Uh oh!
There was an error while loading. Please reload this page.
docs(skill): add the first automation eval — ADR-0044 revise loop - #2300
Merged
Conversation
Adds skills/objectstack-automation/evals/approvals/test-revise-loop.md, the first concrete eval under the skills' (previously placeholder) evals/ format — Scenario / Expected Output / Common Mistakes / Validation Criteria. It pins the expected send-back-for-revision shape (revise branch + signal wait + type:'back' resubmit + maxRevisions), the three footguns the compile-time lint flags, and registerFlow- based pass criteria. This is the authorable (a) half of #2274's eval slice. The executable eval RUNNER (b) remains a separate platform project — the skills' evals/ harness is still "not yet implemented" per each dir's README. Refs #2274, #1770 (ADR-0044). Builds on the lint (#2279) and skill (#2294). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Uh oh!
There was an error while loading. Please reload this page.
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 freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What & why
Part of #2274 (ADR-0044 AI-authoring awareness). Adds the first concrete eval under the skills'
evals/directories — until now everyskills/*/evals/held only a placeholder README documenting the intended format.skills/objectstack-automation/evals/approvals/test-revise-loop.mdfollows that documented format:revisebranch → signalwaitnode → resubmit edge typedtype: 'back'+maxRevisions(mirrorsshowcase_budget_approval).lint-flow-patternsrules from feat(cli): lint ADR-0044 approval revise-loop footguns at compile time #2279,registerFlow, design review).registerFlow-registers + revise branch + back-edge + wait window +maxRevisions >= 1+ no lint findings.Closes the authorable half of #2274's eval slice: it pins, as a checkable spec, the behaviour the skill (#2294) teaches and the lint (#2279) enforces.
Scope (important)
This is the eval spec (markdown), not an executable runner. The skills' eval harness does not exist yet — every
evals/README.mdsays "Not yet implemented." Building a runner that feeds prompts through the agent, registers the output, and scores pass-rate across runs is a separate platform project (it benefits all skills and involves non-deterministic-LLM CI concerns). Tracked as the remaining (b) item on #2274.Verification
check:doc-authoring✓ (164 files clean) ·check:skill-docsin-sync ✓ · markdown-only, no changeset (matches prior skill-doc PRs).Refs #2274, #1770. 🤖 Generated with Claude Code