AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Ln 301 Task Creator

skill-levnikolaevich-claude-code-skills-ln-301-task-creator · by levnikolaevich

Creates implementation, refactoring, and test tasks from templates. Use when an approved task plan needs tasks created via the configured tracker provider and reflected in kanban.

No reviews yet
0 installs
32 views
0.0% view→install

Install

$ agentstack add skill-levnikolaevich-claude-code-skills-ln-301-task-creator

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-levnikolaevich-claude-code-skills-ln-301-task-creator)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
3mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Ln 301 Task Creator? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

> Paths: File paths (references/, ../ln-*) are relative to this skill directory.

Task Creator

Type: L3 Worker Category: 3XX Planning

Standalone-first worker for task creation. It creates tasks from an already approved plan and returns a stable summary contract.

MANDATORY READ: Load references/coordinator_summary_contract.md and references/task_plan_worker_runtime_contract.md MANDATORY READ: Load references/environment_state_contract.md, references/storage_mode_detection.md, references/template_loading_pattern.md, references/creation_quality_checklist.md, and references/destructive_operation_safety.md

Inputs

Core inputs:

  • taskType
  • storyData
  • idealPlan — task list with scopes, AC mappings, dependencies, layer classifications
  • teamId
  • guideLinks

Coordinator context (passed in ADD/CREATE mode):

  • traceabilityTablePath — materialized traceability table from coordinator Phase 2
  • discoveryContext — architecture, tech stack, key files, integration points from coordinator Phase 1
  • tasksToCreate — specific tasks to create (ADD mode). Worker writes the 7-section document, does not decide whether tasks are needed.

Transport inputs:

  • standalone: omit runId and summaryArtifactPath
  • managed: pass both runId and summaryArtifactPath

Runtime

Runtime family: task-plan-worker-runtime

Phase profile:

  1. PHASE_0_CONFIG
  2. PHASE_1_LOAD_INPUTS
  3. PHASE_2_LOAD_CONTEXT
  4. PHASE_3_GENERATE_TASK_DOCS
  5. PHASE_4_VALIDATE_TASKS
  6. PHASE_5_CONFIRM_OR_AUTOAPPROVE
  7. PHASE_6_APPLY_CREATE
  8. PHASE_7_UPDATE_KANBAN
  9. PHASE_8_WRITE_SUMMARY
  10. PHASE_9_SELF_CHECK

Summary artifact rules:

  • emit summary_kind=task-plan
  • standalone runs generate their own run_id and write the default worker-family artifact path
  • managed runs require both runId and summaryArtifactPath and must write the summary to the exact provided path
  • always write the validated summary artifact before terminal outcome

Output Contract

Always build a structured task-plan summary envelope per:

  • references/coordinator_summary_contract.md
  • references/task_plan_worker_runtime_contract.md

Payload fields:

  • mode
  • story_id
  • task_type
  • tasks_created
  • tasks_updated
  • tasks_canceled
  • task_urls
  • kanban_updated
  • dry_warnings_count
  • warnings

Always write the validated summary before terminal outcome.

Workflow

  1. Resolve task provider and template set.
  2. Run DRY and destructive-operation checks where applicable.
  3. Use coordinator context (discoveryContext, traceabilityTablePath) to understand architecture. Research codebase for implementation details (existing patterns, related files, integration points) to write good Technical Approach sections.
  4. Select scope:
  • ADD: use tasksToCreate only
  • CREATE: expand the full idealPlan
  1. Generate task documents from the selected scope.
  2. Validate type-specific rules.
  3. Show preview and get confirmation if needed.
  4. Create tasks via the configured tracker provider.
  5. Update kanban.
  6. Return structured summary.

Critical Rules

  • Remain standalone-capable.
  • Do not require coordinator runtime state.
  • Keep implementation, refactoring, and test rules separated by taskType.
  • Write machine-readable summary output every time.
  • Ideal plan is binding. Create every task in the approved plan. Do not re-evaluate whether tasks should exist.
  • Fast path for ADD: tasksToCreate is the execution scope. Do not re-expand the full ideal plan when the coordinator already selected the delta.
  • STOP before tracker createTask: verify all 7 sections present in body: Context, Implementation Plan, Technical Approach, Acceptance Criteria, Affected Components, Existing Code Impact, Definition of Done. PreToolUse hook will BLOCK creation without them.

Definition of Done

  • [ ] Templates loaded
  • [ ] Task documents generated
  • [ ] Type-specific validation passed
  • [ ] Tasks created in provider-specific storage
  • [ ] kanban updated
  • [ ] Structured summary returned
  • [ ] Summary artifact written to the managed or standalone runtime path

Version: 3.0.0 Last Updated: 2025-12-23

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.