Skill rating

Agent skill for performance-analyzer - invoke with $agent-performance-analyzer

Review recent conversations to find improvements for CLAUDE.md files.

Boîte à outils complète pour la création, l'édition et l'analyse de documents avec support du suivi de modifications, commentaires, préservation du formatage et extraction de texte. Quand Claude doit

Best practices for Zod schema validation and type inference in TypeScript applications.

Launch a meta-judge then a judge sub-agent to evaluate results produced in the current conversation

Deep research and analysis tool. Generates comprehensive HTML reports on any topic, domain, paper, or technology. Enhanced with advanced browser automation — SPA handling, network idle wait, batch ope

Diagnostic audit across all seven layers — identifies the bottleneck layer and recommends where to focus

Design and operate data quality programs for financial data — validation rules, pricing validation, data lineage, exception management, profiling, and governance. Use when building validation rules fo

AI creative director with recursive self-assessment: 20+ methodologies (SIT, TRIZ, Bisociation, SCAMPER, Synectics), 3-axis evaluation calibrated against Cannes/D&AD/HumanKind, 5-phase process from br

Create and checkout a new git branch with smart validation and GitHub issue integration

Staff-level codebase health review. Finds monolithic modules, silent failures, type safety gaps, test coverage holes, and LLM-friendliness issues.

Conduct qualitative user research, synthesize insights, and inform product decisions through interviews, usability testing, and behavioral analysis

论文分析师 (Paper Analyst) — 负责精读论文、提取方法细节、构建对比表。 当被研究主管或文献侦查员指派分析论文时激活。对 Top 20 核心论文进行结构化分析， 生成论文分析卡片和跨论文对比表。

Iterative Five Whys root cause analysis drilling from symptoms to fundamentals

Recognize breakthrough moments, blocking resolutions, and design decisions worth preserving. Detect high-value insights that save future time. Suggest distillation at valuable moments, not routine wor

Agent skill for pagerank-analyzer - invoke with $agent-pagerank-analyzer

Codex/OpenClaw skill audit: live budget, usage, duplicates, compact descriptions.

PRの変更内容をトリアージし、変更カテゴリ分類・表層チェック・必要リファレンス判定を行います。結果を`.pr-triage.json`に出力し、後続のコードレビューフェーズで活用します。CI環境でのコスト最適化に使用してください。

Analyze cost reduction initiatives and operational efficiency measures from earnings transcripts, including headcount actions, facility consolidation, and productivity improvements.

Analyzes events through narrative lens using story structure, character arc analysis, dramatic tension, thematic development, and narrative theory (three-act structure, hero's journey, conflict-resolu

Evidence-driven tracing lane that orchestrates competing tracer hypotheses in Claude built-in team mode

Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.

Restore function symbols by analyzing code patterns, strings, constants, and cross-references

Agent skill for scout-explorer - invoke with $agent-scout-explorer

Agent skill for code-analyzer - invoke with $agent-code-analyzer

Analyze the broker-dealer standard of conduct under SEC Regulation Best Interest's four obligations: Disclosure, Care, Conflict of Interest, and Compliance. Owns what triggers a 'recommendation' under

Run comprehensive worker system benchmarks and performance analysis

Auto-assembles review panel using deterministic rules, dispatches agents against plan file, collects verdicts.

Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.

Search and analyze your own session logs (older/parent conversations) using jq.

Validate a Claude Code plugin structure, frontmatter, and MCP tool references

Audit/harden OpenClaw hosts: SSH, firewall, updates, exposure, backups, disk encryption, gateway security.

Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly

Agent skill for reviewer - invoke with $agent-reviewer

Review RTK Rust code for idiomatic simplification. Detects over-engineering, unnecessary allocations, verbose patterns. Applies Rust idioms without changing behavior.

Get cryptocurrency market data. Get Binance AI analysis report. Get blockchain news updates.

Analyze git diffs for risk scoring, reviewer recommendations, and change classification

Review and improve documentation with parallel evaluation and iterative improvement loop.

Detect and flag personally identifiable information (PII) in text, code, and configurations

Ask the user for a code review through difit after code changes.

Control Adobe desktop apps - Photoshop, Illustrator, Premiere, After Effects, InDesign, Audition - from the shell via Flue, without an MCP server.

Full project audit — launches 5 parallel AI agents (security, bugs, dead code, architecture, performance) to scan your codebase read-only, then compiles a unified report with health grade (A+ to F) an

Issue and verify on-chain certificates on Base L2. Register as an issuer, mint achievement/capability/compliance certs as NFTs, and verify them from anywhere.

DEM Terrain Analysis - Generate slope, aspect, hillshade, contour, curvature, description: 'DEM Terrain Analysis - Generate slope, aspect, hillshade, contour, curvature, flow direction, accumulation f

AI-powered bond analysis expert for China market — covers bond valuation, yield analysis, duration/convexity calculation, credit spread analysis, and bond portfolio management. Built for fixed income

PostGrid Verify (postgrid.com). Use this skill for ANY PostGrid Verify request — searching and reading data. Whenever a task involves PostGrid Verify, use this skill instead of calling the API directl

全球市场实时仪表盘 - A股/港股/美股/日韩指数、贵金属、外汇、自选股管理、个股详情分析、交易税费计算。内置多源聚合引擎（新浪/腾讯/东方财富），自动交叉验证数据可靠性。支持用户自定义数据接口扩展。Global market real-time dashboard with multi-source data aggregation, cross-validation, and HTML das

Turn every Claude Code session into a beautiful Obsidian note — automatically. Generates dual output: structured Markdown reports + interactive Canvas visual maps. Zero config, auto-detects projects.

Execution-based verification guardrail with 14 check items for AI agent output

Generate logos with AI image tools using effective prompt structures, validation loops, and export workflows for App Store icons and brand marks.