Skill rating

Use when identifying seminal papers in a research field, mapping research lineage and intellectual heritage, discovering related work through reference tracking, or finding potential collaborators thr

Help users with Validated demand: Tax preparers and taxpayers need practical help organizing income statements, receipts, deductions, estimated taxes, and handoff checklists before filing or sending r

Use when code review feedback arrives - from a human reviewer, a bot, or a review agent - before implementing any of it. Especially when the feedback is partly unclear, technically questionable, or co

大模型AI智能检测。交互式引导用户明确检测场景（如明厨亮灶、安全生产、消防安全、门店巡检、周界安防），从52个免底库算法清单中推荐适配算法（不含需底库的比对类算法），支持对本地图片/图片URL/摄像头设备抓图（配合 jf-open-pro-capture 技能）调用算法分析并输出结构化检测报告。Use when the user mentions 明厨亮灶、AI检测、算法调用、图片分析、摄像头智能

Generate, validate, compare, or explain HSB HOLOLINK_def.svh macros. Do not use for FPGA_top.sv wrappers or packetizer-only derivation. Generation runs bundled Python scripts locally through shell com

Dynamic DNS updater for self-hosted / homelab / edge devices. Detects the device's public IPv4 and IPv6 addresses via public APIs (ipify, ifconfig.me, icanhazip), compares them against the last-known

Deep Research Suite - One command to aggregate, analyze, and synthesize research from multiple sources. Search → Extract → Summarize → Report.

Detects common LLM coding agent artifacts across four categories (tests, dead code, abstraction, style) over the project or changed files — using parallel subagents when the agent supports them, other

Prepare, safety-review, version, commit, and publish local Codex skills through a GitHub-backed release flow and ClawHub CLI. Use when the user asks to host, publish, release, update, package, audit,

Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-heavy loops, many small launches, host fallback

Help users with Validated demand: Founders and builders need a repeatable way to turn rough product ideas into validated plans, prototypes, and user-facing positioning. This requirement is supported b

Exports sanitized metadata, parameters, reproducibility details, quality metrics, and optional review artifacts from Medical AI inference runs or evidence packs to MLflow. Use after inference, includi

Haven Star Chart v2 portal training — gate, validate, propose submissions with human consent. Skill scripts use allowlisted in-process imports only (no subprocess). P0, math resonance, graph checks, i

Turn interview notes into a structured candidate scorecard and hire recommendation. Use when asked to write an interview scorecard, a candidate evaluation, an interview debrief, or to summarize feedba

PIPL 运行时护栏 (pipl-guard) v1.0.0。 在 AI 应用的输入/输出链路中实时检测个人信息，按风险分级 执行脱敏或阻断，供 Agent 主动调用。区别于事后审计，这是事中防护。 Use when: 需要在 Agent 处理用户输入或返回结果前，实时拦截/脱敏 个人信息；防止敏感数据流入大模型或被输出泄露；为 AI 应用加装 符合《个人信息保护法》的运行时护栏。 核心能力：

Use when the user asks to "optimize entity presence", reconcile an entity identity, or update canonical Knowledge Graph facts; audits and maintains machine-facing identity, sameAs, schema, disambiguat

Audit a multi-card wallet for overlap, gaps, and total annual cost. Given a list of cards the user holds, identifies redundant benefits, uncovered spend categories, and net fee burden. Use when the us

When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mo

Audit locally installed skills against ClawHub: detect version drift, find new publish candidates, review security flags, and triage ownership conflicts. Use when: reviewing whether published skills n

Discover real user demand from public online sources and turn validated opportunities into reviewed, publishable Skill packages. Use when a team wants to scan recent market signals, score demand, remo

OpenClaw update check and upgrade assistant. Triggers on phrases like "check for updates", "any new version", "is openclaw updated", "run the update", "confirm update", "upgrade openclaw". Two modes:

Reviews Rust code for ownership, borrowing, lifetime, error handling, trait design, unsafe usage, and common mistakes. Use when reviewing .rs files, checking borrow checker issues, error handling patt

ClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup for additional security skills.

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "gen

When the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking. Also use when the user mentions "sitemap," "site map," "visual sitemap,

Analyzes article structure, identifies positions requiring visual aids, generates illustrations with Type × Style two-dimension approach. Use when user asks to "illustrate article", "add images", "gen

Research high-performing YouTube videos in a niche using TubeLab's outlier detection API. Identifies outlier videos, analyzes top 3 relevant videos with AI, and generates reports with actionable hook

Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. Generative Engine Optimization (GEO) analysis including brand mention signals

Use when diagnosing KWDB incidents from logs, metrics, or system evidence, especially crashes, OOM, slow SQL, restarts, and cluster-wide availability symptoms.

Your AI Founder Partner for building and scaling startups — diagnose your stage, run hypothesis experiments, make pricing decisions, design growth loops, and ship weekly execution reviews.

个人知识库（LLM Wiki）操作 skill。 当用户提到以下意图时触发： - Ingest：处理新内容、更新知识库、"处理IMA新内容"、"处理印象笔记"、"处理raw里的文件"、"帮我ingest" - Query：查 wiki、"wiki里有没有关于XX"、"从知识库里找XX" - Lint：整理wiki、"检查知识库"、"清理一下wiki" - Visualize：可视化知识图谱、"看看

People-operations assistant covering the full employee lifecycle — recruiting, onboarding, performance reviews, compensation analysis, org planning, policy lookup, and people reporting. Use for any HR

Use when the user wants a concise daily or weekly site/growth standup from TrustGrowth history when connected or from validated available evidence and repository artifacts otherwise.

Claw Deep Research — 自动迭代深度研究。Turn your AI agent into a real research assistant with multi-phase iterative search, contradiction mining, cross-verification, and structured reports. Zero extra API keys

Instantly analyze markdown articles, generate prompts, and seamlessly insert AI illustrations with zero configuration required. Supports Pollinations API (zero-config) with graceful fallback to Huggin

鲁班（Luban）——Skill打磨工坊。把一个"能用的Skill"打磨成"能被理解、能被安装、能被传播、能被验证、能持续进化"的公共Skill资产。 方法论是工匠式的五个动作：验料（先挑战这个Skill的前提是否成立，不值得雕的料直说）、访行（联网寻找同类Skill，看清自己在生态里站什么位置）、过尺（结构、实测、活体三把尺一起量——活体指拉真实运行产物对账，绿色的CI会撒谎）、慢刨（冻结原版做

Use when creating forest plots for meta-analyses, visualizing effect sizes across studies, or generating publication-ready meta-analysis figures. Produces high-quality forest plots with confidence int

Use when the user asks about AI visibility, GEO/AEO, AI Overview citations, LLM brand mentions, llms.txt, or AI crawler access. Assesses whether AI answer engines can reach, use, and cite a site. Open

Use when a user asks what Atlas Flight Booking can do, wants to authorize Atlas, search or compare flights using exact or flexible dates and time preferences, verify a current fare, choose baggage or

Use when the user asks to "map our positioning", "name our competitive alternatives", or "pick a beachhead segment for the launch"; produces a Dunford-style positioning canvas — named competitive alte

Analyze electricity, water, and gas bills to detect anomalies, compare usage, forecast costs, and suggest savings.