LeoYeAI/agent-master-skills / skills/ariadne-thread
ariadne-thread
VerifiedCreate AI-friendly project structures using progressive disclosure indexing (AGENTS.md, module INDEX.md files, file intent headers). ALWAYS use this skill when the user wants to: create or update AGENTS.md or llms.txt, add INDEX.md files to modules, set up project navigation for AI agents, retrofit an existing codebase with AI-friendly indexes, design module boundaries with explicit dependency and modification-risk documentation, or mentions "AI-friendly project", "progressive disclosure", "project index", "codebase navigation", or "ariadne". Also use when the user asks how to structure a new project so AI tools can navigate it efficiently, even if they don't use these exact terms.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 24.2 KB |
| _meta.json | config | 462 B |
| references/doc-standards.md | markdown | 7.7 KB |
| references/index-maintenance.md | markdown | 2.7 KB |
| references/index-templates.md | markdown | 25.9 KB |
| references/language-adaptation.md | markdown | 4.1 KB |
| references/naming-api-conventions.md | markdown | 10.6 KB |
references/index-maintenance.md
View on GitHub# Index Maintenance
## Tier A: AI Agent Self-Maintenance (Real-time)
**Directive**: Every code modification MUST include atomic updates to the relevant Tier A indexes. A code change is NOT complete until the indexes reflect it.
| Trigger | Required Action |
|---------|----------------|
| File added | Add entry to parent `INDEX.md` Files table |
| File renamed/moved | Update parent `INDEX.md`; update `AGENTS.md` if in navigation table |
| File deleted | Remove from parent `INDEX.md`; update `AGENTS.md` if in navigation table |
| Module added | Create `INDEX.md` with all sections; update `AGENTS.md` directory map + navigation |
| Module removed | Delete `INDEX.md`; update `AGENTS.md` directory map + navigation table |
| Public API signature changed | Update `INDEX.md`: Public API table, Interface Contract, Modification Risk |
| New dependency added | Update this module's `INDEX.md` Dependencies (Fan-out count) |
| New caller of this module | Update this module's `INDEX.md` Dependents (Fan-in count) |
| Cross-cutting pattern changed | Update `AGENTS.md` Cross-Cutting Patterns section |
| Test added/removed/renamed | Update `INDEX.md` Tests section |
| File header contract changed | Ensure L2 header matches actual function signatures and behavior |
**Anti-patterns**:
- Stale `INDEX.md` → AI navigates to wrong file or misses dependencies
- Stale Dependents list → AI misses affected callers during refactoring (**most dangerous**)
- Updating Tier B docs during active development → wasted tokens, lower quality output
## Tier B: Iteration-End Documentation Sync (Batch)
At the end of a development iteration (sprint, milestone, or feature completion), sync Tier B documents from Tier A indexes:
1. **Review changes**: Scan all `INDEX.md` and `AGENTS.md` modifications since last sync
2. **Update `architecture.md`**: If module structure, dependency graph, or cross-cutting patterns changed
3. **Create/update ADRs**: For any significant architectural decisions made during the iteration
4. **Update API docs**: Derive from `INDEX.md` Public API tables and L2 contract headers
5. **Update `README.md`**: If project scope, build commands, or quick-start steps changed
6. **Update developer guides**: If workflows or deployment steps changed
7. **Update `docs/*/INDEX.md`**: Sync doc directory indexes with any new/removed documents
**Tier B documents reference Tier A as source of truth** — prefer links to `INDEX.md` sections over duplicating content. This keeps human docs shorter and reduces staleness risk.
**AI instruction**: When the user requests "documentation sync", "update docs", or "iteration end", execute this Tier B batch workflow. During normal development, ignore Tier B files entirely.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |