toolkit/packages/skills/gh-issue/SKILL.md
Analyze and fix the specified GitHub issue
npx skillsauth add stevengonsalvez/agents-in-a-box gh-issueInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Analyze and fix the specified GitHub issue: $ARGUMENTS
Follow these steps:
<!-- recall:begin -->Before fixing the issue, recall prior learnings from the global knowledge base so we don't re-learn or re-decide something already captured:
uv run "{{HOME_TOOL_DIR}}/skills/recall/scripts/recall.py" \
"<QUERY>" \
--limit 5 --format markdown
Query construction for /gh-issue: issue title + top labels + repo name (e.g. "flaky signup test frontend auth").
What to do with results:
Get issue details:
gh issue view $ARGUMENTS to get the complete issue informationgh issue list and ask which to work onUnderstand the problem:
Search the codebase:
Plan and comment your approach:
gh issue comment $ARGUMENTS --body "Implementation plan: ..."Create a development branch:
git checkout -b fix/issue-$ARGUMENTS-{description}Implement the fix:
Verify the solution:
npm test or equivalentnpm run lint, npm run typecheckCreate a pull request:
gh pr create --title "Fix #$ARGUMENTS: {description}" --body "Closes #$ARGUMENTS"Keep the issue open until the pull request is merged
Remember: Use the GitHub CLI (gh) for all GitHub-related tasks and reference the issue number in commits and PR.
documentation
Report reflect drain spend over a time window — tokens split by cached (cache_read), uncached writes (cache_creation), and io (input+output), with a $ estimate, grouped by day / outcome / model / transcript. Reads the drainer's cost log and surfaces outlier runs and cache-reuse health (the 41.5M-token failure mode = low cache reuse + high cache writes). Use to answer "what is reflection costing me" for the last day / week.
development
Show fleet status — every claude session running on the host, merged across ainb + claude-peers broker + background jobs. Use when you need to enumerate sessions before composing an action, see which sessions have a peer registered (broker-routable) vs tmux-only, check the `summary` of each session, or pipe the list into jq for filtering. Default output: text table. Pass --format json for LLM consumption.
testing
Ordered multi-step prompts to fleet targets, ack-gated between steps via JSONL assistant-turn-end detection. Use for cycles like disconnect→reconnect→verify, or any flow where step N+1 requires step N to have completed first. The skill BLOCKS until each target's transcript shows the next assistant turn finishing OR per-step timeout fires (default 300s).
development
Center control panel — enumerate every claude session that is blocked waiting on something: a user answer (AskUserQuestion fired), an API error retry, an idle assistant turn-end with no follow-up, or an explicit WAITING: marker. Returns rich JSON with signal kind + context per session. Use this when you've stepped away from the fleet and want one place to see everything that wants your attention and answer it.