Skill rating

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Deploy a Worker live, no account, via wrangler --temporary.

Record a site's XHR into a HAR, derive an HTTP client.

AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.

W&B: log ML experiments, sweeps, model registry, dashboards.

Turn an unanswerable decision into a questionnaire doc.

Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

1-3-1 decision briefs: problem, three options, one pick.

TRL: SFT, DPO, GRPO, RLOO reward modeling for LLM RLHF.

Adversarial plan interview before implementation.

Fast BPE/WordPiece tokenization and custom vocab training.

Weekly reset: commitments, stalled work, next-week plan.

llama.cpp local GGUF inference + HF Hub model discovery.

Watch product, flight, or listing prices; alert on target.

Agent payments via Stripe Link — cards, SPT, approvals.

Clean training loops with built-in distributed support.

Watch named companies for material news; cited digests.

Hyperliquid market data, account history, trade review.

Use live BCI cognitive and mood state from NeuroSkill.

Speed up long-sequence transformer training and inference.

Passive recon of subdomains, SSL certs, WHOIS, and DNS.

Curate LLM training data: dedupe, filter, PII redaction.

Scrape sites with stealth browsing and Cloudflare bypass.

OBLITERATUS: abliterate LLM refusals (diff-in-means).

Find accounts for a username across 400+ platforms.

Run PyTorch training across GPUs with minimal changes.

Pretrain LLMs at scale with PyTorch 4D parallelism.

Triage an inbox: prioritize threads, draft replies safely.

Stock quotes, history, search, compare, crypto via Yahoo.

Train sparse autoencoders to interpret model features.

Apple Reminders via remindctl: add, list, complete.

YouTube transcripts to summaries, threads, blogs.

Serverless GPU cloud for ML jobs and model APIs.

Reference-free preference alignment, simpler than DPO.

Fine-tune large LLMs with LoRA on limited GPU memory.

Review Kanban handoffs and route verified outcomes.

Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.

Read RSS, Atom, JSON feeds; discover feeds behind a page.

Build explorable isometric architecture atlases as HTML.

Generate one- or two-ink editorial print poster images.

Deploy applications and manage projects with complete CLI reference. Commands for deployments, projects, domains, environment variables, and live documentation access.

Systematic code review patterns covering security, performance, maintainability, correctness, and testing — with severity levels, structured feedback guidance, review process, and anti-patterns to avo

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, anal

Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a G

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This wor

Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.

Perform a comprehensive read-only security audit of Clawdbot's own configuration. This is a knowledge-based skill that teaches Clawdbot to identify hardening opportunities across the system. Use when

Manage, optimize, and troubleshoot the OpenClaw memory system — MEMORY.md curation, daily logs (memory/YYYY-MM-DD.md), memory_search tuning, compaction survival, and vector/hybrid search configuration

Build high-performing OpenClaw agents end-to-end. Use when you want to design a new agent (persona + operating rules) and generate the required OpenClaw workspace files (SOUL.md, IDENTITY.md, AGENTS.m

Python coding guidelines and best practices. Use when writing, reviewing, or refactoring Python code. Enforces PEP 8 style, syntax validation via py_compile, unit test execution, modern Python version