Menu
Claim the next issue from the backlog — picks highest priority todo, moves it to in-progress
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
Run a remote Trinity agent task in a sequential, bounded loop — a fixed number of iterations or until a stop signal, with optional response chaining. Fires server-side via run_agent_loop (caller can disconnect), then polls and renders progress. The remote, durable counterpart to Claude Code's local /loop. Add `local` to run the same bounded loop natively in this session instead — inline back-to-back iterations, or a hand-off to the built-in /loop when a cadence is given.
Make any agent a system-aware orchestrator — installs /discover-agents (discover the fleet from live Trinity and/or a repo list into a descriptive fleet/system-map.yaml), /compose-system (turn the map into a Trinity SystemManifest and deploy_system), and /orchestrate (route, fan out, and run ephemeral agents via Trinity MCP). Aligns with Trinity's existing SystemManifest; no parallel standard.
Create a new skill or playbook. Guides through requirements gathering and generates the appropriate template based on complexity.
Create an executive chief of staff agent — asks about your tools, team, and priorities, then scaffolds a Trinity-compatible agent for daily briefings, meeting prep, and decision tracking
Create a personal medical-records agent — bootstraps a profile from your existing health documents, then ingests new files, maintains structured memory, tracks lab trends, prepares doctor visits, and runs an evidence-based nutrition + supplement framework
Create a content writer agent — asks about your brand voice, platforms, and topics, then scaffolds a Trinity-compatible ghostwriter agent that writes in your voice
| name | claim |
| description | Claim the next issue from the backlog — picks highest priority todo, moves it to in-progress |
| argument-hint | [issue-number] |
| allowed-tools | Bash, Read |
| user-invocable | true |
| metadata | {"version":"1.0","created":"2026-04-28T00:00:00.000Z","author":"Ability.ai","changelog":["1.0: Initial version — claims the highest-priority todo from the GitHub Issues backlog and moves it to in-progress"]} |
ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of
metadata.changelogabove — e.g.claim vX.Y — recent: <summary>. Then proceed.
Select the next issue from the GitHub Issues backlog and mark it as in-progress.
| Source | Location | Read | Write | Description |
|---|---|---|---|---|
| GitHub Issues | Current repo | Yes | Yes | Task backlog |
| GitHub Labels | status:, priority:, skill:* | Yes | Yes | Update status |
gh CLI installed and authenticated (gh auth status)/backlog to check/create)gh issue list --label "status:in-progress" --state open --json number,title --limit 1
If an issue is already in-progress, report it and ask:
If specific issue number provided ($ARGUMENTS):
gh issue view $ARGUMENTS --json number,title,body,labels,state
Verify it exists and is open.
If no argument — find highest priority todo:
# Try P0 first
gh issue list --label "priority:p0" --label "status:todo" --state open --json number,title,body,labels --limit 1
# If none, try P1
gh issue list --label "priority:p1" --label "status:todo" --state open --json number,title,body,labels --limit 1
# If none, try P2
gh issue list --label "priority:p2" --label "status:todo" --state open --json number,title,body,labels --limit 1
# If none, try any status:todo
gh issue list --label "status:todo" --state open --json number,title,body,labels --limit 1
gh issue edit $ISSUE_NUMBER --remove-label "status:todo" --add-label "status:in-progress"
gh issue comment $ISSUE_NUMBER --body "Claimed — starting work."
Display the full issue. If a skill:* label is present, surface it prominently:
## Claimed: #$NUMBER — $TITLE
**Priority:** $PRIORITY
**Skill scope:** $SKILL_LABEL → open `.claude/skills/$SKILL_NAME/SKILL.md`
### Requirements
$ISSUE_BODY
---
Next steps:
- Run `/autoplan` to analyze the change before implementing
- Or run `/adjust-playbook $SKILL_NAME` / `/create-playbook` directly
- When done, run `/commit` to close this issue
If no skill:* label present, note: "No skill tag — run /groom to tag this issue, or proceed with /autoplan."
status:in-progress| Error | Action |
|---|---|
| No open issues | Report "Backlog is empty" |
| Issue not found | Report issue number not found |
| Already in-progress | Ask user how to proceed |
| Label update fails | Report error, check permissions |