update eval-driven-dev skill.#1201
Merged
aaronpowell merged 2 commits intogithub:stagedfrom Mar 29, 2026
Merged
Conversation
Split SKILL into multi-level to keep the skill body under 500 lines, rewrite instructions.
Contributor
There was a problem hiding this comment.
Pull request overview
Updates the eval-driven-dev skill by splitting detailed guidance into multiple reference docs and rewriting the main SKILL workflow to be shorter and more step-focused.
Changes:
- Restructures
skills/eval-driven-dev/SKILL.mdinto a concise 6-step workflow with pointers to new reference docs. - Adds new reference markdown files covering understanding the app, instrumentation, run harness patterns, dataset generation, eval tests, and investigation.
- Updates
docs/README.skills.mdto reflect the new skill description and list all reference files.
Reviewed changes
Copilot reviewed 9 out of 9 changed files in this pull request and generated 8 comments.
Show a summary per file
| File | Description |
|---|---|
| skills/eval-driven-dev/SKILL.md | Rewritten main skill workflow; now references step-specific docs. |
| skills/eval-driven-dev/references/understanding-app.md | New Step 1 deep-dive + MEMORY.md template. |
| skills/eval-driven-dev/references/instrumentation.md | New Step 2 tactical instrumentation guidance + anti-patterns. |
| skills/eval-driven-dev/references/run-harness-patterns.md | New Step 3 end-to-end harness patterns by app type. |
| skills/eval-driven-dev/references/dataset-generation.md | New Step 4 dataset creation guidance + validation checklist. |
| skills/eval-driven-dev/references/eval-tests.md | New Step 5 evaluator selection + test writing guidance. |
| skills/eval-driven-dev/references/investigation.md | New Step 6 iteration/investigation playbook. |
| skills/eval-driven-dev/references/pixie-api.md | Expanded API/CLI reference and evaluator catalog; adds “auto-generated” note. |
| docs/README.skills.md | Updates the skill entry description and enumerates reference files. |
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
aaronpowell
approved these changes
Mar 29, 2026
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
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.
Split SKILL into multi-level to keep the skill body under 500 lines, rewrite instructions.
Pull Request Checklist
npm startand verified thatREADME.mdis up to date.stagedbranch for this pull request.Description
Update eval-driven-dev skill.
Restructured into multi-level instructions to keep the main SKILL.md under 500 lines. Rewrite various sections of the skill for better clarity.
Type of Contribution
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.