Agent skill
meta-optimize-skill-md
Reviews and improves existing skills by auditing clarity, trigger quality, workflow completeness, and instruction density, then rewriting SKILL.md with minimal-drift improvements. Use when user asks to improve a skill, review SKILL.md, optimize skill prompts, tighten skill descriptions, or refactor skill documentation.
Install this agent skill to your Project
npx add-skill https://github.com/jasonraimondi/dotfiles/tree/macos/config/skillshare/skills/meta-optimize-skill-md
SKILL.md
Optimize Existing Skills
Improve existing skills by preserving intent while making SKILL.md clearer, easier to trigger, and more execution-ready.
When to use
Use this skill when the user asks to:
- improve an existing skill
- review or rewrite
SKILL.md - optimize skill trigger descriptions
- reduce ambiguity in skill instructions
- tighten or refactor skill documentation
Required workflow
- Locate and read the target
SKILL.mdfully. - Map current intent in 3-6 bullets before editing.
- Audit quality using the rubric below.
- Propose changes grouped as:
- keep (already strong)
- tighten (wording/structure)
- add (missing critical guidance)
- remove (noise/redundancy)
- Rewrite with minimal drift:
- keep core behavior and scope
- improve wording, ordering, and actionability
- avoid introducing new product/domain claims
- Return both:
- concise review summary
- improved
SKILL.mdcontent (or patch-ready diff)
Optimization rubric
1) Frontmatter quality
nameis stable and slug-safedescriptionclearly states capability + trigger contexts- Trigger language includes realistic user phrases
- Description remains concise and specific
2) Trigger precision
- Skill should be discoverable from common user wording
- Trigger list avoids over-broad claims
- Adjacent skills are not duplicated without need
3) Instruction quality
- Steps are explicit, ordered, and observable
- Ambiguous phrases replaced with concrete actions
- “Do this first” constraints are clearly marked
- Safety/guardrail rules are easy to spot
4) Information architecture
- Most important guidance appears early
- Long sections are chunked with headings/lists
- Optional/advanced material is separated from core flow
5) Token efficiency
- Remove repeated ideas
- Prefer short, directive sentences
- Keep examples only when they reduce ambiguity
Rewrite standards
- Preserve original intent and scope unless user asks to expand
- Prefer minimal-diff edits over full rewrites
- Keep voice imperative and implementation-oriented
- Use checklists for repeatable procedures
- Keep claims timeless (avoid version/date-sensitive phrasing)
Output format
- Audit summary (strengths, gaps, risks)
- Optimization plan (what changed and why)
- Improved
SKILL.md - Open questions (if any assumptions remain)
Anti-patterns
- Rewriting into a different skill/domain
- Adding verbose theory with no execution value
- Removing trigger phrases that aid discovery
- Making the skill longer without improving clarity
- Introducing tools/workflows not available in the environment
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
tools-image-manipulation-image-magick
Process and manipulate images using ImageMagick. Supports resizing, format conversion, batch processing, and retrieving image metadata. Use when working with images, creating thumbnails, resizing wallpapers, or performing batch image operations.
frontend-react-doctor
Run after making React changes to catch issues early. Use when reviewing code, finishing a feature, or fixing bugs in a React project.
typescript-advanced-types
Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications. Use when implementing complex type logic, creating reusable type utilities, or ensuring compile-time type safety in TypeScript projects.
typescript-better-auth-best-practices
Skill for integrating Better Auth - the comprehensive TypeScript authentication framework.
testing-tdd
Test-driven development with red-green-refactor loop. Use when user wants to build features or fix bugs using TDD, mentions "red-green-refactor", wants integration tests, or asks for test-first development.
planning-interview-me
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "interview me".
Didn't find tool you were looking for?