القائمة
Human-supervised development cycle — orchestrates roadmap → claim → autoplan → implement → commit for one skill issue
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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 | sprint |
| description | Human-supervised development cycle — orchestrates roadmap → claim → autoplan → implement → commit for one skill issue |
| argument-hint | [issue-number] |
| allowed-tools | Bash, Read, Skill |
| automation | manual |
| user-invocable | true |
| metadata | {"version":"1.0","created":"2026-04-28T00:00:00.000Z","author":"Ability.ai","changelog":["1.0: Initial version — human-supervised cycle orchestrating roadmap → claim → autoplan → implement → commit for one skill issue"]} |
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.sprint vX.Y — recent: <summary>. Then proceed.
Walks through one complete agent development cycle for a single issue. The implement step is intentionally human-driven — this skill frames and bookends it. The autonomous equivalent is /work-loop.
Invoke /roadmap to show the skill-grouped backlog. This surfaces which skills have the most open work and helps choose a focus area.
If $ARGUMENTS is provided (a specific issue number), skip roadmap and go directly to Step 2 with that issue.
Invoke /claim (or /claim $ARGUMENTS if an issue number was provided).
If already in-progress from a previous session, continue with that issue and skip to Step 3.
Invoke /autoplan on the claimed issue.
The plan will identify:
Wait for the plan output before proceeding.
Print clearly:
## Ready to Implement
Based on the autoplan, run one of:
/adjust-playbook $SKILL_NAME — to modify an existing skill
/create-playbook — to scaffold a new skill
Make your changes, then return here and confirm to commit.
Ask the user: "Type 'done' when the implementation is complete, or 'abort' to stop without committing."
If 'abort': do nothing. Leave the issue in-progress for the next session.
Invoke /commit to stage the changed skill files, write the commit message, and close the issue.
## Sprint Complete
Issue #$NUMBER closed.
Run `/sprint` again to start the next issue, or `/backlog` to review remaining work.
/work-loop/commit directly/autoplan $ISSUE_NUMBER directly