About orchestrate
orchestrate is a skill for coordinating a pre-specified feature across parallel `/implement` subagents working in worktrees. It uses GitHub sub-issues as the work packages and ledger, while the orchestrator handles sequencing, verification, merges, and cleanup without editing `src/`.
Key features
- 01Uses parent issue sub-issues as work packages
- 02Sequences parallel `/implement` agents
- 03Tracks decisions and progress on GitHub issues
- 04Verifies agent work and CI before merging
- 05Coordinates merge order and cleanup
Use cases
- 01Implementing a feature split into GitHub sub-issues
- 02Running parallel agent work in separate worktrees
- 03Tracking blockers and decisions during implementation
- 04Merging reviewed agent pull requests in sequence
Install
Copy the command and run it in a terminal.
npx skills add https:/ / github.com/ timschoch/ skilly --skill orchestrateAfter installing, type/orchestratein Claude Code to confirm it loaded.
Bundled filesops.mdpackage-prompt.md
Details
From the project READMERun a pre-specced feature across parallel /implement subagents on worktrees.
Rule Zero
Never slice or map the work yourself. The parent issue's sub-issues ARE the work packages: fetch them, hand each verbatim to one /implement agent. Sub-issues missing or unclear → stop and ask the owner; do not invent packages. Process fidelity is a requirement — a correct deliverable produced off the pre-specced path gets rejected.
Roles
- Orchestrator (you): read-only +
gh+ spawning. Never editsrc/. Your job: sequencing, relay, verification between phases, merges, cleanup, ops sidecar (seeops.md). - Agents: full
/implementflow — native claim, own worktree, TDD, /code-review, own PR. Duplicate none of it here. - Mechanical tail (merge order, CI watch, branch/worktree cleanup) belongs to the orchestrator. Agents end at "PR open + report".
Ledger
The GitHub issue is the ledger. Whenever anything relevant happens or a decision is made without the owner, post a condensed comment — orchestrator on the parent issue, each agent on its sub-issue:
🤖 decision (bot): <one line>
<2–4 lines: why, link>
Types: decision | question | blocker | progress. Always the 🤖 prefix; decisions explicitly marked (bot). Post via gh issue comment N --body-file .temp/<f>.md (heredocs are blocked). Questions go on the issue and the run proceeds where a tolerant default exists — don't block.
Run sequence
- Sync + fetch sub-issues.
git fetch && git pull --ff-only(the main checkout's branch drifts — verifygit branch --show-current; always branch fromorigin/$(node .agents/skills/verify/scripts/default-branch.mjs)). Then fetch sub-issues — GraphQL only,gh issue viewdoes not render them:
Never claim a GitHub feature is absent from CLI output alone. Done when: every sub-issue is listed with its "Blocked by" edges, or the owner has been asked.gh api graphql -f query='query{ repository(owner:"$OWNER",name:"$REPO"){ issue(number:$N){ subIssues(first:50){ nodes{ number title state } } } } }' - Recon + feasibility. Read the seam files yourself — agent summaries miss API gaps. Diff the spec against current behavior before spawning the affected package. Specs may be AI-written: any one-time external setup step (webhook, OAuth app, DNS, third-party config) gets verified against current provider docs before an agent bakes it into docs — e.g. webhooks need a SECRET, not a token;
projects_v2_itemevents are org-webhook-only. Gaps → ledgerquestion. Done when: every external-world assumption is verified or ledgered. - Sequence + hotspots. Order from each ticket's "Blocked by". Flag shared-file hotspots (e.g. one ADR taking amendments from several tickets): serialize them, or pre-agree the conflict posture in the prompts ("keep shared-file changes additive; second-to-merge rebases"). "New files only" = parallelizable; "touches shared files" = single writer.
- Spawn. One
/implementagent per sub-issue, prompt built frompackage-prompt.md. Sequence-sensitive rules (rebase-before-PR, conflict posture, merge order) go in the original prompt — a mid-flight message crosses with the agent's push and arrives too late. - Relay + verify. An agent's /code-review children report to YOU, not to it — relay verdicts and fix lists promptly; the relay doubles as your QA checkpoint. Idle ≠ done: before acting on any "finished" signal, verify observable state — branch on origin,
git diff --stat, the fix present in the diff (not just the ack). After any relay, expect one more round-trip. Nudge with "finish your remaining steps", never "push now" — a hurried agent skips its own QA. - Merge. On green CI only:
gh run watch <id> --exit-status && gh pr merge <n> --squash --delete-branch && <cleanup>chained in one background call. You own merge order; second-to-merge rebases. Done when: every sub-issue has exactly one merged PR carryingCloses #<sub>. - Wrap-up. One final docs PR for shared-line docs (CLAUDE.md current focus) — never per-ticket. Infra blockers you cannot reach (Neon/Vercel consoles are owner-only) are a legitimate terminal state: ledger a
blockeron the PR with evidence + the owner action needed. Post the final 🤖 tally on the parent issue.
Salvage from an archived earlier run, deploy diagnosis, Projects v2 limits, destructive-script rules: ops.md.