Skill rating

Evaluate SOC 2 report quality using the SOC 2 Quality Guild rubric (Structure, Substance, Source). Use when reviewing a vendor SOC 2 Type 1/Type 2 report, triaging report credibility, producing a risk

Run A/B evaluation tests for any OpenClaw skill, script, hook, or cron job. Make sure to use this skill whenever the user mentions testing, benchmarking, comparing, or evaluating a skill, script, hook

Turn a trend, news item, creator signal, review pattern, or market observation into sharper ecommerce content angles that are timely, useful, and commercially relevant. Use when teams want better hook

Perform 12-Factor App compliance analysis on any codebase. Use when evaluating application architecture, auditing SaaS applications, or reviewing cloud-native applications against the original 12-Fact

File-based todo and task tracking in the todos/ directory. Use when creating, triaging, listing, or managing todo files, tracking work items, managing the backlog, converting PR comments to tracked ta

AI-writing fingerprint diagnosis for Chinese text. Use when Codex needs to inspect a draft for overly smooth, formulaic, generic, or authorless writing patterns; quote the exact passages that feel mac

Use when reviewing product, strategy, hiring, execution, operations, prioritization, org design, manufacturing/process, or messaging decisions through an Elon Musk-inspired first-principles lens groun

When the user wants to research keywords, find target keywords, or analyze search intent. Also use when the user mentions "keyword research," "keyword tool," "target keywords," "search volume," "searc

Analyze digital transformation solutions for a given industry from major vendors (Huawei, Alibaba, Baidu, Tencent) + vertical industry digital solution providers. Find specific products/solutions or d

Help patients find suitable doctors based on symptoms, specialty, location, and doctor ratings. Use when the user wants to find a doctor, get medical recommendations, or seek healthcare provider infor

Use when auditing Go code involving logging, error handling, HTTP response data, Kubernetes Secret management, or credential storage. Covers CWE-200/532/522/312/552. Keywords: information disclosure,

Diagnose and recover OpenClaw browser tool timeouts (browser.status/tabs/snapshot) involving gateway ports 18789/18791 and Chrome CDP 9222 conflicts. Use when browser tool says timed out/restart gatew

Distill decision contexts, options, trade-offs, and outcomes into structured decision records. Use when the user is facing a choice, has made a decision they want to document, or needs to analyze past

Lightweight memory consolidation for OpenClaw agents. Reviews recent daily memory files (`memory/*.md`), extracts durable knowledge, and merges it into `MEMORY.md` without imposing a new file architec

Use when a data engineer needs a structured design review of a proposed data pipeline, ETL/ELT flow, or dbt/SQL model before it ships. Produces severity-rated findings across correctness, idempotency,

Use when reviewing one or more Chinese-language resumes against a JD, batch-ranking candidates, identifying red flags and follow-up interview questions, or re-screening a prior candidate batch. Trigge

When the user wants to create, optimize, or audit e-commerce category pages or listing pages. Also use when the user mentions "category page," "product category," "faceted navigation," "filter URLs,"

Calculate economic value added and shareholder return. Use for investment analysis, valuation, and capital allocation decisions.

Decompose Return on Net Assets into component ratios. Use for asset efficiency analysis, capital structure review, and business model comparison.

Scan any website for third-party scripts, trackers, and security risks. Detects PCI DSS compliance issues, missing CSP headers, fingerprinting scripts, and privacy risks. Use when asked to scan a site

Audit tool and command results before acting on them. Use when an agent has already run a command or tool, especially in multi-step workflows where a failed, partial, or suspicious result could be acc

Review a secondhand furniture listing before pickup with seller questions, photo requests, measurement checks, transport planning, hygiene and pest warnings, recall reminders, and safer meetup guidanc

Huawei Cloud MRS Hive SQL specification checking skill. Checks SQL statements against defined syntax and specification rules using the automated checker engine. No extra manual analysis beyond defined

Use when writing a Chinese-language interview evaluation from interview audio transcripts, video recordings, or interviewer notes. Triggers include 把这段面试录音转写写成面评、根据这份面试转写帮我写面试评价、给候选人写录用建议、判断候选人是否进入下一轮

When the user wants to create, optimize, or audit FAQ page content. Also use when the user mentions "FAQ page," "frequently asked questions," "help page," "Q&A page," "FAQ schema," "FAQ section," "com

Surgical quick fix — max 5 tool calls, zero exploration, read-diagnose-fix-verify. Use for small bugs, typos, simple changes that don't need deep analysis.

Define, apply, or review a reusable metadata-based filename standard for files, folders, inventories, archives, and generated catalogs. Use when the user wants to extract a naming convention into a st

Pull the people who liked or commented on any LinkedIn post and segment them by ICP fit (peer / aspirational / prospect / other). Produces an engager roster, tier breakdown, and outbound action lists

Evaluate a specifically provided RAG question, answer, and retrieved contexts with Ragas metrics. Use when the user explicitly requests RAG evaluation or hallucination analysis and has chosen a local

Binance Alpha new coin launch detector. Uses WebSocket to monitor !miniTicker@arr stream and detects new trading pairs immediately when they appear. Maintains known symbols set in memory and triggers

Quick macOS display snapshot. Captures what's currently on screen without opening a browser. Saves to /tmp or a custom path. Supports multiple displays and periodic watch mode. USE WHEN: Agent needs

Use when analyzing folders/tranches of declassified UAP/UFO/FOIA PDFs such as war.gov/UFO PURSUE, FBI Vault, NARA boxes, or AARO releases. Runs inventory, text extraction, entity/redaction analytics,

Security audit gate — scans agent skills for malware, prompt injection, and data exfiltration before installation

Apply AI-assisted coding best practices when helping with programming tasks. Use when (1) the user asks for help writing, refactoring, debugging, or architecting code, (2) the user request is too vagu

When the user wants to create, optimize, or audit a product listing or category page. Also use when the user mentions "product page," "product listing," "shop," "e-commerce products," "product catalog

When the user wants to design, optimize, or audit hero sections (above-the-fold main visual area). Also use when the user mentions "hero," "hero section," "hero area," "above the fold," "above the fol

TCPA consent verification for lead generation. Use when adding consent capture to web forms, verifying lead consent before contact, claiming/managing consent sessions, pulling proof for disputed leads

Use this skill when a supply chain analyst, procurement manager, or sourcing team needs to assess a supplier's risk profile. Produces a scored five-dimension risk scorecard, a Low/Medium/High/Critical

Prepare and publish a git release tag by inspecting the repo's release convention, bumping affected package versions, validating release builds, committing the release prep, pushing the branch, and pu

Activate when: user says 'let's check what could go wrong before we commit', 'I want to stress-test this plan', 'we're about to launch and I'm worried we're missing something', 'premortem', or is abou

Use this skill when a clinician or medical scribe needs to convert raw encounter notes, dictation, or bullet points into a structured SOAP note. Produces a Subjective/Objective/Assessment/Plan draft w

When the user wants to create, optimize, or audit pricing page content and structure. Also use when the user mentions "pricing page," "pricing table," "plans," "subscription," "pricing plans," "pricin

Avoid common mistakes and debug issues in PydanticAI agents. Use when encountering errors, unexpected behavior, or when reviewing agent implementations.

Audit GitHub Actions workflows that use self-hosted runners for untrusted trigger and credential-hardening risks.

Create a safe visible-diagnostic map for home Wi-Fi problems using device symptoms, router lights, placement notes, outage checks, speed tests, and support-ready evidence.

Audit an agent skill with Semia inside OpenClaw. Use when the user asks to run `semia scan <path>`, "Run Semia audit on this skill", or audit a skill/plugin for behavior risk.

Optimize Vercel build and deploy speed — audit checklist for new and existing projects.

Test and debug CORS (Cross-Origin Resource Sharing) configurations on live URLs. Use when checking if a server returns correct CORS headers, debugging CORS errors, testing preflight OPTIONS requests,

Manage GitHub stars with AI-powered categorization and cleanup. Use when a user wants to organize their starred repos into GitHub Lists, clean up stale/deprecated stars, export star data for analysis,

SaaS metrics calculator and dashboard builder for subscription businesses. Compute MRR, ARR, churn rate, NRR/GRR, LTV, CAC, CAC payback period, magic number, Rule of 40, quick ratio, and cohort retent