Repository navigation
feat(skills): add self-audit — four-dimension reasoning quality gate before delivery - #1361
Closed
YuhaoLin2005 wants to merge 7 commits into
Closed
YuhaoLin2005 wants to merge 7 commits into
YuhaoLin2005 wants to merge 7 commits into
Conversation
…rences/patterns.md + evals/evals.json
YuhaoLin2005
changed the title
…ead See-Also, clarify Hard Constraints, expand Verification
Author
Author
|
Apologies — this PR was short-lived because I opened it from my fork's The contribution is now on #1367 with a clean 👉 #1367 |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why this exists
anthropics/skills has skills for almost every task in the development lifecycle — but nothing that checks whether the AI's reasoning itself was sound before shipping.
code-reviewerchecks other people's code.security-reviewchecks for vulnerabilities. This skill checks a different dimension: did the AI actually deliver what was asked, without contradicting itself, rationalizing gaps, or claiming verification it didn't do?What it does
Four questions before shipping:
Relationship to existing skills
code-reviewersecurity-reviewshipping-and-launchExtracted from practice
Derived from a five-library learning-capture workflow used across 200+ sessions. The pattern of "audit before shipping" reduced repeated mistakes measurably — bugs that slipped through one session were caught in the next because the audit habit forced them to surface.