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

150 stars 32 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add guia-matthieu/clawfu-skills --skill rlm
Manual install
git clone --depth 1 https://github.com/guia-matthieu/clawfu-skills.git /tmp/clawfu-skills
mkdir -p ~/.claude/skills
cp -r /tmp/clawfu-skills/skills/meta/rlm ~/.claude/skills/rlm

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 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.

```bash
# 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

1. **NEVER** read more than 3-5 files into your main context
2. **ALWAYS** use parallel agents when file count > 5
3. **Write Python scripts** for state tracking across 50+ files — let the script scan and summarize
4. 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.
Read the full skill on GitHub

Details

Skill name
rlm
Path
skills/meta/rlm/SKILL.md
License
MIT
Repo updated
1 October 2026

FAQ

What does the Rlm skill do?

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

How do I install the Rlm skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add guia-matthieu/clawfu-skills --skill rlm. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Rlm popular?

It lives in guia-matthieu/clawfu-skills, which has 150 GitHub stars and 32 forks, and is included in 1 curated skill list.

Related skills

Aarrr Metrics

150

guia-matthieu/clawfu-skills

Measure and optimize growth using the AARRR (Pirate Metrics) framework with stage-specific KPIs and funnel analysis

Marketing, Sales & BusinessIn 1 list32

Ab Test Stats

150

guia-matthieu/clawfu-skills

Calculate A/B test statistical significance. Use when: determining if test results are significant; calculating required sample size; estimating test duration; analyzing conversion experiments; making data-driven decisions

Testing & QAIn 1 list32

Account Health

150

guia-matthieu/clawfu-skills

Assess customer account health using product usage, support sentiment, payment status, and relationship signals

Finance & CryptoIn 1 list32

Sonarqube AI Slop Gate

228

pproenca/dot-skills

Corrects the wrong defaults a model has when standing up self-hosted SonarQube Server as a continuous gate on AI-generated code, verified against docs.sonarsource.com in July 2026 (Server 2026.3, LTA 2026.1). Use when configuring SonarQube, designing a quality gate, or wiring a scan step into CI for AI-assisted work. Covers the setups that run green while measuring almost nothing — the fudge factor skips duplication and coverage conditions below 20 new lines and is on by default; duplication is never measured on test code; no `new_cognitive_complexity` metric exists to gate on; `sonar.host.url

AI, LLMs & Agents19

Reserved Handle Policy

201

swyxio/skills

Design, implement, audit, or refresh protected username and handle namespaces for public products. Use whenever a product has open signup, mutable handles, profile URLs, impersonation or squatting risk, reserved route names, short usernames, common-word or common-name claims, developer/AI terminology, notable social identities, or administrator-approved handle assignment—even if the user only asks for a username denylist.

AI, LLMs & Agents12

Summarize Anything

201

swyxio/skills

Summarizes arbitrarily long text (1k-1M words) using recursive map-reduce with any LLM backend. Accepts raw text, markdown, transcripts, articles, codebases, or any plaintext input. Produces one or more output formats: executive summary, section headings with timestamps, YouTube description, Twitter/X posts, title options, thumbnail prompts, blog outlines, pull quotes, and more. Supports focus directives ("focus on the AI parts", "emphasize the business angle") to steer the summary. Pluggable backends: OpenRouter, Ollama, OpenAI, Anthropic, Gemini, or any OpenAI-compatible endpoint. Use this s

AI, LLMs & Agents12

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.