Research and Audits
Research and audit skills help with investigation, competitive analysis, due diligence, and structured reviews of a product, market, or codebase. Use this category when the job is to understand something deeply, compare options, or surface risks before acting.
861 skills
Skills in this category
verification-loop
Comprehensive verification system running build, type, lint, test, and security checks across Claude Code sessions.
weather
Current weather and multi-day forecasts for any global location, no API key required.
write-xiaohongshu
Research top Xiaohongshu posts, analyze patterns and emotional resonance, enrich with background research, then write and publish a note.
writing-clearly-and-concisely
Strunk's timeless rules for clearer, stronger prose in documentation, commit messages, and UI text.
agentic-engineering
AI-driven engineering workflows with eval-first execution, task decomposition, and cost-aware model routing.
alert-manager
Proactive monitoring and alert system for SEO and GEO metrics with threshold-based notifications.
apify-brand-reputation-monitoring
Monitor brand reputation across Google Maps, Booking.com, TripAdvisor, Facebook, Instagram, YouTube, and TikTok.
asc-cli-usage
App Store Connect CLI reference for command discovery, flags, output formats, and authentication.
baoyu-image-cards
Break down complex content into eye-catching image card series with multiple style options.
build-dashboard
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md .
claude-automation-recommender
Analyze codebases and recommend tailored Claude Code automations across all extensibility options.
claude-devfleet
Use this skill when you need to dispatch multiple Claude Code agents to work on coding tasks in parallel. Each agent runs in an isolated git worktree with full tooling.
clickhouse-best-practices
28 ClickHouse best practices rules organized by schema design, query optimization, and data ingestion strategy.
colosseum-copilot
Colosseum Copilot is a research API for startup opportunity discovery in crypto and Solana, with support for suggesting new archive sources.
content-hash-cache-pattern
Cache expensive file processing results using SHA-256 content hashes instead of file paths.
context-budget
Analyze token overhead across every loaded component in a Claude Code session and surface actionable optimizations to reclaim context space.
continuous-agent-loop
Decision framework for autonomous agent loops with quality gates, evals, and recovery patterns.
cpp-pro
Modern C++20/23 specialist for writing, optimizing, and debugging high-performance systems code.
create-agent
Bootstrap a modular AI agent with OpenRouter SDK, extensible hooks, and optional terminal UI.
dependabot
Source details, install context, and public review data are available on the full page.
differential-review
Security-focused differential analysis of code changes with adaptive depth, blast radius calculation, and markdown reporting.
dmux-workflows
Orchestrate parallel AI agent sessions using dmux, a tmux pane manager for agent harnesses.
doublecheck
Run a three-layer verification pipeline on AI-generated output. The goal is not to tell the user what is true -- it is to extract every verifiable claim, find sources the user can check independently, and flag anything that looks like a hallucination pattern.
elite-longterm-memory
Six-layer memory architecture combining WAL protocol, vector search, git-based knowledge graphs, and cloud backup.