一键导入
update-tasks
Reconcile active task files with plans without spawning new workers, including success, failure, blocked, malformed, and stale states
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Reconcile active task files with plans without spawning new workers, including success, failure, blocked, malformed, and stale states
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Automated project implementation orchestrator that drives feature-driven development from a single initial prompt through to completed code. Use this skill when the user invokes /init-project, /init-features, /add-feature, /continue-tasks, /continue-new-session, /iterate-tasks, /review-tasks, /update-tasks, /analyze-features, or /reinit. Also trigger proactively when docs/INITIAL_PROMPT.md exists and the user says anything like "move forward", "keep building", "what's next", "continue the implementation", or "start working on the project", AND when the user says "set up project management", "bootstrap a new project", "initialize the project workflow", or "make sure agents follow the project plan". This skill manages the full lifecycle: scaffolding a new project with enforcement artifacts, extracting feature specs via interview, generating phased implementation plans, spawning typed agents to execute tasks, monitoring completion sentinels, recovering from failures, and archiving finished work — all driven by m
Generate a copy-ready prompt that a fresh session (Claude Code, Codex, or Gemini) can paste in to immediately begin work on the next recommended action that was identified in this session's most recent recap. Reference-style — names file paths with short excerpts, no large inline content.
Self-perpetuating, subagent-driven iteration of the project pipeline. One invocation: (1) merges any pending PR left by the previous turn, (2) dispatches the recap-recommended next action as a fresh subagent so each unit of work gets a clean context, then (3) emits a copy-ready prompt for the action that comes AFTER the one just completed. Designed to pair with /loop for unattended runs and to minimize parent-context growth.
Run the full project orchestration loop with approved-spec gating, dependency ordering, verified completion, and deterministic failure/blocked handling
Use when starting a new project from scratch or retrofitting the project-manager workflow onto an existing repo. Scaffolds the docs/ tree, copies canonical templates, installs agent-enforcement artifacts (AGENTS.md, CLAUDE.md fragment, pre-commit guard, Claude Code hook, PR template, ROADMAP), and seeds INITIAL_PROMPT.md. Idempotent: re-running only fills gaps.
Dry-run project status report. Produces a read-only snapshot of feature specs, dependency blockers, plans, active tasks, stale work, verification backlog, and open issues without spawning agents or modifying files.
| name | update-tasks |
| description | Reconcile active task files with plans without spawning new workers, including success, failure, blocked, malformed, and stale states |
Synchronize docs/tasks/active/ back into docs/plans/. This command is idempotent and never
spawns agents.
Run references/scripts/pm-validate.ps1 first when present. If validation fails, reconcile only the
specific active completion files that are valid enough to parse; avoid broad plan edits until the
reported schema problems are fixed.
For each docs/tasks/active/*.md:
feature, phase, task, covers, role, and created.docs/plans/{feature}-plan.md preferred).## Completion Instructions.## Completion heading.Status: success, Status: failure, or Status: blocked.created or file modified time is older than 24 hours, report
the task as stale.Parse Summary:, Artifacts:, Tests:, and Notes:.
Tests: passing: false, add a corrective build/test task and do not mark the implementation
final.verification pending in the notes, and archive the
active file.done, append the summary to plan notes, and archive the active file.Verification is required for implementation, API, build, security, UI/frontend/backend/database, migration, refactor, cleanup, and other code-changing work.
failures: count.todo unless unrecoverable.docs/tasks/locks/{task-id}.lock.md as released.docs/tasks/logs/{task-id}.md when present.blocked, write a failure issue under docs/issues/, and
report that user input is required.blocked.docs/issues/ with the reason and decision needed.released and preserve the blocker in the task log.If a final ## Completion heading exists but no valid Status: follows it:
If no valid sentinel exists and the task is older than 24 hours:
lease_expires_at is also expired, report the lease as expired. Do not take or cancel the
claim automatically.claimed_by, claimed_at, and lease_expires_at; a
matching lock file records the same lease under docs/tasks/locks/.lease_expires_at.released.cancelled, record the reason, and leave the task
active unless the user authorizes archiving.Return a concise report with: