" range where gains diminish.
[eval-driven-dev]    ⚠  No numbered workflow steps — agents follow sequenced procedures more reliably.
�[32m✅ All checks passed (1 skill(s))�[0m

[Copilot]

Pull request overview

Updates the eval-driven-dev skill to a newer pixie-qa version and restructures the workflow into smaller, step-scoped reference documents, with helper scripts for setup and background process management.

Changes:

• Bumped skill metadata to version: 0.4.0 and documented pixie-qa version/source.
• Refactored the skill workflow into Steps 1–7 with per-step reference docs (and added generated API references).
• Added resources/ shell scripts to automate setup, background server start, and server stop; updated docs/README.skills.md references accordingly.

Reviewed changes

Copilot reviewed 26 out of 26 changed files in this pull request and generated 7 comments.

Show a summary per file

File	Description
skills/eval-driven-dev/SKILL.md	Updates workflow structure, adds setup/stop guidance, bumps metadata/version.
skills/eval-driven-dev/resources/setup.sh	Automates skill update, pixie-qa install/upgrade, pixie init, and starts web UI server.
skills/eval-driven-dev/resources/stop-server.sh	Attempts to stop pixie web UI server based on a lock-file/port.
skills/eval-driven-dev/resources/run-with-timeout.sh	Utility to run a command in background and kill it after a timeout.
skills/eval-driven-dev/references/understanding-app.md	Removes legacy Step 1 reference (replaced by new Step 1a/1b/1c refs).
skills/eval-driven-dev/references/run-harness-patterns.md	Removes legacy run harness patterns reference (replaced by new Step 3 + examples).
skills/eval-driven-dev/references/pixie-api.md	Removes legacy pixie API reference (replaced by generated API refs).
skills/eval-driven-dev/references/instrumentation.md	Removes legacy instrumentation reference (replaced by Step 2 + instrumentation API ref).
skills/eval-driven-dev/references/eval-tests.md	Removes legacy eval tests reference (replaced by Step 4–6 + generated refs).
skills/eval-driven-dev/references/dataset-generation.md	Removes legacy dataset generation reference (replaced by Step 5 ref).
skills/eval-driven-dev/references/1-a-entry-point.md	Adds new Step 1a entry-point artifact guidance.
skills/eval-driven-dev/references/1-b-data-flow.md	Adds new Step 1b DAG artifact guidance.
skills/eval-driven-dev/references/1-c-eval-criteria.md	Adds new Step 1c eval criteria artifact guidance.
skills/eval-driven-dev/references/2-instrument-and-observe.md	Adds new Step 2 instrumentation/trace/DAG validation workflow.
skills/eval-driven-dev/references/3-run-harness.md	Adds new Step 3 run harness contract + pointers to examples.
skills/eval-driven-dev/references/run-harness-examples/fastapi-web-server.md	Adds FastAPI harness example and concurrency/lifespan notes.
skills/eval-driven-dev/references/run-harness-examples/cli-app.md	Adds CLI harness example.
skills/eval-driven-dev/references/run-harness-examples/standalone-function.md	Adds standalone-function harness example.
skills/eval-driven-dev/references/4-define-evaluators.md	Adds new Step 4 evaluator mapping + custom evaluator guidance.
skills/eval-driven-dev/references/evaluators.md	Adds generated built-in evaluator catalog and rules.
skills/eval-driven-dev/references/testing-api.md	Adds generated testing API reference and dataset JSON format.
skills/eval-driven-dev/references/instrumentation-api.md	Adds generated instrumentation API reference and CLI commands.
skills/eval-driven-dev/references/5-build-dataset.md	Adds new Step 5 dataset JSON build/validate guidance.
skills/eval-driven-dev/references/6-run-tests.md	Adds new Step 6 test execution + analysis guidance.
skills/eval-driven-dev/references/7-investigation.md	Updates investigation workflow to Step 7 and adds a stop/continue gate.
docs/README.skills.md	Updates listed reference files/dirs for the skill.