القائمة
Mark a task as completed and move it to done. Use when the user finishes work, says "done with task", "complete task", "mark as done", or when all acceptance criteria are met.
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
| name | complete-task |
| description | Mark a task as completed and move it to done. Use when the user finishes work, says "done with task", "complete task", "mark as done", or when all acceptance criteria are met. |
| argument-hint | ["task ID or number"] |
| allowed-tools | ["Read","Write","Bash","Glob","Grep"] |
| model | haiku |
Mark a task as completed, move it to the complete directory, and handle learnings.
Task identifier (optional): $ARGUMENTS — accepts TSK-001, 001, or 1.
Verify .backlog/ exists.
If $ARGUMENTS provided, find matching file in .backlog/tasks/active/. If not there, check .backlog/tasks/pending/ (a task can be completed without having been started) — if found there, confirm with the user before proceeding. If found nowhere, say so and stop.
If no argument, list active tasks and ask which to complete.
Read the task file and check acceptance criteria:
[x], proceedTSK-{{ID}} has unchecked acceptance criteria:
- [ ] Criterion 3
Options:
1. Mark as complete anyway (criteria no longer relevant)
2. Continue working (abort completion)
3. Update criteria (remove/modify items)
Gather learning candidates from two sources, then create each one silently using auto-draft mode (see /flowstate:add-learning Step 2a). Do NOT ask the user first.
3a. From the task file's Learnings section — each entry becomes a full learning (expand the one-line entry into Context / Insight / Application using the task body and tags).
3b. From the recent conversation — scan for non-obvious discoveries that emerged while working on this task: gotchas, root causes ("ah, that failed because…"), patterns that worked, things to avoid. High signal only — skip routine work.
For every candidate from 3a or 3b, run:
cat <<'BODY' | node "${CLAUDE_PLUGIN_ROOT}/dist/bin/flowstate.js" learning-create --title "{{TITLE}}" --tags "{{TAGS}}" --task {{TSK_ID}} --body -
{{BODY_DRAFTED_FROM_CONTEXT}}
BODY
Surface every captured learning in the confirm output (Step 5) so the user can edit or delete if signal was wrong. If no candidates from either source, skip silently — do NOT prompt.
node "${CLAUDE_PLUGIN_ROOT}/dist/bin/flowstate.js" task-move {{ID}} --to complete
The CLI updates frontmatter (status: complete, completed: today), adds a progress log entry, moves the file to tasks/complete/, and updates tasks/index.md automatically.
Completed TSK-{{ID}}: {{TITLE}}
{{PENDING_COUNT}} tasks remaining.
Learnings auto-captured: {{N}}
- LRN-XXX: {{TITLE}} ← list each, so the user can edit/delete
/flowstate:next-task — Get a recommendation · /flowstate:add-learning — Capture another
If N == 0, omit the "Learnings auto-captured" block entirely.
Activate when the project has a .backlog/ directory, or when the user discusses tasks, backlog, ideas, reports, bugs, or learnings. Provides contextual awareness of the flowstate backlog management system.
Generate a Changesets entry and commit it, for Changesets-managed monorepos. Use when the user says "changeset", "add changeset", needs to record a package version bump, or finishes work that should ship in the next release. Detects modified packages from staged files, picks major/minor/patch from the diff, and leaves `changeset version` to CI. Do NOT use for single-package repos or repos without a `.changeset/` directory.
Audit project docs (README, CLAUDE.md, AGENTS.md, package READMEs, docs/) for content drift AND structural fit — versions, commands, paths, examples and instructions out of sync with the code, plus a 3-tier layout check (rules stay terse, READMEs stay human, deep docs live under docs/). Use when the user says "check docs", "are the docs up to date?", after significant code changes, or before a release. Reports content + structural issues; defers markdown style/formatting to a linter. Monorepo-aware.
Create a git commit following Conventional Commits. Use when the user says "commit", "commit these changes", has finished a logical unit of work, or wants to save progress to git. Analyzes the staged diff to infer type/scope, scans for secrets and sensitive files, warns before committing to main/master, and never bypasses hooks without permission.
Review a GitHub pull request with specialized agents running in parallel (code quality, security, QA, architecture as needed). Use when the user says "review PR", "review this pull request", "/review-pr", pastes a GitHub PR URL, or finishes a branch and wants feedback before merge. Fetches diff via `gh`, checks CI status, produces a structured report with risk matrix and merge recommendation. Requires GitHub CLI authenticated.
Document a learning or insight discovered during development. Use when the user says "learned something", "TIL", "note this", "remember this for next time", or when a non-obvious discovery is made while working.