Conversation
There was a problem hiding this comment.
Copilot review overview
🟢 Approval recommended
The catalog entry is properly pinned and no unresolved issues were identified.
Review effort: Balanced
Findings: None
What changed in this PR
Adds Hermes Blind as a contributor-managed AI skill catalog entry pinned to its v0.3.2 release commit.
Changes:
- Adds metadata, description, and discovery tags.
- Uses an immutable definition URL and the
application/ai-skillmedia type.
| File | Description |
|---|---|
catalog/hermes-labs-ai/hermes-blind.json |
Defines the Hermes Blind catalog entry. |
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds the Hermes Blind Claude Code/Codex recovery skill as one contributor-managed catalog entry.
The definition URL is publicly retrievable and pinned to the v0.3.2 release commit,
a1ae08ed555c079dde22da3a17466b5881e596a3. The identifier, media type, description, tags, and metadata remain unchanged.The earlier pin's skill selected CLI 0.3.0. This update is justified by 0.3.2's session-discovery fix: an isolated CLI comparison with the same log under a literal symlinked project path fails on 0.3.0 and produces the expected anchor on 0.3.2. The skill still supports an existing CLI on PATH and explicit-session fallback.
Validation:
python3 -m unittest discover -s tests: 19 tests pass.python3 scripts/generate_ai_catalog.pyand--checkpass against the live MCP catalog (2,144 total entries at validation time).application/ai-skilltype.Hosted CI at head
a20c416: Catalog and CodeQL both reportaction_requiredwith zero jobs run. Maintainer action is needed before hosted checks can execute; the passing results above are local validation.Only
catalog/hermes-labs-ai/hermes-blind.jsonis submitted. Generated aggregate changes were used for validation and left to the repository's regeneration workflow, avoiding unrelated live MCP catalog churn. This is a discovery entry for a local skill, not a hosted MCP service or a claim of measured behavioral recovery.Affiliation: Hermes Blind is maintained by Hermes Labs.
Rolando Bosch is the responsible human contributor. This contribution was selected through Hermes Labs’ autonomous triage and executed through its engineering infrastructure.