Skill rating

Shrink a task you're avoiding down to a first step so small it's almost impossible not to do — beating activation-energy paralysis. Use when asked I can't get started on, help me start this task, this

Strips AI writing patterns from text and rewrites it to sound genuinely human by removing statistical defaults and injecting the specific signals that human writers produce. Use when a draft reads as

Write a product demo script that tells a value story instead of a feature tour. Use when asked to write a sales demo script, structure a product demo, plan demo talk track and flow, or turn a feature

Convert a business question into a complete dashboard specification. Use when asked to design a dashboard, create a dashboard spec or brief, plan a BI report, or define what charts and metrics a dashb

Triage a raw bug report into something a team can act on — clean repro steps, a defensible severity/priority, environment, likely area/owner, and duplicate check. Use when asked to triage this bug, se

Turn a team or reporting structure into a clean org chart. Use when asked to draw an org chart, show reporting lines, visualize team structure, or map who reports to whom. Produces a ready-to-render M

Be a club or association treasurer without being an accountant — the two-column cashbook that's genuinely enough, monthly reconciliation in 20 minutes, the treasurer's report members actually understa

Appeal a denied disability benefit (SSDI/SSI, PIP, DLA, ESA and similar) — decode the denial reason, build the evidence-backed case that answers it, hit the deadline, and prepare for the hearing. Use

Give someone difficult feedback — a report, a peer, a friend — so it actually lands and helps, without crushing them or dodging the point. Use when asked how do I give hard feedback, tell someone some

Design a usage-based pricing scheme that scales revenue with value without scaring customers away — the metric that tracks value, tiers with included volume, and the guardrails that prevent bill shock

Find where the food money actually goes — a no-shame ledger built from real receipts/statements, the four leak categories (waste, convenience markup, brand autopilot, the takeaway blur), a per-leak fi

Take a board game idea from 'wouldn't it be cool if' to a playtestable prototype — core loop, tension source, components you can make tonight, balance starting-points, and a real playtest protocol wit

Set up and run a body-doubling session — using another person's presence (in the room, on a call, or a chat check-in) to start and stay on the task your ADHD brain keeps bouncing off. Use when someone

Build a credit history from zero in a new country — understand that credit doesn't transfer across borders, get the first products that report, avoid the newcomer traps, and reach a usable score in mo

Get siblings onto one team about aging parents before the crisis does it for them — a structured family meeting with an agenda that prevents old-roles regression, a fair-not-equal division of care wor

Write to an elected representative in a way that actually gets action — a specific ask, your local stake, why it's in their interest to respond, and the follow-up — instead of an angry email that gets

Climb ranked on purpose instead of on tilt — a VOD-review protocol (three deaths per game, one pattern per week), a tilt debrief that ends queue-rage sessions, and honest fundamentals-first improvemen

Check whether a specific venue — a restaurant, office, event space, Airbnb, clinic — will actually work for your access needs, before you commit, with the exact questions to ask and the red flags in t

Stress-test a proposed org change before announcing it — simulate who gains, who loses, who blocks, where friction erupts in the first 90 days, and run the memo leak test: how does this land when it l

Get your attention back with a 30-day protocol that assumes you'll break it — a screen-time ledger without moralizing, friction engineering (what to delete, grayscale, where the phone sleeps), planned

Strips AI writing patterns from text and rewrites it to sound genuinely human — removing the statistical defaults, then adding earned voice calibrated to genre (opinion pieces get a person's voice; do

Report a public hazard or code problem to the authority that can actually fix it — a pothole, broken streetlight, illegal dump, unsafe building, code violation, blocked drain — with the right departme

Write the band agreement before the money or the breakup arrives — who owns the songs, how money splits (writing vs performing distinguished), who owns the name, what happens when someone quits, and t

Run a tabletop drill of a voice-clone or deepfake fraud attempt — the 'CEO needs this wire today' call — against your actual approval process, before a real attacker does, then debrief the tells and f

Run a club, PTA, or association AGM that finishes on time and holds up later — the notice and agenda done right, a quorum plan, minutes that capture decisions not conversations, elections without awkw

Send your position to a meeting instead of your body — a one-page brief carrying your stances, fallbacks, red lines, tradables, and delegation limits, readable by the colleague (or agent) representing

Get through the brutal logistics after a death — who to notify, what accounts and services to close, in what order, and what genuinely can't wait vs what can wait months — with explicit permission to

Query Google Analytics 4 (GA4) data through the Google Analytics Data API for trends, countries, sources, pages, and conversion analysis. Use when a user wants GA/GA4 metrics inside OpenClaw, wants to

Query Fitbit health data including sleep, heart rate, activity, SpO2, and breathing rate. Use when user asks about their fitness, sleep quality, steps, or health metrics.

Detect systematic inference-level biases in an AI agent's reasoning via Cerebratech CogDx API ($0.10 per call, credits accepted). Use when an agent keeps making the same type of error across different

Fetch live ClawHub publisher metrics for a specific user, including published skills, author rank, total downloads, stars, current installs, all-time installs, comments, and top-skill breakdowns. Use

Operate Weibo via browser automation for composing posts, publishing content, replying to comments, checking mentions, and monitoring basic account metrics. Use when users ask to manage 微博运营、发布内容、互动回复

Review business contracts for risks, missing clauses, unfavorable terms, and compliance gaps. Use when analyzing NDAs, MSAs, SaaS agreements, vendor contracts, SOWs, or employment agreements. Generate

When the user wants to plan, design, or implement an A/B test or experiment. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate t

Track and report token usage and cost for conversations. Use when: (1) User asks about token consumption (e.g. "token用了多少", "花了多少钱", "how much did this cost", "usage stats"), (2) At the end of long/co

Automatic failure pattern recording and recall system. Prevents repeating the same mistakes by logging errors with context, root cause, and resolution. Use when: (1) a command/task fails and you want

Very helpful in deep-reading one selected research paper, journal article, arXiv paper, working paper, technical report, benchmark paper, dataset paper, replication study, or synthesis paper and produ

Gets current weather and short forecast (today/tomorrow) for the user's configured home location via Yandex Weather API. Trigger when user asks about weather, temperature, wind, conditions, or forecas

Manage SubsTracker subscriptions and configuration via CLI scripts. Handles login, subscription CRUD, config updates, notifications, and dashboard queries. Use this skill whenever the user mentions su

This skill should be used when the user requests comprehensive research, deep investigation, or detailed academic-style reports on any topic. Trigger phrases include "deep research", "comprehensive in

One-command OpenClaw security audit, scoring, and auto-remediation. Addresses CVE-2026-33579 and common misconfigurations. Scans for exposed API keys, weak file permissions, unauthenticated endpoints,

Track OpenClaw token usage and API costs from local session data. Prefer openclaw-cost-diff for current cost analysis and window-over-window comparison across models, agents, and channels. Use this sk

Set and track goals for a solopreneur business using OKRs (Objectives and Key Results) and related frameworks. Use when defining business goals, creating quarterly or annual targets, building KPIs, tr

Use when a task needs Alibaba Cloud Model Studio Qwen Deep Research models to plan multi-step investigation, run iterative web research, and produce structured reports with citations or evidence summa

Vault discovery, comparison, and analytics for Paradex vaults. Ranks vaults by risk-adjusted returns, analyzes operator track records, monitors TVL changes, and recommends vaults based on user risk pr

This skill should be used when the user wants to "track job applications", "add a job application", "update application status", "view my job pipeline", "get application analytics", "delete job applic

Generate a Salesforce report blueprint from real org metadata. Use this skill when someone asks to build a report in Salesforce, understand how to query their org's data, map objects to a reporting qu

Automatically visualize any data file (CSV/Excel/JSON) with one command. No coding required. Keywords: data visualization, chart generator, CSV plot, CSV visualization, Excel chart, JSON visualizatio

Review OpenRouter usage, analytics, and troubleshooting data via API. Use when the user asks for spend/usage monitoring, activity trends, per-key management reporting, or deep investigation of specifi

Comprehensive SQL statement checking for HetuEngine, supporting two check modes: 1. Syntax Check - Keyword validation, statement structure verification, clause completeness, HetuEngine syntax compatib