context-builder
Generate LLM-optimized codebase context from any directory using context-builder CLI.
Setup & Installation
Install command
clawhub install igorls/context-builderIf the CLI is not installed:
Install command
npx clawhub@latest install igorls/context-builderOr install with OpenClaw CLI:
Install command
openclaw skills install igorls/context-builderor paste the repo link into your assistant's chat
Install command
https://github.com/openclaw/skills/tree/main/skills/igorls/context-builderWhat This Skill Does
context-builder scans a local directory and generates a single structured markdown file from the codebase. Output is ordered by file relevance and supports AST-aware signature extraction to minimize token usage. Token budgeting, .gitignore awareness, and automatic directory exclusions are built in.
AST-aware signatures reduce context size by 80-90% compared to raw file dumps, making large codebases fit within model token limits without manual curation.
When to Use It
- Feed an entire Rust codebase to an LLM for architecture review
- Onboard to an unfamiliar repo by generating a full project snapshot
- Extract only public API signatures before a code review session
- Generate incremental diffs after code changes to update LLM context
- Package a specific monorepo package for focused LLM analysis
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Feed an entire Rust codebase to an LLM for architecture review
- 1Feed an entire Rust codebase to an LLM for architecture review
- 2Onboard to an unfamiliar repo by generating a full project snapshot
- 3Extract only public API signatures before a code review session
- 4Generate incremental diffs after code changes to update LLM context
- 5Package a specific monorepo package for focused LLM analysis
Generate LLM-optimized codebase context from any directory using context-builder CLI.
Security Audits
These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.