Skill rating

Orchestrate F1 test drives to validate the Cyrus agent system end-to-end across issue-tracker, EdgeWorker, and activity rendering.

Security code review for vulnerabilities. Use when asked to "security review", "find vulnerabilities", "check for security issues", "audit security", "OWASP review", or review code for injection, XSS,

Adversarial code review using cross-model approach. Spawns reviewers on the opposing model (Claude uses Codex, Codex uses Claude) to challenge work from distinct critical lenses. Produces a synthesize

Detects missing zeroization of sensitive data in source code and identifies zeroization removed by compiler optimizations, with assembly-level analysis, and control-flow verification. Use for auditing

Detect new or modified skills in .agents/skills/ by comparing git hashes against ai-skills, snapshot for rollback, review, publish to ai-skills, install locally, and cherry-pick lockfile to TARGET. Re

Review current uncommitted git changes with full file context and produce a structured report with severity levels, actionable fixes, and an approval verdict.

Run Playwright smoke tests, debug failures, and verify fixes

DaleStudy/skills 저장소의 스킬 생성, 수정, 검증 시 사용. 다음 상황에서 활성화: (1) 새 스킬 생성 요청 시, (2) skills/ 디렉토리 내 SKILL.md 파일 수정 시, (3) SKILL.md 변경 검토 또는 리뷰 시, (4) 스킬 frontmatter 또는 메타데이터 작업 시, (5) 'skill', 'SKILL.md', 'fr

Walk through a live web app AS a real user to find usability + behavioural bugs that static reviews miss. REQUIRES proof of interaction (typing, clicking, sending, observing) before any verdict — a sw

Agent skill for researcher - invoke with $agent-researcher

Validate pending migrations for foreign key consistency, rollback safety, and best practices

Analyze and create a testing strategy for native Android apps - install testing libraries, set up test infrastructure, create harnesses for unit tests, UI tests, screenshot tests, and end-to-end tests

Aggregate and display system metrics with anomaly detection for a time period

Detect and classify candlestick patterns from ingested OHLCV data

Analyze token usage patterns and recommend cost optimizations with estimated savings

Code review assistance with linting, style checking, and best practices

USDC is Circle's stablecoin deployed across multiple blockchain ecosystems including EVM chains (Ethereum, Base, Arbitrum, Polygon, Arc) and Solana. Use this skill to check balances, send transfers, a

UI test recipe -- composes browser-record (capture) + browser-replay (verify) so every test produces a replayable RVF artifact, not an ephemeral run

Query Google Search Console for SEO data - search queries, top pages, CTR opportunities, URL inspection, and sitemaps. Use when analyzing search performance, finding optimization opportunities, or che

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.

Message signing and verification — SIP-018 structured Clarity data signing (on-chain verifiable), Stacks plain-text message signing (SIWS-compatible), Bitcoin message signing (BIP-137 for legacy/wrapp

Review code changes against accepted ADRs for compliance violations

Copy-paste detector for 220+ languages. Detect duplicated code and measure duplication percentages.

Use when you want to validate changes before committing, or when you need to check all React contribution requirements.

WorldLines scenario creation and revision with clear multi-agent dialogue, validation, and real-model playtesting.

Reference tool for devtools — covers intro, quickstart, patterns and more. Quick lookup for Perf Analyzer concepts, best practices, and implementation patterns.

Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, conte

Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as close

EU AI Act Compliance for Autonomous Agents. Complete compliance toolkit for AI agent commerce: EU AI Act risk classification, Annex IV technical documentation, cryptographic audit trails (Article 12),

Teach your AI agent to think about security. A reasoning methodology for vetting skills before installation — red/green flag heuristics, 4-phase audit protocol, post-install verification. No scripts,

CORS (Cross-Origin Resource Sharing) misconfiguration auditor. Probes any API endpoint with crafted Origin headers to detect the most dangerous CORS vulnerabilities — reflecting arbitrary Origins (any

Xiaohongshu content operations expert for myopia prevention brands. Full-chain support: topic planning, copywriting (with 90-score upgrade), data review, competitor analysis, and business conversion.

AI-powered options strategy master for China market — covers options pricing, Greeks calculation, strategy analysis (covered call, protective put, spreads, straddles), and volatility trading. Built fo

Zero-Trust Agent Verification: Cryptographic Reputation Systems. Complete buyer-side guide to verifying AI agent identity, auditing performance claims, and building trust scores with cryptographic ver

Review contracts and legal agreements (PDF, Word, images) for risks, unfair clauses, missing provisions, and key obligations using SoMark for accurate document parsing. Provides structured risk analys

Generate a professional PDF report from a GEO audit using pandoc + Chrome headless. Converts GEO-AUDIT-REPORT.md into a styled, client-ready PDF with a cover page, color-coded score tables, severity-t

使用极鲸云按明确 Ozon 商品 ID 查询和分析当前支持站点的真实评论，包括评分、正文、优缺点、规格、媒体、有用数、卖家回复和评论时间。用户需要研究 Ozon 商品卖点、差评原因、消费者痛点、规格风险、口碑变化或产品改良方向时使用。必须先有明确 goodsId，只依据实际返回评论形成结论。

AI 身份核验与溯源工具（三锚一票方法论）：对任意 AI 智能体/对话/Agent 执行身份核验——账号锚（Account Anchor 登录身份/可验证凭证）、行为锚（Behavior Anchor 行为模式一致性）、记忆锚（Memory Anchor 长期记忆一致性）三维交叉核验，最终一票给出可信度结论（Level 1-4）。对标国际标准：W3C DID v1.1 / Verifiable C

Camera snapshot and monitoring skill for OpenClaw — capture, compare, and manage camera snapshots with automated detection and alerts

A comprehensive test skill for ClawHub publish validation with detailed documentation and practical examples

Secondly: A simple test skill for verifying clawhub.ai upload functionality

Use this skill whenever the user needs to operate or diagnose a Ceph cluster via its ceph-mgr Dashboard REST API — decode a HEALTH_WARN/ERR state into cause + action (cluster_health), read the cluster

Install and manage Expert Library Plus - the world's first AI expert library with name-based quality anchors. Enhances 43+ professional experts with historical figures like Steve Jobs, John Resig, a

Guide someone through optimizing anything using iterative self-improvement loops, OR run autonomous optimization loops with binary eval scoring. Systematically improve prompts, skills, websites, email

Expert AI agent specializing in accessibility auditor. From The Agency (github.com/msitarzewski/agency-agents).

Lockfile security and integrity auditor for JavaScript, Python, Go, and Rust projects. Detects phantom dependencies (packages in lockfile but not in manifest), lockfile drift (manifest changed without

Analyze financial reports and research notes (PDF, Word, images) to extract key financial metrics, profitability trends, risk signals, and management commentary. Uses SoMark to accurately parse comple

多智能体协作（整合与进阶·元能力）。给定一项任务/一个待决问题，自动完成： 角色分工(提议者/批判者/事实核查/综合裁决) → 任务派发 → 多视角作答 → 交叉验证(reason-verify) → 投票聚合/辩论择优 → 输出带置信度的共识结论。 对标一线大模型智能体的「多 agent 辩论/自一致性」能力，且把每个 agent 的产出 都过一遍可靠自验证、按可靠度加权投票。当复杂决策需要多视

Accessibility Tester for AI Native Full-Stack Software Factory Layer 11 - specializes in WCAG 2.1 compliance testing, screen reader compatibility, keyboard navigation, color contrast, and ARIA validat