--- title: /skill:task (deprecated) description: "Drafts a task file for AI implementation." --- # /skill:task > **Deprecated for pi:** this skill is still port pending. It may contain Claude Code-specific instructions and is hidden from automatic invocation with `disable-model-invocation: true`. Drafts a task file for AI implementation. ## Triggers Activates when the user writes: - `create a task` - `task from ticket` - `draft a task` - `prepare an implementation prompt` ## Use it ``` /yoke:task https://github.com/owner/repo/issues/86 /yoke:task add dark theme to settings ``` ## Inputs and outputs **Input:** `$ARGUMENTS` — ticket URL (GitHub Issues, YouTrack, Jira) and/or a free-form task description. ``` /yoke:task https://github.com/owner/repo/issues/86 /yoke:task add dark theme to settings ``` **Output:** —
Full instructions ````markdown --- name: task description: >- Drafts a task file for AI implementation. Triggered when the user writes "create a task", "task from ticket", "draft a task", "prepare an implementation prompt", or passes a ticket URL / feature description. --- # Draft a task for AI implementation You are the orchestrator. Coordinate sub-agents and talk to the user. Delegate codebase investigation through the Agent tool: - Investigation → `agents/task-investigator.md` You formulate the task; implementation belongs to other skills. --- ## Input `$ARGUMENTS` contains one or both of: - **Ticket URL** — GitHub Issues, YouTrack, Jira, etc. - **Task text** — description, code snippets, links --- ## Phases ### Phase 1 — Parse **1. Fetch the ticket:** - GitHub Issues → `gh issue view ` - Other trackers → take the content from the user's text; use the URL only for the slug **2. Extract materials from the input:** Collect a separate list of: - links (Figma, docs, API) - paths to files and screenshots - pasted code snippets - external resources Copy this list verbatim into the `Materials` section. **3. Build the task slug** — identifier + English kebab-case description: - `86-black-jack-page` — from GitHub issue #86 - `R2-50-user-id-to-db` — from YouTrack R2-50 - `fix-navbar-overflow` — no URL, text only Take the ID from the URL plus 2–4 descriptive words. With no URL, use the description only. **4.** Extract `TICKET_ID` from the slug (per `${CLAUDE_PLUGIN_ROOT}/skills/gca/reference/commit-convention.md`). **Transition:** slug and TICKET_ID determined, materials saved → Phase 2. --- ### Phase 2 — Investigate **Launch task-investigator through the Agent tool.** The agent definition lives in `agents/task-investigator.md`. Prompt to the agent: ``` Investigate the codebase area for this task: [paste the ticket essence]. Find and document: 1. Entry points with file:line 2. Patterns to reuse (1-2 similar implementations) 3. Tests covering the area, or note their absence 4. Integration risks and fragile dependencies 5. Reusable utilities, components, or patterns ``` **Stop criteria — Investigate is done when:** - [ ] Entry points are identified with line numbers - [ ] Patterns to reuse are found with example files - [ ] Tests for the touched area are listed, or you confirm their absence - [ ] Risk zones are identified If any item stays open, re-dispatch task-investigator with narrower scope. **Transition:** all four criteria closed → Phase 3. --- ### Phase 3 — Synthesize **Apply the 5-dimension checklist to Phase 2 findings.** For each: one sentence of reasoning, then the formulation. 1. **Intent Clarity.** Two developers should read the Task and do the same thing. Use one concrete verb per Task — not "improve" or "fix". 2. **Scope Boundaries.** State what is in scope and what is out. Each Constraint maps to a concrete risk from Investigate: a fragile file, similar code that must stay, a dependency surface. 3. **Context Anchoring.** Cite paths and line numbers — `src/auth/middleware.ts:validateToken():89`, not "the auth module". Context has 4 subsections: Area architecture, Files to change, Patterns to reuse, Tests. 4. **Acceptance Criteria.** Write each Verification bullet as a command with expected result OR an observable behavior. Pull edge cases from Investigate findings. 5. **Reuse Opportunities.** For each requirement, find a partial existing solution. Record under Patterns to reuse with paths. **Complexity:** trivial (1 file, ≤5 lines) / simple (1-2 files, clear scope) / medium (3-7 files, possible regressions) / complex (architecture, multiple layers, no tests, public API). **If the task touches UI components, styles, or frontend work** (React, Vue, Svelte, CSS, Tailwind, animations, layouts, pages): read `reference/frontend-guide.md` and apply its checklists to the Requirements, Constraints, and Verification dimensions. For deeper Bad/Good examples and anti-patterns, see `reference/synthesize-guide.md` — supplementary. **Question validation:** Re-read `$ARGUMENTS`. Keep only questions the prompt leaves open. Fold the user's decisions into Requirements and Constraints as facts. **Interactive clarifications:** Draft 3–7 clarifying questions whose answers change requirements, scope, or architecture. Ask the user via AskUserQuestion in batches of 1–4 questions. For each question: - 2–4 answer options with explanations - Recommended option first, labeled `(Recommended)` - The user may pick "Other" for free-form input After each batch, revise Requirements, Constraints, and Context. Fold the answers into the section wording. Repeat until the user answers every question. **Transition:** 5 dimensions applied, questions asked and answers folded in → Phase 4. --- ### Phase 4 — Write **1.** `mkdir -p docs/ai/` **2.** Write `docs/ai//-task.md`: ``` # **Slug:** **Ticket:** **Complexity:** **Type:** ## Task ## Context ### Area architecture ### Files to change ### Patterns to reuse ### Tests ## Requirements 1. 2. ... ## Constraints - - - ## Verification - `` → - - ## Materials - [Description](url) - `path/to/file` ``` **3. Self-check the prose** — re-read the file. Edit inline if any sentence violates: - Active voice — "the agent reads the file" - Positive form — "Add tests" (not "Don't forget tests") - Concrete language — files, lines, function names - No needless words - Imperative mood **4. Auto-commit the artifact.** Check: is `docs/ai/` in `.gitignore`? If yes — tell the user and skip the commit. Otherwise commit per the convention in `${CLAUDE_PLUGIN_ROOT}/skills/gca/reference/commit-convention.md`: ```bash git add docs/ai//-task.md git commit -m "TICKET docs(SLUG): add task definition" ``` Format: `TICKET docs(SLUG): add task definition` (NO colon after ticket). Example: `#86 docs(86-black-jack-page): add task definition`. Commit only the task artifact, no other files. **Transition →** Phase 5. --- ### Phase 5 — Complete Report the file path and task slug, then run the finishing loop. Send a notification: `bash ${CLAUDE_PLUGIN_ROOT}/lib/notify.sh --type STAGE_COMPLETE --skill task --phase Complete --slug "$TASK_SLUG" --title "Task ready" --body "docs/ai/$TASK_SLUG/$TASK_SLUG-task.md"` **Offer next step:** Offer 3 options through AskUserQuestion: 1. **Run /yoke:plan (Recommended)** — auto-handoff to planning 2. **Review via revdiff** — interactive review of the task file 3. **Finish** — exit **Handle the choice (one-shot, no loop):** - **Run /yoke:plan:** call the Skill tool with `/yoke:plan` and the argument `docs/ai//-task.md`. Exit. - **Review via revdiff:** call the Skill tool with `/revdiff` and the argument `--only docs/ai//-task.md`. If the return is non-empty, apply the annotations to the task file and overwrite. Then exit. (For another pass, the user invokes `/revdiff` manually.) If the plugin is missing — print `Install the revdiff plugin:` followed by ` /plugin marketplace add umputun/revdiff` and ` /plugin install revdiff@umputun-revdiff`, then exit. - **Finish:** report the file path. Exit. --- ## Rules - Language: match the ticket/input language, or follow the project-level definition in CLAUDE.md / AGENTS.md. - task-slug — English kebab-case - One task — one file, no decomposition - Write in active voice. Omit needless words. Name files and lines instead of abstractions. ````
{/* Footer */} ## Source [View `SKILL.md` on GitHub →](https://github.com/yokeloop/yoke/blob/main/skills/task/SKILL.md)