ai-tools/fine-grained-skill-builder/SKILL.md
Guide for building fine-grained skills where content is split into many small files to minimize tokens loaded per invocation. Use when creating or restructuring a skill to be token-efficient with section-based progressive disclosure.
npx skillsauth add randyhaylor/enhanceclaude fine-grained-skill-builderInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Minimize tokens loaded per invocation by breaking content into small, purpose-specific files loaded only when needed.
skill-name/
├── SKILL.md ← frontmatter + TOC only (links to section indexes)
├── section-a/
│ ├── index.md ← section TOC (links to content files)
│ ├── topic-1.md ← 1 table, 1 snippet, or ≤4 bullets
│ └── topic-2.md
├── section-b/
│ ├── index.md
│ └── ...
└── templates/
└── example.xml ← raw assets, no markdown wrapper
SKILL.md body: section list only — no contentindex.md: file list with one-line descriptions — no contentindex.md stub per section upfrontSKILL.md pointing to stubsKey constraint for agent prompts: give each agent an explicit file list and source files. Vague scope causes overlap or gaps.
tools
# XState v5 Quick Reference ## How to Look Up API Details For complete function signatures, types, and interfaces, **grep `api-reference.md`** — do NOT read it in full (12k+ lines). Example: ``` Grep pattern="createActor" path="~/.claude/skills/xstate/api-reference.md" output_mode="content" -C 5 ``` Then use `Read` with `offset`/`limit` to get the full section. This is the primary way to get precise technical info when the quick reference below isn't enough. ## Design Workflow Recommended
tools
Workaround for agent teams in VS Code extension where TeamCreate teammates cannot execute tools. Uses an echo-back-and-resume pattern where agents return tool requests instead of executing them directly.
development
Format documentation, READMEs, and structured text using header hierarchy where each level stands alone. Use when creating docs, research notes, summaries, or when user requests 'scannable,' 'well-structured,' 'skimmable,' or 'readable at multiple depths' output. Applies to markdown, technical specs, and any hierarchical text formatting.
development
Enforce strict Test-Driven Development workflow: write one test, make it pass, verify, then proceed. Prevents over-implementation and ensures code matches requirements exactly. Use when implementing new features, adding settings, or building functionality incrementally.