Ready to supercharge your AI agents?

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

Init Deep — Progressive Disclosure CLAUDE.md · majiayu000 | DecimalAI

agent toolingby majiayu000

Init Deep — Progressive Disclosure CLAUDE.md

majiayu000/agent-init-deep

Source majiayu000/claude-skill-registry ↗License MIT

Initialize or migrate to nested CLAUDE.md structure for progressive disclosure. Claude auto-loads CLAUDE.md from any directory it enters, so nested files get discovered automatically.

SkillScore91Maintained

Automatic

AI Engineer pack

Last verified 8/18/2026

What it changes

Passed 20 of 22 test cases with the skill, and 7 of 22 without it.

Without skill32%

With skill91%

Checks it passed that the model alone missed

Requests definition of done requirements.
Specifies the directory path as docs/agents/.
Uses CLAUDE.md as the root instructions file name.

and 13 more in the full report

13 fixed7 passed either way2 still failing0 broke

Pass-rate lift: +59 pp
Tokens: +44%
Agent turns: 0%
Response time: -43%

Model gemini-3.6-flashMeasured 8/18/2026v120 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/majiayu000-agent-init-deep/SKILL.md https://app.decimal.ai/s/majiayu000-agent-init-deep/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add majiayu000-agent-init-deep, 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/majiayu000-agent-init-deep/ and pins it in .decimal/skills.lock

decimalai skills add majiayu000-agent-init-deep

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

curl -fsSL --create-dirs -o .claude/skills/majiayu000-agent-init-deep/SKILL.md https://app.decimal.ai/s/majiayu000-agent-init-deep/SKILL.md

Raw file: /s/majiayu000-agent-init-deep/SKILL.md ↗ · machine-readable summary at /s/majiayu000-agent-init-deep.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 13

Prompt

We are setting up a root CLAUDE.md file. What is the target line count range for keeping root context minimal and high-value?

What was checked, without and with the skill
Checked	Without skill	With skill
Recommends approximately 40 to 50 lines for the root CLAUDE.md file.	Missed	Passed

case-05 · gemini-3.6-flash · 8/18/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md166 linessingle file

Init Deep — Progressive Disclosure CLAUDE.md

Set up or migrate to a progressive disclosure CLAUDE.md structure using docs/agents/ for topic-specific guidance.

Context Model

Static (root CLAUDE.md)      — loaded every conversation, minimal, high-value
Semi-dynamic (docs/agents/)  — linked from root, loaded on-demand when relevant
Fully dynamic (skills)       — triggered by metadata match, loaded only when invoked

Root CLAUDE.md should be ~40-50 lines. Everything else belongs in docs/agents/ or skills.

Target Structure

CLAUDE.md                        # Root: identity, tech stack, key rules, workflow, links
docs/agents/
├── tooling.md                   # e.g. package manager, linting, formatting, hooks
├── commands.md                  # e.g. script execution, build filters, passing args
├── guardrails.md                # e.g. data isolation, secrets, library docs
├── definition-of-done.md       # e.g. coverage, lint, type-check, format requirements
└── [topic].md                   # Additional topic-specific files as needed

Workflow

Step 1: Detect State

Check for:
- CLAUDE.md exists?
- docs/agents/ exists?
- How many lines is CLAUDE.md?

If no CLAUDE.md → Greenfield path If CLAUDE.md exists → Migration path

Track record

Benchmark

20 / 22

test cases passed, vs 7 / 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 — 8/3/2026

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

majiayu000 / claude-skill-registry

skills/agent/agent-init-deep/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

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

Ready to supercharge your AI agents?

See it in action

What's inside

Init Deep — Progressive Disclosure CLAUDE.md

Context Model

Target Structure

Workflow

Step 1: Detect State

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills