rlm
Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps
- License 许可
- MIT
- 最近更新
- 2026-05-19
- Stars
- ★ 10
- Forks
- 2
01 前言 Front Matter
- name
- rlm
- license
- MIT
- metadata
- { "author": "ClawFu", "version": "2.1.0", "mcp-server": "@clawfu/mcp-skills" }
- description
- Process large codebases (>100 files) using the Recursive Language Model pattern. Orchestrates parallel sub-agents to map-reduce across files without context rot. Use when: analyzing large repositories; auditing security or auth across many files; finding patterns across 50+ files; processing large log files or data dumps
03 SKILL.md 正文
Recursive Language Model (RLM)
"Context is an external resource, not a local variable."
You are the Root Node. Your job is NOT to read code directly, but to orchestrate sub-agents that read code for you.
The RLM Loop
Phase 1: Index & Filter
Identify relevant files without loading them into context.
# Find candidate files
grep -rl "pattern" src/ --include="*.ts"
find . -name "*.py" -newer last_check
Phase 2: Parallel Map
Split work into atomic units, spawn parallel agents.
- Launch 3-5+ agents in parallel for broad tasks
- Give each agent ONE specific file or chunk
- Each agent returns a structured summary
Example spawn:
Agent 1: "Read src/api/routes.ts. List all endpoints with their auth decorators."
Agent 2: "Read src/api/users.ts. List all endpoints with their auth decorators."
...
Phase 3: Reduce & Synthesize
Collect all agent outputs, find patterns, compile into a coherent answer.
If incomplete, recurse: run a second RLM pass on the specific gaps.
Critical Rules
- NEVER read more than 3-5 files into your main context
- ALWAYS use parallel agents when file count > 5
- Write Python scripts for state tracking across 50+ files — let the script scan and summarize
- If parallel agents are unavailable, fall back to iterative Python scripting
Example: "Find all API endpoints, check for Auth"
Wrong (monolithic): Read each file sequentially → context fills up, reasoning degrades.
RLM Way:
grep -l "@Controller" src/**/*.ts→ 20 files- Spawn 20 agents, each extracts endpoints + auth status
- Collect outputs, compile table, identify missing auth
Output Format
Return a structured summary:
- Findings table (file, pattern, status)
- Gaps identified (what needs deeper investigation)
- Confidence level (how complete the scan was)
Skill Boundaries
Excels for: Codebases >100 files, cross-file pattern search, audit tasks, large file analysis.
Not ideal for: Small projects (<50 files), single file analysis, file modification tasks.
04 同仓库更多 Skills
zarr-python
Chunked N-D arrays for cloud storage. Compressed arrays, parallel I/O, S3/GCS integration, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
youtube-downloader
Download and process YouTube content for research. Use when: downloading competitor videos for analysis; extracting audio for podcasts; getting transcripts for content repurposing; archiving webinars; research content curation
yc-pitch-deck
Create a compelling startup pitch deck that follows the structure proven to raise billions from top investors. Master the YC and Sequoia formats that get founders funded. Use when: **Fundraising** to create investor pitch decks; **YC application** to structure your narrative; **Demo Day prep** to craft your 2-minute pitch; **Angel investors** to communicate your opportunity; **Partnership pitches** to structure compelling asks
x-twitter-scraper
Use when the user needs X (Twitter) data or confirmation-gated X actions through Xquik: tweet search, user lookup, follower extraction, media download, monitoring, webhooks, MCP, SDKs, posting, likes, DMs, and profile updates. Requires a Xquik API key. Never ask for X login material.
write-vignette
Create R package vignettes using R Markdown or Quarto. Covers vignette setup, YAML configuration, code chunk options, building and testing, and CRAN requirements for vignettes. Use when adding a Getting Started tutorial, documenting complex workflows spanning multiple functions, creating domain-specific guides, or when CRAN submission requires user-facing documentation beyond function help pages.
write-validation-documentation
Write IQ/OQ/PQ validation documentation for computerized systems in regulated environments. Covers protocols, reports, test scripts, deviation handling, and approval workflows. Use when validating R or other software for regulated use, preparing for a regulatory audit, documenting qualification of computing environments, or creating and updating validation protocols and reports for new or re-qualified systems.