本文へ移動
cccskills
無料GitHub で公開

openspec-archive-change

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

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。

インストール方法を見る

含まれるファイル(1)

  • SKILL.md8.4 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。

Archive a completed change in the experimental workflow.

Store selection: If the user names a store (a store is a standalone OpenSpec repo registered on this machine) or the work lives in one, run openspec store list --json to discover registered store ids, then pass --store <id> on the commands that read or write specs and changes (new change, status, instructions, list, show, validate, archive, doctor, context). Other commands do not take the flag. Hints printed by commands already carry the flag; keep it on follow-ups. Without a store, commands act on the nearest local openspec/ root.

Input: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.

Steps

  1. If no change name provided, prompt for selection

    Run openspec list --json to get available changes. Use the AskUserQuestion tool to let the user select.

    Show only active changes (not already archived). Include the schema used for each change if available.

    IMPORTANT: Do NOT guess or auto-select a change. Always let the user choose.

  2. Check artifact completion status

    Run openspec status --change "<name>" --json to check artifact completion.

    Parse the JSON to understand:

    • schemaName: The workflow being used
    • planningHome, changeRoot, artifactPaths, and actionContext: path and scope context
    • artifacts: List of artifacts with their status (done or other)

    If any artifacts are not done:

    • Display warning listing incomplete artifacts
    • Use AskUserQuestion tool to confirm user wants to proceed
    • Proceed if user confirms
  3. Check task completion status

    Read the tasks file (typically tasks.md) to check for incomplete tasks.

    Count tasks marked with - [ ] (incomplete) vs - [x] (complete).

    If incomplete tasks found:

    • Display warning showing count of incomplete tasks
    • Use AskUserQuestion tool to confirm user wants to proceed
    • Proceed if user confirms

    If no tasks file exists: Proceed without task-related warning.

  4. Assess delta spec sync state

    Use artifactPaths.specs.existingOutputPaths from status JSON to check for delta specs. If none exist, proceed without sync prompt.

    If delta specs exist:

    • Compare each delta spec with its corresponding main spec at openspec/specs/<capability>/spec.md
    • Determine what changes would be applied (adds, modifications, removals, renames)
    • Show a combined summary before prompting

    Prompt options:

    • If changes needed: "Sync now (recommended)", "Archive without syncing"
    • If already synced: "Archive now", "Sync anyway", "Cancel"

    If user chooses sync, use Task tool (subagent_type: "general-purpose", prompt: "Use Skill tool to invoke openspec-sync-specs for change '<name>'. Delta spec analysis: <include the analyzed delta spec summary>"). Proceed to archive regardless of choice.

  5. Perform the archive

    Create an archive directory under planningHome.changesDir if it doesn't exist:

    mkdir -p "<planningHome.changesDir>/archive"
    

    Generate target name using current date: YYYY-MM-DD-<change-name>

    Check if target already exists:

    • If yes: Fail with error, suggest renaming existing archive or using different date
    • If no: Move changeRoot to the archive directory
    mv "<changeRoot>" "<planningHome.changesDir>/archive/YYYY-MM-DD-<name>"
    
  6. Display summary

    Show archive completion summary including:

    • Change name
    • Schema that was used
    • Archive location
    • Whether specs were synced (if applicable)
    • Note about any warnings (incomplete artifacts/tasks)

Output On Success

## Archive Complete

**Change:** <change-name>
**Schema:** <schema-name>
**Archived to:** the archive path derived from `planningHome.changesDir`/YYYY-MM-DD-<name>/
**Specs:** ✓ Synced to main specs (or "No delta specs" or "Sync skipped")

All artifacts complete. All tasks complete.

Guardrails

  • Always prompt for change selection if not provided
  • Use artifact graph (openspec status --json) for completion checking
  • Don't block archive on warnings - just inform and confirm
  • Preserve .openspec.yaml when moving to archive (it moves with the directory)
  • Show clear summary of what happened
  • If sync is requested, use openspec-sync-specs approach (agent-driven)
  • If delta specs exist, always run the sync assessment and show the combined summary before prompting
<!-- keel:openspec-surface-overlay version=5.167.0 -->

Keel Archive Overlay

Keel rules below take precedence over conflicting generic OpenSpec instructions in this file.

  • Invoke the OpenSpec CLI as keel openspec … throughout this file. The commands below are written as a bare openspec, which resolves only where OpenSpec is separately installed on PATH; keel openspec resolves either way, and keel --doctor reports which case this repository is.

Target-native subagent gate

  • The current agent remains responsible for Keel ownership, task/archive decisions, scope control, and final reporting.
  • Use a target-native subagent when the current agent decides it is useful for a bounded helper step, or as a delegate implementing the selected task using existing task write authority when a guard manifest is active and matches the task, fingerprint and Touch; optional delegation: tiers are metadata.
  • Target-native subagents acting as helpers return report/evidence only. A delegate may write, and only inside Touch; its reported command results are a claim, and the current agent re-runs each M<n> check itself before recording Evidence.
  • Delegation is refused with no active guard manifest, because an absent manifest passes every write through silently and looks identical to a checked one.
  • Neither may mark tasks complete, update OpenSpec state, commit, sync, archive, or change Acceptance; the current agent reviews all output before acting.
  • The subagent brief must name the selected change/task, required read context, allowed write boundary or read-only diagnostic scope, expected commands/evidence, and prohibited actions. Compile it with keel project --event subagent-start for a read-only helper or add --subagent-mode implementation for a guarded delegate; no extra user activation is required. Host policy remains authoritative; Keel adds no separate carrier because the host already has one.
  • Prohibited actions include scope expansion, Acceptance changes, completion marking, sync/archive decisions, commits, handoff changes, and cross-runtime delegation unless the selected task or user explicitly authorizes them.
  • The current agent owns final sync/archive decisions and must verify task evidence, follow-up ownership, and completion gates before proceeding.
  • Before final sync/archive, each related critical expectation must have behavior evidence, a durable follow-up owner, or an explicit discard reason.
  • Target-native subagents may help with bounded assessment or evidence production only; they cannot archive, sync, change acceptance, or bypass completion gates.
  • The current agent reviews any subagent report before running openspec-sync-specs, /opsx:sync, or /opsx:archive.
  • Do not treat generic OpenSpec archive delegation language as authority to transfer Keel ownership.
  • Invoke OpenSpec through keel openspec (for example keel openspec validate); a bare openspec command may not be on PATH.
  • When /opsx:sync has already promoted the change's spec delta, run the archive with --skip-specs so the promoted delta is not re-applied; archive is not idempotent over an already-synced delta.
  • After archiving, run keel guard clear to drop the change's guard manifest; the read-only gate never clears it for you.
  • A repository that standing-authorizes archive in keel/config.yaml does not need the per-occurrence archive confirmation; a repository that declares nothing still needs it.
  • The completion gate and follow-up ownership checks still run unchanged under a standing authorization; it removes the confirmation, not the proof.
<!-- keel:openspec-surface-overlay:end -->

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。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

Align explicit requirements, implicit expectations, non-goals, observable acceptance, evidence, and decision authority before OpenSpec specs and executable tasks finalize. Use when authoring or updating a proposal, design, specs, or tasks, or when a request hides a material product choice. Do not use for routine implementation of an already-authorized task, unrelated conversation, or facts the repository can answer.

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。

TanglmChris/keel22026年10月20日 更新

Debug Keel agent command or validation failures under Keel's selected OpenSpec task contract. Use when `/opsx:apply` or a selected task reports failed commands, failing tests, validation errors, retry-fuse decisions, or needs an evidence-bound failure report.

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。

TanglmChris/keel22026年10月20日 更新

Create, validate, or clear the optional keel-handoff/v1 pointer override when human intent cannot be inferred uniquely.

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。

TanglmChris/keel22026年10月20日 更新

Run the current agent's thin semantic consistency review after shared Keel Core gates and before task completion, sync, archive, or meaningful handoff.

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。

TanglmChris/keel22026年10月20日 更新

Use when the user explicitly authorizes automatic execution or resume of exactly one OpenSpec task on Codex or Claude. Drives the single-task native goal lifecycle through Keel gates, keeps the current agent the sole holder of write authority, and stops at the task boundary. Never activate for ordinary apply, proposal work, ambiguous or multiple tasks, or OpenCode.

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。

TanglmChris/keel22026年10月20日 更新

Drive Keel agent test-first or evidence-first execution for a selected OpenSpec task. Use when a task needs software tests, hardware testbench, assertions, lint, new behavior proof, regression coverage, or red/green evidence before implementation.

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。

TanglmChris/keel22026年10月20日 更新

TanglmChris のスキルをすべて見る

このスキルの問題を報告する