Repository navigation
Make the first Skill Forge audit easier to try and understand - #2
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Skill authors can now start with a compact audit prompt and see a reproducible example before reading the detailed installation and release procedures.
The README leads with the user outcome and links to a synthetic meeting-notes demonstration. Its recorded inspector results show a missing dependency failing, then static inspection passing while contradictory instructions remain. Qualitative findings and unmeasured agent behavior are explicitly separated. Exact inputs, inspector hashes, selected output fields, and reproduction instructions are included. The optional human examples are registered in SKILL.md and its matching contract inventory, within the existing 1,000-word limit. Inspector and runtime behavior are unchanged.
Validation: all three documented runs reproduced every recorded field and expected exit code (2, 0, 0); hashes and relative links checked; a synthetic documentation wrapper verified that example paths do not become package dependencies; staged whitespace check passed; strict privacy scan passed for all 70 indexed files. Separate documentation review found no actionable issues. The seven-job PR CI run passed, including the Linux containment suite and source/build/archive-verification/packaged-runtime checks on Ubuntu, macOS, and Windows with Python 3.9 and current stable Python.