CLAUDE MD Initializer

Use when onboarding a repository into Claude Code by creating or improving CLAUDE.md, and optionally identifying useful skills, hooks, and verifier setup.

Security Scan

This instruction-only skill is internally consistent with its stated purpose (creating/improving CLAUDE.md for a repo) and does not request extra credentials, installs, or unusual privileges.

Purpose & Capability

Name, description, and SKILL.md align: the skill's stated goal is to read a repository and produce a CLAUDE.md and optional recommendations. It does not request unrelated binaries, env vars, or config paths.

Instruction Scope

Instructions ask the agent to read repository structure, README, existing instructions, and tooling config — which is appropriate for onboarding documentation. Recommend adding an explicit guardrail to avoid reading or including secrets (e.g., .env, private keys, credentials) in the produced CLAUDE.md; the current guardrails prohibit inventing commands but don't explicitly restrict handling of sensitive files.

Install Mechanism

No install spec and no code files; instruction-only skills have minimal disk/write footprint and the lowest install risk.

Credentials

The skill declares no required environment variables, credentials, or config paths — proportional to its purpose.

Persistence & Privilege

always is false and the skill does not request persistent system-wide changes. disable-model-invocation is false (normal). Nothing in the skill attempts to modify other skills or agent configs.

Scan Findings in Context

[no_regex_findings] expected: The scanner found no matches; this is expected because the skill is instruction-only (no code files for regex analysis).

Assessment

This skill appears coherent and appropriate for producing repository onboarding docs. Before installing, consider: (1) review or augment the SKILL.md to explicitly exclude reading or embedding secrets (e.g., .env, private keys, CI secrets) and add an exclusion list; (2) run the skill on a fork or read-only copy first to confirm it doesn't surface sensitive data; (3) review any generated CLAUDE.md for accidental inclusion of credentials before committing; (4) because the skill's source is unknown, prefer installing it in a limited/sandboxed environment or after verifying its origin if you require higher assurance.

Use this skill when a repo needs onboarding documentation for future agent sessions.

Workflow

1. Read the repository structure, README, existing instructions, and tooling config.
2. Identify key build, test, and run commands.
3. Summarize the high-level architecture and important conventions.
4. Create or improve CLAUDE.md without stuffing it with generic advice.
5. Suggest follow-on skills, hooks, or verifier setup if they materially help.

Guardrails

• Do not invent commands or conventions.
• Focus on repo-specific knowledge, not generic coding advice.
• Keep the file practical for future agent sessions.

Example Requests

• Analyze this repo and produce a strong CLAUDE.md for future agent sessions.
• Upgrade the existing CLAUDE.md so future coding agents onboard faster.

Inputs

• Repository structure
• Existing docs and config
• Important commands and conventions

Outputs

• New or improved CLAUDE.md
• Optional follow-up recommendations

Success Criteria

• Repo-specific commands are captured correctly.
• Architecture notes are practical, not generic.
• The file helps future agents move faster.

Non-Goals

• Generic engineering advice
• Invented commands or undocumented workflows

Source Provenance

Derived from src/commands/init.ts.