Skill rating

Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonom

Audit whether AI agents can actually use your product — docs, APIs, onboarding, errors, and discoverability, evaluated from a non-human user's perspective. Use when asked if a product is agent-ready,

Specify the tracing, metrics, and alerting for an AI agent or LLM feature in production. Use when asked what to log for an LLM app, design agent tracing or spans, define quality and cost monitors, or

Decode a home, renters, or auto insurance policy into what's actually covered, what's excluded, and what the payout math really looks like before you need it. Use when someone asks 'what does my insur

Simulate defending your planning application before the committee that decides it — the neighbour objections read into the record, the character-of-the-area catch-all, the parking pile-on, the council

Model the cost and latency of an LLM feature before it ships and surprises the bill. Use when asked to estimate LLM API costs, set a latency/token budget, decide which model tier to use, or bring down

Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use when asked to stop prompt changes breaking production, set up golden tests or C

Write a buyer's offer cover letter to a seller to strengthen a real-estate bid. Use when asked to write a real-estate offer letter, a buyer's 'love letter' to a seller, an offer cover note, or to make

Design a voice AI agent for phone or in-app conversations — call flows, interruption handling, escalation to humans, and the metrics that catch a bad voice experience. Use when asked to design a voice

Redesign seat-based pricing for the agent era — when one human runs ten agents, per-seat models collapse. Use when agents are eroding seat counts, when asked to migrate to usage- or outcome-based pric

Plan the migration of an LLM feature from one model to another without breaking production. Use when a model is being deprecated, a newer model looks better or cheaper, or when asked how to upgrade mo

Decompose work across parallel subagents properly — task slicing that avoids collisions, briefs that stand alone, and result integration that catches contradictions. Use when work can genuinely parall

Write a standout rental application / cover letter to a landlord or letting agent. Use when asked to write a rental application, a letter to a landlord, a renter cover letter, or to strengthen an appl

Design an MCP server for a product — the tool surface, auth model, and safety boundaries that make it genuinely usable by AI agents. Use when asked to spec an MCP server, expose a product to agents, d

Articulate founder-market fit — the why-you and why-now story investors and accelerators (YC-style) probe hardest. Use when asked to write the founder story, answer 'why are you the right team', draft

Design or optimize a paywall / upgrade screen to convert free users to paid without killing trust. Use when asked to improve a paywall, upgrade prompt, or free-to-paid conversion, or to decide what to

Write a compelling, accurate real-estate listing description. Use when asked to write a property listing, an MLS/Zillow description, a real-estate listing, or to make a property description more appea

Structure AI and ML product decisions with the rigour of any product decision. Use when building AI-powered features, evaluating LLM integrations, designing AI products, or assessing AI readiness. Pro

Plan and promote an open house that draws buyers and generates leads. Use when asked to plan an open house, market an open house, or create an open-house checklist. Produces a plan — timing and promot

Reconstruct the decision actually made in a messy Slack, email, or meeting thread into a proper decision record — commitments named, silent assumptions surfaced, non-decisions called out. Use when ask

Write in-product onboarding copy that gets users to value fast. Use when asked to write onboarding copy, a welcome flow, product tour/tooltips, setup steps, or activation messaging. Produces the copy

Turn a document the team keeps rewriting into a template that actually helps — extract the recurring skeleton, mark what varies with real placeholder prompts, keep it lighter than the ceremony it repl

Design a scoring rubric and LLM-as-judge prompt to evaluate the quality of an AI feature's output. Use when asked to create an eval rubric, define quality dimensions, build an LLM judge, or decide how

Design a referral program that drives real word-of-mouth growth. Use when asked to build a referral or refer-a-friend program, create an incentive/reward structure, or turn happy users into a growth c

Specify the safety and reliability guardrails for an LLM feature before it ships. Use when asked to define LLM guardrails, add safety controls to an AI feature, prevent prompt injection or jailbreaks,

Write an AI usage policy people can actually follow — approved tools, data rules, disclosure duties, and review obligations, in one page instead of legal fog. Use when asked for a company AI policy, a

Route a fuzzy request to the right skill in this library. Use when the user is unsure which skill fits, asks 'which skill should I use for X', describes a task without naming a skill, or when a reques

Execute a written plan with discipline — verify each step before advancing, surface deviations instead of improvising around them, and keep a visible execution log. Use when working through a plan (yo

Write a handoff summary so another agent or person (or a fresh session) can pick up the work with full context. Use when ending a work session, hitting a context limit, switching agents, or pausing a

Design an evaluation plan for an LLM or AI feature before shipping it. Use when asked how to evaluate a prompt/model/agent, set up an eval harness, define quality metrics for an AI feature, or build a

Write reusable support macros / canned responses that sound human, not robotic. Use when asked to write a support macro, a canned response, a saved reply, or a template for a common customer ticket. P

Run a real brainstorm — divergent generation without judgment, then convergent selection with explicit criteria — instead of listing ten obvious ideas and calling it creativity. Use when asked to brai

Write an executable work plan BEFORE starting a complex task — decomposed steps with verification points, risks pre-named, and explicit stop conditions — so execution becomes checking boxes instead of

Diagnose and rewrite an underperforming LLM prompt so it produces reliable, well-structured output. Use when asked to improve a prompt, fix a prompt that gives inconsistent or wrong results, reduce ha

Convert currencies and fetch live exchange rates with zero API keys — Frankfurter (ECB rates) primary, open.er-api.com fallback, via plain curl. Use when asked convert 500 dollars to euros, what's the

Coordinate multiple OpenClaw instances in a shared GitHub repository under a half-trust model with secrecy boundaries, approval gates, structured tasks, claims, handoffs, risks, and decision records.

FluxA Agent Wallet allows AI agents to securely use a user’s wallet, enabling the agent to perform payment-related actions within the approved scope. Capabilities include x402 payments, USDC transfers

Soul.Markets SDK for AI agent commerce. Upload your soul.md, create services, execute other agents' services, and earn USDC. The marketplace where differentiated intelligence trades. Use when monetizi

Review agentic software-development plans and release readiness for Codex, GitHub, and ClawHub work. Use when a user asks for scoped delivery planning, implementation review, public-surface checks, or

Auditory intelligence for AI agents. Transforms human audio into into structured data, semantic reports, and machine-readable markdown. Use when you need market intelligence, crypto alpha, speaker-att

QA and peer review agent. Reviews output from other agents before delivery. Use when: (1) content from Scribe needs review before posting, (2) research from Scout needs validation before acting on it,

Install and configure BEE — the Belief Extraction Engine for OpenClaw. Gives agents persistent structured memory across sessions. Auto-extracts beliefs at session end, scopes by agent namespace, and i

Audit and score OpenClaw AgentSkills against structural compliance, quality standards, and OpenClaw-specific architecture patterns. Produces a 0-100 score with A-F grade, dimensional breakdown, and ac

Reduce token usage in AI agent systems (Claude Code, OpenClaw, GPT Codex, Cursor, Windsurf, Aider, etc.) by applying context compression, selective loading, prompt deduplication, caching strategies, a

Background reasoning agent that autonomously explores open questions using a local LLM (Qwen3.5-9B), a private knowledge graph for dead-end tracking, and Perplexity web search. Fires on a schedule, pi

Trustless encrypted vault with TOTP auth and clean-room session isolation. Secrets your agent holds but cannot read. Use when user wants to store, retrieve, or manage encrypted secrets securely.

Pixel art desktop lobster that lip-syncs to OpenClaw TTS speech. Use when: (1) user wants a visual avatar for their AI agent, (2) user wants a desktop overlay that animates when their agent speaks, (3

Read and write WordPress.com site content through WordPress.com's hosted MCP server. Thin pass-through to WordPress.com's official MCP; the live tool catalog is whatever that server advertises. Use wh

Enable Microsoft Word's Track Changes (修订模式) on documents using native OOXML elements. Supports cross-run text matching and precise paragraph-level replacement. Use when agents need to modify Word doc

Reduce MCP token costs by up to 94% and enforce least-privilege tool access. Creates YAML policies that control which MCP tools each agent can see and call. Use when user mentions token costs, context