agent-environment-retr…
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.
Use when the user asks to find PRs to review or check the team review queue. Not for summarizing or resolving feedback on a specific PR: use resolve. Read-only.
$ npx -y skills add OutlineDriven/odin-claude-plugin --skill gh-review-requests --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/gh-review-requestsContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when the user asks to find PRs to review or check the team review queue. Not for summarizing or resolving feedback on a specific PR: use resolve. Read-only.
name: gh-review-requests description: 'Use when the user asks to find PRs to review or check the team review queue. Not for summarizing or resolving feedback on a specific PR: use resolve. Read-only.'
| Field | Bound contract | |---|---| | Trigger | User asks to find PRs to review, show review requests, or check the team review queue. | | Authority | Read-only. No file, VCS, credential, paid, published, deployed, or remote mutation. | | Side effect | Fetches unread GitHub review-request notifications and filters by team; emits chat output only. | | Done | A table of open PRs needing review with URLs and reasons, or a no-results report, is returned. |
1. Verify `gh` is authenticated by running `gh auth status`. If it is not, stop and report the auth failure class; do not attempt to write credentials. Done when: `gh` is authenticated or the auth failure is reported. 2. Fetch unread notifications with reason `review_requested`: run `gh api --paginate /notifications` and keep entries where `reason == "review_requested"` and `unread == true`. Done when: unread review-requested notifications are fetched. 3. For each retained notification, resolve the subject URL into the PR record with `gh pr view <number> --repo <owner/repo> --json number,title,author,url,reviewRequests` to obtain title, author, URL, and the review request teams. Done when: every retained notification is resolved into a PR record. 4. If a team filter is supplied, keep only PRs whose `reviewRequests` include that team slug or one of its members; resolve members with `gh api /orgs/<org>/teams/<slug>/members` when the filter is a team slug. Done when: the team filter is applied or confirmed absent. 5. If a repository scope is supplied, drop any PR whose repository is not in the supplied set. Done when: the repository filter is applied or confirmed absent. 6. Build a table with columns: Repository, PR (title and number), Author, URL, Reason (e.g., "review requested", "team: <slug>"). Done when: the table is built with all five columns. 7. If the table is empty, return a no-results report stating that no unread review requests matched the filters. Done when: the table or no-results report is returned.
A chat-output table of open PRs needing review, one row per PR, with Repository, PR, Author, URL, and Reason columns; or a no-results report when no unread review requests match the filters, partial results labeled as such.
Formerly the ODIN Claude Plugin. The repository URL is unchanged. Outline-Driven Development, nicknamed ODIN, is a highly opinionated code-agent skill library: principles-first engineering, surgical editing, and workflow automation, published as installable
Repo: OutlineDriven/odin-claude-plugin
Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.
Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential,…
Use when a human explicitly asks for a full repository agent-compatibility pass returning a scored report with prioritized fixes. Not for tasks that require…
Use when setting up a project, auditing agent command permissions, or asking which read-only bash commands and domains to allow. Not for remote, credential,…
Use when asked to build or review a CLI intended for coding agents and return flag-driven, pipeline-safe, idempotent design advice. Not for running or…
Use when the user asks to make the skills framework work in a new harness, IDE, or CLI. Not for remote, credential, publish, deploy, or irreversible changes.