// 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
Run a structured 5-pass finishing audit on any website before launch — scoring visual polish, technical foundation, UX completeness, content quality, and cross-device readiness on 100 points. Use when: **Pre-launch** - Final validation before going live; **Post-redesign** - Verify nothing broke during the overhaul; **Client handoff** - Structured proof that the site is ready; **Quarterly review** - Catch accumulated debt; **Single-pass focus** - Run just Pass 2 after a perf sprint
Use when rewriting AI-generated text to match a specific person's or brand's authentic voice. Use when AI output sounds generic, corporate, or detectable. Unlike generic "humanizers," this skill requires voice analysis input and produces voice-consistent output, not fake imperfections.
Model best-case, worst-case, and likely revenue scenarios with sensitivity analysis for strategic planning. Use when: building financial forecasts; presenting board scenarios; planning headcount around revenue uncertainty; modeling pricing changes impact; preparing investor updates with upside/downside ranges
Use when analyzing server logs to understand how AI crawlers (GPTBot, ClaudeBot, PerplexityBot) interact with your site. Use when optimizing content placement for LLM retrieval, diagnosing why AI search isn't citing your content, or auditing crawl patterns to find optimization gaps.
Use when optimizing for AI search visibility where individual experts and entities outperform generic brand pages. Use when building cross-platform authority for people, organizations, or products that AI models should recognize and cite.
Analyze paid advertising performance across channels and recommend budget reallocation to maximize ROAS and minimize CAC. Use when: planning quarterly ad budget allocation, diagnosing underperforming ad channels, deciding whether to scale spend on a channel, calculating marginal ROI across Google Ads, Meta, LinkedIn, or TikTok, rebalancing media mix after performance shifts, or setting up a test-and-scale framework for new channels.
| name | rlm |
| 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 |
| license | MIT |
| metadata | {"author":"ClawFu","version":"2.1.0","mcp-server":"@clawfu/mcp-skills"} |
"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.
Identify relevant files without loading them into context.
# Find candidate files
grep -rl "pattern" src/ --include="*.ts"
find . -name "*.py" -newer last_check
Split work into atomic units, spawn parallel agents.
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."
...
Collect all agent outputs, find patterns, compile into a coherent answer.
If incomplete, recurse: run a second RLM pass on the specific gaps.
Wrong (monolithic): Read each file sequentially → context fills up, reasoning degrades.
RLM Way:
grep -l "@Controller" src/**/*.ts → 20 filesReturn a structured summary:
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.