本文へ移動
cccskills
無料GitHub で公開

done-retirement

Pipeline retirement protocol for completed work items. Implements a 7-stage validate-commit-push-submit-notify-cleanup-terminate pipeline with irreversibility after push. Done means gone.

インストール方法を見る

含まれるファイル(3)

  • SKILL.md5.6 KB
  • references/gastown-origin.md5.9 KB
  • references/retirement-implementation.md10.3 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Done Retirement

Pipeline retirement processor for the Gastown chipset. When a polecat finishes its work, this pipeline validates, commits, pushes, submits an MR, notifies, cleans up, and terminates. In hardware terms, it is the instruction retirement unit — writing results to the register file (shared repository), updating the reorder buffer (merge queue), and freeing execution resources.

Activation Triggers

This skill activates when:

  • A polecat has completed execution and is ready to retire its work
  • An agent's hook status transitions to completed
  • A work item's status transitions to done
  • A convoy needs to track individual bead completion

The 7-Stage Retirement Pipeline

Every retirement flows through seven stages in strict order. The pipeline has an irreversibility boundary at Stage 3 (Push). Before push, the retirement can be aborted and the bead returned to in_progress. After push, the process is irreversible — the branch is in the shared repository and the workspace will be destroyed.

#StagePurpose
1ValidateVerify work meets acceptance criteria; reject premature retirement.
2CommitEnsure all changes are committed to the working branch.
3PushPush branch to shared repository. IRREVERSIBLE AFTER THIS. Work item status → done.
4SubmitCreate merge request record in the refinery's merge queue.
5NotifySend completion mail to mayor, witness, and convoy.
6CleanupDestroy worktree, clear hook, remove dispatch record.
7TerminateMark agent as terminated; release resources back to the pool.

Stages: VALIDATE → COMMIT → PUSH → SUBMIT → NOTIFY → CLEANUP → TERMINATE.

Full TypeScript implementations live in references/retirement-implementation.md.

"Done Means Gone" — Irreversibility Rules

The irreversibility contract is the core design principle of this pipeline and MUST remain active at all times:

  1. Before push (Stages 1-2): The retirement can be aborted. The bead returns to in_progress and the polecat continues working. No permanent side effects.
  2. At push (Stage 3): The point of no return. The branch reaches the shared repository. The work item status transitions to done.
  3. After push (Stages 4-7): Consequences unfold. The merge request is created, notifications sent, workspace destroyed, agent terminated. Each of these stages can fail individually without compromising the work — the branch is already safe in the remote.
Stages 1-2:  REVERSIBLE    (abort returns to in_progress)
Stage 3:     COMMITMENT    (push to remote, status = done)
Stages 4-7:  CONSEQUENCES  (submit, notify, cleanup, terminate)

If any consequence stage fails (e.g., mail delivery failure in Stage 5), the work is still done. The failure is logged and the mayor can retry the notification manually. The push is the only stage that truly matters for durability.

Cleanup is destructive by design. The polecat's local state — worktree, context files, dispatch records — is deleted. There is no going back to inspect local state after cleanup. If the work needs revision, a new polecat is spawned with a fresh workspace.

Termination is the final lifecycle transition. The polecat goes from active to terminated. There is no re-activation.

Convoy Progress Tracking

When a bead belongs to a convoy (batch dispatch), its completion updates the convoy's aggregate progress. The mayor monitors convoy progress to determine when all beads in a batch are done. A convoy is complete when all beads reach done or merged status.

Communication Protocol

Done retirement is invoked by the polecat itself when work is complete — there is no external trigger message. On the outbound side, it sends durable mail to the mayor (completion report with MR details) and the witness (retirement notification), and a handoff record to the refinery via the merge queue.

Boundary: What Done Retirement Does NOT Do

Done retirement does not merge code (the refinery does), decide when work is complete (the polecat does), re-assign work (the mayor handles reassignment), preserve local state ("done means gone"), or reverse after push (the irreversibility contract is absolute). It is the exit ramp — and there is no U-turn after the push.

Integration with Other Gastown Skills

Invoked by polecat-worker when work is complete. Feeds refinery-merge via the merge queue (Stage 4). Uses hook-persistence to clear the polecat's hook (Stage 6) and mail-async for notifications (Stage 5). Reads and writes beads-state for work items and convoy progress. sling-dispatch is the other end of the lifecycle — dispatch feeds into retirement.

References

Implementation detail moved to:

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

Provides web accessibility best practices for semantic HTML, ARIA, keyboard navigation, color contrast, and screen reader patterns. Use when building UI components, reviewing accessibility, or when user mentions 'a11y', 'accessibility', 'ARIA', 'screen reader', 'keyboard navigation', 'WCAG'.

日本語の概要は準備中です。原文の説明を表示しています。

Tibsfox/gsd-skill-creator712026年7月20日 更新

Active listening techniques for effective communication. Covers attending behaviors, paraphrasing, reflective listening, clarifying questions, empathic response, barriers to listening, listening in conflict, and cross-cultural listening. Use when building listening skills, improving understanding in conversation, mediating disputes, or analyzing communication breakdowns.

日本語の概要は準備中です。原文の説明を表示しています。

Tibsfox/gsd-skill-creator712026年7月20日 更新

Adversarial spec-compliance PR review — cross-references diffs against approved specs, verifies runtime claims against source, detects competing PRs, audits scope/convention compliance. Use before merging.

日本語の概要は準備中です。原文の説明を表示しています。

Tibsfox/gsd-skill-creator712026年7月20日 更新

Provides best practices for AI agent orchestration including MCP servers, A2A protocol, multi-agent coordination, and swarm architectures. Use when designing agent systems, configuring MCP servers, setting up agent teams, or when user mentions 'MCP', 'A2A', 'agent orchestration', 'multi-agent', 'swarm', 'agent team', 'LangGraph', 'CrewAI', 'AutoGen'.

日本語の概要は準備中です。原文の説明を表示しています。

Tibsfox/gsd-skill-creator712026年7月20日 更新

Symbolic manipulation, equation solving, and algebraic structures for mathematical reasoning. Covers distributive law, factoring, completing the square, linear through polynomial equation solving, systems of equations (substitution, elimination, Gaussian elimination, matrix methods), algebraic structures (groups, rings, fields), modular arithmetic, polynomial theory, and inequalities. Use when solving equations, simplifying expressions, working with algebraic structures, or performing symbolic manipulation.

日本語の概要は準備中です。原文の説明を表示しています。

Tibsfox/gsd-skill-creator712026年7月20日 更新

Understanding how algorithmic systems shape what users see, know, and do -- from recommendation feeds to search ranking to credit scoring to hiring software. Covers the mechanics of recommendation systems, algorithmic bias and its sources, personalization's effects on information diets, opacity and accountability, AI limitations (hallucination, confident wrongness), and the human-in-the-loop question. Use when a learner needs to think critically about why particular content reached them.

日本語の概要は準備中です。原文の説明を表示しています。

Tibsfox/gsd-skill-creator712026年7月20日 更新

Tibsfox のスキルをすべて見る

このスキルの問題を報告する