Agent skill
touch-skill
Create or update agent skills. Use when creating new skills from scratch, refactoring existing skills, or validating skills. Provides templates, validation, and progressive disclosure patterns.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/touch-skill
SKILL.md
Ultrathink.
Role
You are a skill architect. Create or update skills — not features or existing code.
Context Assessment
- Similar skill exists? → Suggest enhancing instead
- Requirements already gathered? → Skip research
Core Principles
- Skills are not documentation — Active workflow knowledge, not passive reference
- Soft line limits — SKILL.md ~150, references ~500, workflows ~200
- Progressive disclosure — Load details on-demand via references/workflows
- Script-first — Executable scripts for deterministic, token-efficient operations
- SKILL.md = philosophy, not patterns — Principles (WHY) inline, details (HOW) in references
- Link, don't embed — Cross-reference with "-> See [file.md]" pattern
- Right-altitude — Concrete but not hardcoded
- Anti-convergence — List what to avoid, suggest uncommon alternatives
Process
1. Understand
- Parse requirements from
$ARGUMENTS - Identify skill purpose, scope, and type (knowledge vs workflow)
2. Research
Three sources make a good skill. Follow skill-research.md.
- Discover existing skills — Search skill-sources.md. Skim SKILL.md first to check scope relevance. If relevant, read references and produce an extraction note (reuse/skip/gaps). If not relevant, state why and move on.
- Fetch official docs — Combine with
researchanddocs-seekerskill. Extract correct API patterns, vendor recommendations, and migration guides. - Synthesize — Combine existing skill patterns with official docs into right-altitude domain knowledge. Skills teach how to use a technology well, not project conventions. Flag any content from model knowledge (no doc backing).
If user provides URLs → explore internal links for additional content.
3. Design
- Plan SKILL.md structure using appropriate template
- For knowledge skills → See skill-template.md
- For workflow skills → See workflow-skill-template.md and workflow-patterns.md
GATE: User approves skill design before creation.
4. Create
Create at .claude/skills/{skill-name}/:
SKILL.md— main entry pointreferences/— supporting documentationscripts/— executable utilities (if needed)templates/— reusable templates (if needed)
Quick start scripts:
scripts/init_skill.py <skill-name> --path <output-directory>
scripts/init_workflow_skill.py <skill-name> --path <output-directory>
5. Validate
scripts/validate_skill.py <path/to/skill>
scripts/validate_skill.py <path/to/skill> --type=workflow
Skill Types
Knowledge/Reference Skills
- See anatomy.md for structure and YAML frontmatter
- See design-principles.md for philosophy
Workflow Skills
Task runners (/cook, /fix, /discuss) with roles, processes, gates, and $ARGUMENTS.
- See workflow-patterns.md for patterns
- See workflow-skill-template.md for template
References
| Reference | Content |
|---|---|
| anatomy.md | Skill structure, YAML frontmatter |
| requirements.md | Line limits, naming, .env rules |
| bundled-resources.md | scripts/, references/, assets/ |
| design-principles.md | Philosophy, progressive disclosure |
| workflow-patterns.md | Gates, delegation, role boundaries |
| examples.md | Good/bad patterns |
| skill-sources.md | Curated external skill sources and repositories |
Scripts
| Script | Purpose |
|---|---|
init_skill.py |
Initialize new skill from template |
init_workflow_skill.py |
Initialize workflow-type skill |
validate_skill.py |
Validate skill structure (--type=workflow for workflow checks) |
package_skill.py |
Create distributable zip |
Templates
| Template | Purpose |
|---|---|
| skill-template.md | Knowledge/reference SKILL.md |
| workflow-skill-template.md | Workflow/task-runner SKILL.md |
| script-template.py | Example Python script |
| reference-template.md | Example reference file |
Workflows
- New Skill — Requirements to packaging
- Refactor Skill — Break down bloated skills
- Validation & Packaging — Validate and distribute
- Research — Discover, extract, and synthesize from existing skills and docs
Requirements
$ARGUMENTS
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?