Add evidence-based agent instructions audit skill 馃馃馃 - #2271
Closed
fablerlabs wants to merge 1 commit into
Closed
Add evidence-based agent instructions audit skill 馃馃馃#2271fablerlabs wants to merge 1 commit into
fablerlabs wants to merge 1 commit into
Conversation
github-actions
Bot
added
new-submission
Contributor
|
馃煛 Contributor Reputation Check: MEDIUM risk
Maintainers: please review this contributor before merging. |
github-actions
Bot
added
the
needs-review:MEDIUM
selutions
approved these changes
Jul 11, 2026
Contributor
|
This doesn't provide much upskill on the agent so we won't be accepting it. |
edburns
added a commit
to edburns/awesome-copilot
that referenced
this pull request
Aug 6, 2026
The polling loop in Step 3 only checked for copilot_work_finished, ignoring copilot_work_finished_failure. When CCA timed out internally (as in PR github#2272 for issue github#2271), the shepherd burned the full 2-hour timeout waiting for an event that would never arrive. Now: detect copilot_work_finished_failure, check if CCA produced substantive work despite the failure, and either proceed with validation or re-assign CCA for another attempt. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: d7a38160-a65e-4d0c-9087-4f28da2a51b8
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
agent-instructions-auditfor evidence-based review ofAGENTS.md,.github/copilot-instructions.md, andCLAUDE.mdWhy this is distinct
This skill audits existing agent instructions against repository evidence. It does not generate another instructions file: its purpose is to catch stale commands, missing repository maps, unverifiable claims, conflicting instruction files, and absent verification loops, then provide concrete replacement text.
Affiliation
Submitted by Fabler Labs, the author and maintainer of the source skill. The source-repository metadata is included for provenance; the skill is self-contained and requires no external or paid service.
Validation
bash eng/fix-line-endings.shnpm run skill:validate- all 372 skills validspec-compliance,valid-refs)npm run build- generated thedocs/README.skills.mdinstall entrycopilot skill addandcopilot skill list --jsonrecognized the skill and bundled pathgit diff --check