AGENT SKILL

ln-520-test-planner

Orchestrates test planning pipeline (research → manual → auto tests). Coordinates ln-521, ln-522, ln-523.

License 许可
MIT
最近更新
2026-05-02
Stars
★ 3
Forks
1

01 前言 Front Matter

name
ln-520-test-planner
license
MIT
description
Orchestrates test planning pipeline (research → manual → auto tests). Coordinates ln-521, ln-522, ln-523.

02 资源文件 2

03 SKILL.md 正文

Paths: File paths (shared/, references/, ../ln-*) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root.

Test Planning Orchestrator

Coordinates the complete test planning pipeline for a Story by delegating to specialized workers.

Inputs

Input Required Source Description
storyId Yes args, git branch, kanban, user Story to process

Resolution: Story Resolution Chain. Status filter: To Review

Purpose & Scope

  • Orchestrate test planning: research → manual testing → automated test planning
  • Delegate to workers: ln-521-test-researcher, ln-522-manual-tester, ln-523-auto-test-planner
  • No direct work — only coordination and delegation via Skill tool
  • Called by ln-500-story-quality-gate after regression tests pass

When to Use

This skill should be used when:

  • Invoked by ln-500-story-quality-gate after quality checks pass
  • All implementation tasks in Story are Done
  • Need complete test planning (research + manual + auto)

Prerequisites:

  • All implementation Tasks in Story status = Done
  • Regression tests passed (ln-513)
  • Code quality checked (ln-511)

Pipeline Overview

ln-520-test-planner (Orchestrator)
    │
    ├─→ ln-521-test-researcher
    │     └─→ Posts "## Test Research: {Feature}" comment
    │
    ├─→ ln-522-manual-tester
    │     └─→ Creates tests/manual/ scripts + "## Manual Testing Results" comment
    │
    └─→ ln-523-auto-test-planner
          └─→ Creates test task in Linear via ln-301/ln-302

Workflow

Phase 0: Resolve Inputs

MANDATORY READ: Load shared/references/input_resolution_pattern.md

  1. Resolve storyId: Run Story Resolution Chain per guide (status filter: [To Review]).

Phase 1: Discovery

  1. Auto-discover Team ID from docs/tasks/kanban_board.md
  2. Validate Story ID

Phase 2: Research Delegation

  1. Check if research exists:

    • Search Linear comments for "## Test Research:" header
    • If found → skip to Phase 3
  2. If no research:

    • Use Skill tool to invoke ln-521-test-researcher
    • Pass: Story ID
    • Wait for completion
    • Verify research comment created

Phase 3: Manual Testing Delegation

  1. Check if manual testing done:

    • Search Linear comments for "## Manual Testing Results" header
    • If found with all AC passed → skip to Phase 4
  2. If manual testing needed:

    • Use Skill tool to invoke ln-522-manual-tester
    • Pass: Story ID
    • Wait for completion
    • Verify results comment created
  3. If any AC failed:

    • Stop pipeline
    • Report to ln-500: "Manual testing failed, Story needs fixes"

Phase 4: Auto Test Planning Delegation

  1. Invoke auto test planner:

    • Use Skill tool to invoke ln-523-auto-test-planner
    • Pass: Story ID
    • Wait for completion
  2. Verify results:

    • Test task created in Linear (or updated if existed)
    • Return task URL to ln-500

Phase 5: Report to Caller

  1. Return summary to ln-500:
    • Research: completed / skipped (existed)
    • Manual testing: passed / failed
    • Test task: created / updated + URL

Worker Invocation (MANDATORY)

CRITICAL: All delegations use Agent tool with subagent_type: "general-purpose" for context isolation.

Phase Worker Purpose
2 ln-521-test-researcher Research real-world problems
3 ln-522-manual-tester Manual AC testing via bash scripts
4 ln-523-auto-test-planner Plan E2E/Integration/Unit tests

Prompt template:

Agent(description: "[Phase N] test planning via ln-52X",
     prompt: "Execute test planning worker.

Step 1: Invoke worker:
  Skill(skill: \"ln-52X-{worker}\")

CONTEXT:
Story: {storyId}",
     subagent_type: "general-purpose")

Anti-Patterns:

  • ❌ Direct Skill tool invocation without Agent wrapper
  • ❌ Running web searches directly (delegate to ln-521)
  • ❌ Creating bash test scripts directly (delegate to ln-522)
  • ❌ Creating test tasks directly (delegate to ln-523)
  • ❌ Skipping any phase without justification

Critical Rules

  • No direct work: Orchestrator only delegates, never executes tasks itself
  • Sequential execution: 521 → 522 → 523 (each depends on previous)
  • Fail-fast: If manual testing fails, stop pipeline and report
  • Skip detection: Check for existing comments before invoking workers
  • Single responsibility: Each worker does one thing well

Definition of Done

  • [ ] Story ID validated
  • [ ] Research phase: ln-521 invoked OR existing comment found
  • [ ] Manual testing phase: ln-522 invoked OR existing results found
  • [ ] Auto test planning phase: ln-523 invoked
  • [ ] Test task created/updated in Linear
  • [ ] Summary returned to ln-500-story-quality-gate

Output: Summary with phase results + test task URL

Phase 6: Meta-Analysis

MANDATORY READ: Load shared/references/meta_analysis_protocol.md

Skill type: planning-coordinator. Run after all phases complete. Output to chat using the planning-coordinator format.

Reference Files

  • Workers: ../ln-521-test-researcher/SKILL.md, ../ln-522-manual-tester/SKILL.md, ../ln-523-auto-test-planner/SKILL.md
  • Caller: ../ln-500-story-quality-gate/SKILL.md
  • Risk-based testing: ../shared/references/risk_based_testing_guide.md

Version: 4.0.0 Last Updated: 2026-01-15

04 同仓库更多 Skills

levalencia
levalencia/agent-god-mode

zarr-python

Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.

★ 3
levalencia
levalencia/agent-god-mode

zabbix

Zabbix monitoring system automation via API and Python. Use when: (1) Managing hosts, templates, items, triggers, or host groups, (2) Automating monitoring configuration, (3) Sending data via Zabbix trapper/sender, (4) Querying historical data or events, (5) Bulk operations on Zabbix objects, (6) Maintenance window management, (7) User/permission management

开发工程师后端与接口Skill与智能体开发
★ 3
levalencia
levalencia/agent-god-mode

x-twitter-growth

X/Twitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X/Twitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize engagement. Complements social-content (generic multi-platform) with X-specific depth: algorithm mechanics, thread engineering, reply strategy, profile optimization, and competitive intelligence via web search.

★ 3
levalencia
levalencia/agent-god-mode

what-if-oracle

Run structured What-If scenario analysis with multi-branch possibility exploration. Use this skill when the user asks speculative questions like "what if...", "what would happen if...", "what are the possibilities", "explore scenarios", "scenario analysis", "possibility space", "what could go wrong", "best case / worst case", "risk analysis", "contingency planning", "strategic options", or any question about uncertain futures. Also trigger when the user faces a fork-in-the-road decision, wants to stress-test an idea, or needs to think through consequences before committing.

★ 3
levalencia
levalencia/agent-god-mode

vercel-react-best-practices

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

前端开发
★ 3
levalencia
levalencia/agent-god-mode

venue-templates

Access comprehensive LaTeX templates, formatting requirements, and submission guidelines for major scientific publication venues (Nature, Science, PLOS, IEEE, ACM), academic conferences (NeurIPS, ICML, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). This skill should be used when preparing manuscripts for journal submission, conference papers, research posters, or grant proposals and need venue-specific formatting requirements and templates.

内容创作者写作与文案资料检索与研究
★ 3