ln-301-task-creator
from levnikolaevich/claude-code-skills
Greate Claude Code skills collection. Production-ready skills that cover the full delivery workflow — from research and discovery to epic planning, task breakdown, implementation, testing, code review, and quality gates.
65 stars13 forksUpdated Jan 25, 2026
npx skills add https://github.com/levnikolaevich/claude-code-skills --skill ln-301-task-creatorSKILL.md
Universal Task Creator
Worker that generates task documents and creates Linear issues for implementation, refactoring, or test tasks as instructed by orchestrators.
Purpose & Scope
- Owns all task templates and creation logic (Linear + kanban updates)
- Generates full task documents per type (implementation/refactoring/test)
- Enforces type-specific hard rules (no new tests in impl, regression strategy for refactoring, risk matrix and limits for test)
- Drops NFR bullets if supplied; only functional scope becomes tasks
- Never decides scope itself; uses orchestrator input (plans/results)
Task Storage Mode
| Aspect | Linear Mode | File Mode |
|---|---|---|
| Create task | create_issue(parentId, state: "Backlog") | Write("docs/tasks/epics/.../tasks/T{NNN}-{slug}.md") |
| Task ID | Linear issue ID (e.g., PROJ-123) | File-based (e.g., T001, T002) |
| Status | Linear state field | **Status:** Backlog in file |
| Kanban | Auto-synced | Must update kanban_board.md manually |
File Mode task creation:
- Determine next task number: count existing
T*.mdfiles + 1 - Generate filename:
T{NNN}-{slug}.md(e.g.,T003-implement-auth-service.md) - Write task file using template
- Add link to
kanban_board.mdunder Story in Backlog section
Invocation (who/when)
- ln-300-task-coordinator: CREATE (no tasks) or ADD (appendMode) for implementation tasks.
- Orchestrators (other groups): Create refactoring or test tasks as needed.
- Never called directly by users.
Inputs
- Common:
taskType, teamId, Story data (id/title/description with AC, Technical Notes, Context). - Implementation CREATE: idealPlan (1-6 tasks), guideLinks.
- Implementation ADD: appendMode=true, newTaskDescription, guideLinks.
- Refactoring: codeQualityIssues, refactoringPlan, affectedComponents.
- Test: manualTestResults, testPlan (E2E 2-5, Integration 0-8, Unit 0-15, Priority ≤15), infra/doc/cleanup items.
Workflow (concise)
- DRY Check (Codebase Scan): For EACH Task in plan:
- Extract keywords: function type, component name, domain from Task description
- Scan codebase:
Grep(pattern="[keyword]", path="src/", output_mode="files_with_matches")for similar functionality - IF similar code found (≥70% keyword match):
- Add
⚠️ DRY Warningsection to Task description BEFORE Implementation Plan:> [!WARNING] > **DRY Check:** Similar functionality detected in codebase > - Existing: src/services/auth/validateToken.ts:15-42 > - Similarity: 85% (function name, domain match) > - **Recommendation:** Review existing implementation before creating new code > - Option 1: Reuse existing function (import and call) > - Option 2: Extend existing function with new parameters > - Option 3: Justify why reimplementation needed (document in Technical Approach)
- Add
- IF no duplication → Proceed without warning
- Rationale: Prevents code duplication BEFORE implementation starts
- Template select: Load template based on taskType (see "Template Loading" section).
- Generate docs: Fill sections for each task in plan/request using provided data, guide links, and DRY warnings.
- Validate type rules: Stop with error if violation (see table below).
- Preview: Show titles/goals/estimates/AC/components, DRY warnings count, and totals.
- Confirmation required: Proceed only after explicit confirm.
- Create issues: Call Linear create_issue with parentId=Story, state=Backlog; capture URLs.
- Update kanban: Add under Story in Backlog with correct Epic/indent.
- Return summary: URLs, counts, hours, guide link count, DRY warnings count; next steps (validator/executor).
Type Rules (must pass)
| taskType | Hard rule | What to verify |
|---|---|---|
| implementation | No new test creation | Scan text for "write/create/add tests" etc.; allow only updating existing tests |
| refactoring | Regression strategy required | Issues listed with severity; plan in 3 phases; regression strategy (Baseline/Verify/Failure); preserve functionality |
| test | Risk-based plan required | Priority ≤15 scenarios; E2E 2-5, Integration 0-8, Unit 0-15, Total 10-28; no framework/library/DB tests |
Critical Notes
- MANDATORY: Always pass
state: "Backlog"when calling create_issue. Linear defaults to team's default status (often "Postponed") if not specified. - DRY Check: Scan codebase for EACH Task before generation. If similar code found (≥70% keyword match) → add
⚠️ DRY Warningsection with 3 options (reuse/extend/justify). Skip scan for test tasks (no implementation code). - Foundation-First order for implementation is preserved from orchestrator; do not reorder.
- No code snippets; keep to approach, APIs, and pseudocode only.
- Documentation updates must be included in Affected Components/Docs sections.
- Language preservati
...
Repository Stats
Stars65
Forks13
LicenseMIT License