agni-kai
Zuko's Agni Kai for bakeoffs. The formal firebending duel, where competing implementations fight under the same rules and a judge…
Appa's messenger hawk for PR feedback. Hawky, Sokka's messenger hawk, flies out and brings the letters home. Use for get-pr-comments, /get-pr-comments, "what did the reviewers say", "summarize the PR comments", "fetch the review comments", or "what's left on this PR". Fetches
$ npx -y skills add tmcfarlane/team-avatar --skill messenger-hawk --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/messenger-hawkContext preview
The summary Claude sees to decide when to auto-load this skill.
Appa's messenger hawk for PR feedback. Hawky, Sokka's messenger hawk, flies out and brings the letters home. Use for get-pr-comments, /get-pr-comments, "what did the reviewers say", "summarize the PR comments", "fetch the review comments", or "what's left on this PR". Fetches
name: messenger-hawk description: Appa's messenger hawk for PR feedback. Hawky, Sokka's messenger hawk, flies out and brings the letters home. Use for get-pr-comments, /get-pr-comments, "what did the reviewers say", "summarize the PR comments", "fetch the review comments", or "what's left on this PR". Fetches review and discussion comments on the active PR, groups them by severity and actionability, and returns an ordered action list.
Sokka's messenger hawk, Hawky, flies out to the camp and comes back with every letter. He does not answer the letters. He brings them home, sorted, so the team can decide what to do. Fetch the feedback on a PR the same way, and hand back a clear list.
1. **Resolve the active PR.** Use the PR the user named, or the one for the current branch.
gh pr view --json number,url,headRefName,reviewDecision
2. **Fetch review comments and discussion comments.** Get all three kinds. Discussion comments and review summaries:
gh pr view <number> --json comments,reviews
Inline review comments, with file and line:
gh api --paginate "repos/<owner>/<repo>/pulls/<number>/comments"
Thread resolution state, so resolved threads drop out of the action list:
gh api graphql -f query='query($owner:String!,$repo:String!,$number:Int!){repository(owner:$owner,name:$repo){pullRequest(number:$number){reviewThreads(first:100){nodes{isResolved isOutdated comments(first:20){nodes{author{login} body path line url}}}}}}}' -F owner=<owner> -F repo=<repo> -F number=<number>On Origin, use `origin pr view <pr> --comments` and `origin pr thread list <pr>` instead. 3. **Group the feedback by severity and actionability.** Separate a blocker (a correctness, security, or data bug) from a suggestion and a nit. Mark which comments came from a human and which from a review bot. Bot findings get the fix, dismiss, or ask classification from [review-bot-triage.md](../yip-yip/references/review-bot-triage.md). 4. **Return an ordered action list.** Blockers first, then requested changes, then suggestions and nits.
Team Avatar: a universal agent orchestrator for Claude Code, Codex, and Cursor. Nine Avatar characters, 58 engineering skills. pstack with Avatar characters on top.
Zuko's Agni Kai for bakeoffs. The formal firebending duel, where competing implementations fight under the same rules and a judge…
Aang showing a new friend around the team. Explains Team Avatar to a user, the roster and who owns what, how to invoke a skill on…
Aang's operating mode for Team Avatar, principal-level engineering where each task goes to the character who owns that…
Aang choosing which bender takes which fight. Configures which model each Team Avatar character runs on, the default reasoning…
Sokka's battle map, the decision trail he keeps so anyone can see how the campaign was won. Use for show-me-your-work,…
Appa's morning departure for picking up paused or handed-off work. The team breaks camp, reads the map they left, and flies on…