adrianbrowning/plan-to-tasks
skills/plan-to-tasks/SKILL.md
Convert project plans to JSONL format (issues + dependencies). Use when users ask "convert plan to jsonl", "create jsonl from plan", "export plan as json" or "convert plan to taks", "create tasks from plan", "export plan as tasks".
development
Updated Mar 27, 2026
$ install --global
skillsauthnpx skillsauth add adrianbrowning/agent-skills plan-to-tasksInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Mar 30, 2026, 5:29 AM36.4s10 files scanned
SKILL.md
- name:
- plan-to-tasks
- description:
- Convert project plans to JSONL format (issues + dependencies). Use when users ask "convert plan to jsonl", "create jsonl from plan", "export plan as json" or "convert plan to taks", "create tasks from plan", "export plan as tasks".
Plan to JSONL Converter
Transform project plans into JSONL format: Story (Epic) → Task → SubTask with embedded dependencies.
When to Apply
Use this skill when:
- User provides a project plan/spec to break down
- Converting markdown plans to JSONL format
- Exporting task hierarchies as structured data
- Creating work queues for external systems
- User asks to "convert to jsonl", "create jsonl from plan", "export plan as json"
Core Conversion Process
Step 1: Analyze the Plan
Identify three levels:
- Stories (Epics): Major features/components → Type:
epic - Tasks: Implementation work → Type:
task - SubTasks: Granular actions → Type:
task
CRITICAL: Extract ALL details from plan - see Information Extraction.
Step 2: Create Self-Contained Tasks
Each task must include complete context for agent to work independently. Agent selects by priority only - no hierarchy traversal.
See Self-Contained Tasks for template and examples.
Step 3: Add Dependencies
Use appropriate dependency types: blocks, depends_on, related, discovered-from.
See Dependency Types for patterns.
Rules Summary
Detailed rules in rules/ directory:
- TDD-First Approach - Mandatory Red→Green→Refactor for features/bugs
- Type Schema - TypeScript type definition and task characteristics
- Self-Contained Tasks - 1500+ char descriptions with complete context
- Information Extraction - Extract requirements, user stories, specs
- Dependency Types - blocks, related, discovered-from, parent-child
- Priority Scale - P0-P4 rationale (hard tasks first)
- Labels Organization - Feature grouping, TDD phases, stack tags
- JSONL Queries - 50+ jq command examples
- Best Practices - Output format, expected structure, final checklist
Example
Given:
Feature: User Authentication
- Login with email/password
- JWT tokens (15min access, 7day refresh)
- Rate limiting (5 attempts per 15min)
Convert to JSONL with:
- Complete technical approach (bcrypt, JWT, Redis)
- Implementation details (files, functions, config)
- Error handling (400/401/403/429/500)
- Testing requirements (coverage, test cases)
- Dependencies (bcrypt, jsonwebtoken, ioredis)
See Self-Contained Tasks for full example.
Related Skills
/tdd-integration- TDD Red-Green-Refactor cycle for implementation
Output Structure
└── plan/issues.jsonl # One issue per line, dependencies embedded
Each line: complete JSON object following Type Schema.
STOP ONCE JSONL IS CREATED! DO NOT IMPLEMENT OR TEST ANYTHING YET!
Related Skills
adrianbrowning/typescript-patterns
development
VerifiedTrustedCommunity
Best practices for TypeScript types, interfaces, assertions, and type safety. Use when writing or reviewing TypeScript code.
SKILL.mdUpdated Mar 27, 2026
adrianbrowning/skills/testing-best-practice
development
VerifiedTrustedCommunity
--- name: testing-best-practice description: A Skill for writing, reviewing, and refactoring tests using Artem-style principles: test intent over implementation, mock boundaries not internals, avoid flakiness, prefer integration tests, and use `using` for cleanup. --- # Testing Best Practice ## Instructions When the user asks for help with tests (writing new tests, improving existing ones, or defining testing standards), follow these rules: 1. **Test intent, not implementation** - Make te
SKILL.mdUpdated Mar 27, 2026
adrianbrowning/tdd-integration
development
VerifiedTrustedCommunity
Enforce Test-Driven Development with strict Red-Green-Refactor cycle using integration tests. Auto-triggers when implementing new features or functionality. Trigger phrases include "implement", "add feature", "build", "create functionality", or any request to add new behavior. Does NOT trigger for bug fixes, documentation, or configuration changes.
SKILL.mdUpdated Mar 27, 2026
adrianbrowning/react-router-loader-performance
development
VerifiedTrustedCommunity
React Router v7 loader performance optimization techniques. Use when optimizing TTFB, eliminating waterfalls, consolidating database queries, or streaming secondary data in loaders. Triggers on "slow loaders", "optimize TTFB", "speed up React Router", "loader performance", or when loaders exceed 500ms response time.
SKILL.mdUpdated Mar 27, 2026