Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Ariadne Thread · LeoYeAI | DecimalAI

documentationby LeoYeAI

Ariadne Thread

ariadne-thread

Source LeoYeAI/openclaw-master-skills ↗License MIT

Create 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", "proj

SkillScore36Maintained

Automatic

AI Engineer pack

Last verified 7/26/2026

What it changes

Passed 8 of 22 test cases with the skill, and 1 of 22 without it.

Without skill5%

With skill36%

7 fixed1 passed either way14 still failing0 broke

Pass-rate lift: +32 pp
Tokens: +252%
Agent turns: 0%
Response time: -34%

Model gemini-3.6-flashMeasured 7/26/2026v18 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/ariadne-thread/SKILL.md https://app.decimal.ai/s/ariadne-thread/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ariadne-thread, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/ariadne-thread/ and pins it in .decimal/skills.lock

decimalai skills add ariadne-thread

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ariadne-thread/SKILL.md https://app.decimal.ai/s/ariadne-thread/SKILL.md

Raw file: /s/ariadne-thread/SKILL.md ↗ · machine-readable summary at /s/ariadne-thread.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

What's inside

The instructions your model reads when the skill loads.

SKILL.md426 lines6 files

Ariadne Thread

Create codebases that AI agents can navigate efficiently through progressive disclosure — revealing only what's needed, when it's needed.

When to Use

Apply this skill when the user:

Starts a new project and wants AI-friendly structure
Restructures or indexes an existing codebase
Adds project navigation (AGENTS.md, INDEX.md, llms.txt)
Designs module boundaries and dependencies
Mentions: "AI-friendly project", "progressive disclosure", "project index", "codebase navigation", or "ariadne"

Language-agnostic: applies to any language. See language-adaptation.md for per-language mappings.

When NOT to apply: Minimal single-file projects, quick prototypes, or codebases where indexing overhead outweighs benefit. Skip full L1/L2 when the project has fewer than ~5 source files; a lightweight AGENTS.md may suffice.

Core Philosophy

Like Ariadne's thread through the labyrinth, a well-indexed codebase gives AI agents a clear path from project overview to implementation detail. An agent should understand your project structure, locate any function, and assess the impact of any modification — without reading the entire codebase.

Two optimization targets:

Navigation efficiency — minimize tokens consumed to find the right code
Modification safety — maximize probability of correct changes via explicit contracts and dependency visibility

The 4-Level Index Architecture

L0  PROJECT ROOT     ← AGENTS.md (80–150 lines, prefer brevity)
│                       Project map, navigation table, build commands, cross-cutting patterns
│
L1  MODULE INDEX     ← Each directory gets an INDEX.md (~50 lines)
│                       Purpose, public API, bidirectional dependencies, contracts,
│                       task routing, modification risk, test mapping
│
L2  FILE INTENT      ← File headers (~5-10 lines per file)
│                       What this file does, public interface, contracts, side effects
│
L3  INLINE DETAIL    ← Comments on non-obvious logic only
                        Why, not what; tricky edge cases; business rules

Track record

Benchmark

8 / 22

test cases passed, vs 1 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/ariadne-thread/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 5 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

What's inside

Ariadne Thread

When to Use

Core Philosophy

The 4-Level Index Architecture

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills