$ loading_
Create, revise, and validate AI skills before deployment.
The material indicates a prompt/documentation-only writing methodology skill with no required secrets, no declared remote endpoints, and no described code execution or data exfiltration behavior. Given its open-source and auditable nature, overall risk is low, though supply-chain caution remains due to low adoption and unknown maintenance status.
The material explicitly states that no keys or environment variables are required, and the README does not request login, API tokens, or other sensitive credentials, so no clear credential exposure or abuse surface is evident.
The system flags it as prompt-only and lists no remote endpoint hosts; the content is primarily a methodology for writing skills and does not describe sending user data to any external service.
As a skill marked prompt-only, the material contains no installation, script execution, local process spawning, or system command invocation instructions; the referenced directory paths appear to be documentation examples rather than execution capabilities.
The README mentions that personal skills typically live under specific user-directory paths, but it does not state that it will automatically read, modify, or upload those files; based on the material, it appears to be a static reference document without excessive data access requests.
The source is an open-source GitHub repository, which is a meaningful risk-reducing factor due to auditability; however, the license is unspecified, community adoption is 0 stars, and maintenance status is unknown, so trust and ongoing maintenance evidence are limited and the repository should be reviewed before use.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "writing-skills" skill from askskill: 1. Download https://raw.githubusercontent.com/obra/superpowers/main/skills/writing-skills/SKILL.md 2. Save it as ~/.claude/skills/writing-skills/SKILL.md 3. Reload skills and tell me it's ready
Generate a complete definition for a “meeting notes organizer” skill, including purpose, input/output constraints, sample prompts, and test cases.
A structured new skill draft with description, rules, examples, and basic validation content.
Improve this skill description to make trigger conditions clearer, and add three usage examples that better match real user scenarios.
Revised skill copy with clearer trigger conditions and more practical examples.
Review this skill for unclear definitions, weak examples, or missing edge cases, then provide fixes and a validation checklist.
A list of issues, improvement suggestions, and validation steps for pre-launch review.
Writing skills IS Test-Driven Development applied to process documentation.
Personal skills live in agent-specific directories (~/.claude/skills for Claude Code, ~/.agents/skills/ for Codex)
You write test cases (pressure scenarios with subagents), watch them fail (baseline behavior), write the skill (documentation), watch tests pass (agents comply), and refactor (close loopholes).
Core principle: If you didn't watch an agent fail without the skill, you don't know if the skill teaches the right thing.
REQUIRED BACKGROUND: You MUST understand superpowers:test-driven-development before using this skill. That skill defines the fundamental RED-GREEN-REFACTOR cycle. This skill adapts TDD to documentation.
Official guidance: For Anthropic's official skill authoring best practices, see anthropic-best-practices.md. This document provides additional patterns and guidelines that complement the TDD-focused approach in this skill.
A skill is a reference guide for proven techniques, patterns, or tools. Skills help future Claude instances find and apply effective approaches.
Skills are: Reusable techniques, patterns, tools, reference guides
Skills are NOT: Narratives about how you solved a problem once
| TDD Concept | Skill Creation |
|---|---|
| Test case | Pressure scenario with subagent |
| Production code | Skill document (SKILL.md) |
| Test fails (RED) | Agent violates rule without skill (baseline) |
| Test passes (GREEN) | Agent complies with skill present |
| Refactor | Close loopholes while maintaining compliance |
| Write test first | Run baseline scenario BEFORE writing skill |
| Watch it fail | Document exact rationalizations agent uses |
| Minimal code | Write skill addressing those specific violations |
| Watch it pass | Verify agent now complies |
| Refactor cycle | Find new rationalizations → plug → re-verify |
The entire skill creation process follows RED-GREEN-REFACTOR.
Create when:
Don't create for:
Concrete method with steps to follow (condition-based-waiting, root-cause-tracing)
Way of thinking about problems (flatten-with-flags, test-invariants)
API docs, syntax guides, tool documentation (office docs)
skills/
skill-name/
SKILL.md # Main reference (required)
supporting-file.* # Only if needed
Flat namespace - all skills in one searchable namespace
Separate files for:
Keep inline:
Frontmatter (YAML):
name and description (see agentskills.io/specification for all supported fields)name: Use letters, numbers, and hyphens only (no parentheses, special chars)description: Third-person, describes ONLY when to use (NOT what it does)
---
name: Skill-Name-With-Hyphens
…
Execute implementation plans by splitting and advancing independent tasks in-session.
Systematically investigate bugs, test failures, and unexpected behavior before fixing.
Helps decide merge, PR, or cleanup steps after branch work is complete.
Turn requirements into a clear step-by-step execution plan before implementation.
Set conversation rules to discover and invoke skills before replying.
Clarify intent, requirements, and solution direction before any creative implementation work.
Create a custom skill with structure, documentation, and optional bundled scripts.
Create or refine AI skills with scope, workflows, and tool integrations.
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.
Create or update skills that extend Codex with knowledge, workflows, and tools.
Create, refine, validate, and restructure AgentSkills and SKILL.md files.
Create reusable SKILL.md skills that package repeatable workflows for future use.