nomad3/writing-plans
apps/api/app/skills/_bundled/writing-plans/SKILL.md
--- name: writing-plans engine: markdown version: 1 category: coding tags: [planning, tdd, implementation, tasks] auto_trigger: "Use when creating an implementation plan for a multi-step feature or task" source_repo: https://github.com/obra/superpowers --- ## Description Create comprehensive, bite-sized implementation plans with full file structure mapping, TDD steps, and zero placeholders. # Writing Plans ## Overview Write comprehensive implementation plans assuming the engineer has zero co
$ install --global
skillsauthnpx skillsauth add nomad3/servicetsunami-agents writing-plansInstall 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: Jun 12, 2026, 7:02 AM166.8s1 file scanned
SKILL.md
- name:
- writing-plans
- engine:
- markdown
- version:
- 1
- category:
- coding
- tags:
- [planning, tdd, implementation, tasks]
- auto_trigger:
- Use when creating an implementation plan for a multi-step feature or task
- source_repo:
- https://github.com/obra/superpowers
Description
Create comprehensive, bite-sized implementation plans with full file structure mapping, TDD steps, and zero placeholders.
Writing Plans
Overview
Write comprehensive implementation plans assuming the engineer has zero context for our codebase and questionable taste. Document everything they need to know: which files to touch for each task, code, testing, docs they might need to check, how to test it. Give them the whole plan as bite-sized tasks. DRY. YAGNI. TDD. Frequent commits.
Assume they are a skilled developer, but know almost nothing about our toolset or problem domain. Assume they don't know good test design very well.
Announce at start: "I'm using the writing-plans skill to create the implementation plan."
Scope Check
If the spec covers multiple independent subsystems, suggest breaking this into separate plans — one per subsystem. Each plan should produce working, testable software on its own.
File Structure
Before defining tasks, map out which files will be created or modified and what each one is responsible for.
- Design units with clear boundaries and well-defined interfaces.
- Prefer smaller, focused files over large ones that do too much.
- Files that change together should live together.
- In existing codebases, follow established patterns.
Bite-Sized Task Granularity
Each step is one action (2-5 minutes):
- "Write the failing test" — step
- "Run it to make sure it fails" — step
- "Implement the minimal code to make the test pass" — step
- "Run the tests and make sure they pass" — step
- "Commit" — step
Task Structure
Each task block:
- State exact file paths to create/modify/test
- Provide actual code in every step (no placeholders)
- Provide exact commands with expected output
- Use checkbox syntax for tracking:
- [ ] Step N: ...
No Placeholders
Never write: "TBD", "TODO", "implement later", "add error handling", "write tests for the above" without actual test code, "similar to Task N".
Self-Review
After writing the plan:
- Spec coverage: Can you point to a task for every requirement?
- Placeholder scan: Any red flags from the No Placeholders section?
- Type consistency: Do signatures in later tasks match earlier definitions?
Fix inline. Then save the plan to docs/plans/YYYY-MM-DD-<feature-name>.md.
Related Skills
nomad3/smart-commit
development
VerifiedTrustedCommunity
--- name: smart-commit engine: markdown version: 1 category: coding tags: [git, commit, quality, conventional-commits] auto_trigger: "Use when ready to commit changes with quality checks and a good commit message" source_repo: https://github.com/angakh/claude-skills-starter --- ## Description Run quality checks, then stage and commit with a well-formed conventional commit message. # Smart Commit ## Overview Run quality checks, then stage and commit with a well-formed conventional commit mess
1SKILL.mdUpdated Jun 12, 2026
nomad3/security-review
development
VerifiedTrustedCommunity
--- name: security-review engine: markdown version: 1 category: coding tags: [security, owasp, vulnerabilities, pentest, audit] auto_trigger: "Use when doing a security audit, reviewing auth code, or before merging sensitive changes" --- ## Description Deep security audit of changed code focused exclusively on vulnerabilities — more thorough than a regular code review. # Security Review ## Overview Deep security audit of changed code. Focuses exclusively on vulnerabilities — more thorough th
1SKILL.mdUpdated Jun 12, 2026
nomad3/scaffold
tools
VerifiedTrustedCommunity
--- name: scaffold engine: markdown version: 1 category: coding tags: [scaffold, boilerplate, codegen, templates, components] auto_trigger: "Use when generating boilerplate for a new component, endpoint, model, or test file" source_repo: https://github.com/angakh/claude-skills-starter --- ## Description Generate boilerplate for common code structures: React components, API endpoints, test files, data models, CLI commands. # Scaffold ## Overview Generate boilerplate for common code structures
1SKILL.mdUpdated Jun 12, 2026
nomad3/run-tests
development
VerifiedTrustedCommunity
--- name: run-tests engine: markdown version: 1 category: coding tags: [testing, pytest, jest, coverage, quality] auto_trigger: "Use when running the test suite or checking test coverage" source_repo: https://github.com/angakh/claude-skills-starter --- ## Description Auto-detect the project's test framework and run the full test suite with coverage reporting. # Run Tests ## Overview Auto-detect the project's test framework and run the full test suite with coverage. **Announce at start:** "R
1SKILL.mdUpdated Jun 12, 2026