Audit all skill instructions for Astra and Fable - #43
Conversation
Revise all 24 skills and their active supporting flows around the requested outcome. Remove redundant intake and approval loops, preserve domain methods and evidence, and keep external actions within the authorized scope. Correct CLI examples, installed paths, credential setup, repository-cache preservation, and migration recovery guidance. Simplify the two meta skills, align authoring templates and release docs, and record retention decisions and verification in the audit report.
|
Important
This repository does not receive automatic reviews because it has fewer than 10 stars. ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Advanced Run ID: Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b01407b2c1
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
1 participant
A complete request could still stall on mandatory intake, repeated confirmation, or a conflicting instruction hidden in a nested skill file. This audits all 24 skills and the shared authoring guidance against the current GPT-6 Astra and Claude Fable 5.1 guidance.
The final behavior keeps every skill because each still carries distinct domain knowledge, tooling, or a useful deliverable. It removes compulsory setup and approval loops, narrows overlapping triggers, keeps authorized work moving, preserves source-grounded coaching, and fixes command, path, credential, cache, backup, and external-action boundaries. The shared templates and release docs now agree with those rules and retain the concrete runbook details needed to publish safely.
A Fable 5.1 review covered the full 87-file audit, then a second focused Fable pass checked the corrections. The accepted findings fixed cross-file contradictions in Flight Planner, Customer Discovery, Leadership Coach, Notify, PDF to Markdown, Doc Review Viewer, generated-skill paths, coaching templates, and the release workflow. The audit report records the retention rationale, scope, and limitations.
Validation: all repository version, feedback, inventory, name, path, and diff checks pass; 57 local Markdown links resolve; pytest passes 195 tests with 1 skip; migration validation passes 27/27 cases; and the Node migration-note smoke test passes. The documented GitHub branch protection, merge, Actions-permission, Dependabot, and secret-scanning baseline was also verified through read-only API calls.
No live skill installation or npm release was performed.