From skillkit
Guides Claude Code skill creators: explains skills, skills vs subagents, decision framework, platform rules, and validates existing skills before building.
How this skill is triggered — by the user, by Claude, or both
Slash command
/skillkit:skillkit-helpThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Detect which path the user needs and jump directly to it.
knowledge/application/09-case-studies.mdknowledge/application/12-testing-and-validation.mdknowledge/foundation/01-why-skills-exist.mdknowledge/foundation/02-skills-vs-subagents-comparison.mdknowledge/foundation/03-skills-vs-subagents-decision-tree.mdknowledge/foundation/06-platform-constraints.mdknowledge/foundation/08-when-not-to-use-skills.mdDetect which path the user needs and jump directly to it.
| User says | Route |
|---|---|
| "what are skills", "how do skills work", "explain", "understand", "not sure", "should I" | → Path A |
| "validate", "check", "review my skill", "is this good" | → Path B |
| "ready to build", "let's create", "make a skill" | Tell them: "You're ready — invoke /skillkit directly to start building." |
| Ambiguous | Ask: "Do you want to (A) understand how skills work, (B) validate an existing skill, or are you ready to build (invoke /skillkit)?" |
Goal: Build a mental model of skills — what they are, when to use them, and whether you actually need one — before starting to build.
Step 1 — Why skills exist
Load and read in full: knowledge/foundation/01-why-skills-exist.md
Summarize for the user: skills are reusable prompt-time instructions that extend your agent's behavior for specific tasks. They live in ~/.claude/skills/ and are invoked via /skill-name.
Step 2 — Skills vs subagents
Load and read: knowledge/foundation/02-skills-vs-subagents-comparison.md
Explain the difference with a concrete example:
/review-pr, load these code review instructions"Step 3 — Decision framework
Load and read: knowledge/foundation/03-skills-vs-subagents-decision-tree.md
Walk the user through the decision tree for their specific use case.
Step 4 — Platform constraints
Load and read: knowledge/foundation/06-platform-constraints.md
Cover the key rules: frontmatter requirements, size limits, trigger conditions.
Step 5 — Hand off to the builder
Tell the user: "You now have enough context to start building. Invoke /skillkit — it will guide you through the full creation workflow."
Goal: Check an existing skill for quality issues before sharing or publishing.
Step 1 — Load validation standards
Load and read in full: knowledge/application/12-testing-and-validation.md
Step 2 — Run the checklist
Ask the user to share their SKILL.md content or path. Then check:
name, description, category all present## headingsReport findings: pass/fail per item, specific fix for each failure.
npx claudepluginhub rfxlamia/skillkit --plugin verify-before-shipCreates new Claude Code skills from scratch following best practices for structure, naming, frontmatter, progressive disclosure, reference organization, and tool scoping. Use for building skills or converting slash commands.
Creates, modifies, improves, tests, and benchmarks Claude Code skills using category-aware design, gotchas-driven development, eval prompts, and performance analysis.
Creates, fixes, analyzes, and validates skills for AI agents. Includes scripts for structure checks, quality analysis, and character budget management.