Loading...
Loading...
Found 1,176 Skills
Controls a cloud browser from a sandboxed remote machine. Use when the agent is running in a sandbox (no GUI) and needs to navigate websites, interact with web pages, fill forms, take screenshots, or expose local dev servers via tunnels.
Run knip to find and remove unused files, dependencies, and exports. Use for cleaning up dead code and unused dependencies.
This skill should be used to generate realistic, persona-consistent synthetic coaching and therapy session transcripts for evals, demos, and training data. It produces fictional but believable coach/client (or therapist/client) dialogue grounded in a chosen modality (ICF/GROW coaching, CBT, IFS parts work, ACT/motivational interviewing) and exports to Fathom/Granola transcript style, plain dialogue, structured JSON, or Obsidian markdown. Triggers on requests like "generate a synthetic coaching session", "make fake therapy transcripts for evals", "create demo session transcripts", "synthetic CBT dialogue", "persona-consistent coaching transcript", "test data for my session summarizer", or "mock coaching call".
Design and maintain TypeScript packages in a monorepo, including exports and build configuration.
Capture Unreal Engine traces, inspect Trace Store files, keep Unreal Insights GUI open, and export/summarize timing/counter data.
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
This skill should be used when the user wants to write, review, or refactor TypeScript code to follow industry best practices. Common triggers include "follow ts best practices", "review this typescript", "fix the typescript style", "make this idiomatic typescript", "apply typescript conventions", and "audit this ts file". Bakes in branded types, discriminated unions, ts-pattern for multi-branch logic, JSDoc on exports, kebab-case file naming, and *Params/*Options object-arg conventions. Skip when the user wants pure functional refactors (use ts-best-practices-functional) or is writing framework components (React/Vue/Svelte have different conventions).
Production-grade fault tolerance for distributed systems. Use when implementing circuit breakers, retry with exponential backoff, bulkhead isolation patterns, or building resilience into LLM API integrations.
Comprehensive analysis of Xiaohongshu notes in terms of content quality, keyword optimization, title attractiveness, sensitive content risks, commercialization level, interaction potential, etc. Suitable for pre-publication review, content optimization suggestions, and improving note exposure. Trigger words include "analyze Xiaohongshu notes", "Xiaohongshu content review", "note optimization", "XHS analysis", or upload Xiaohongshu note content to request analysis.
Identifying sensitive data exposure vulnerabilities including API key leakage, PII in responses, insecure storage, and unprotected data transmission during security assessments.
AI-powered codebase security scanner that reasons about code like a security researcher — tracing data flows, understanding component interactions, and catching vulnerabilities that pattern-matching tools miss. Use this skill when asked to scan code for security vulnerabilities, find bugs, check for SQL injection, XSS, command injection, exposed API keys, hardcoded secrets, insecure dependencies, access control issues, or any request like "is my code secure?", "review for security issues", "audit this codebase", or "check for vulnerabilities". Covers injection flaws, authentication and access control bugs, secrets exposure, weak cryptography, insecure dependencies, and business logic issues across JavaScript, TypeScript, Python, Java, PHP, Go, Ruby, and Rust.
Execute mcloud variables commands to list and get environment variables for a Cloud environment. Use when inspecting, reading, or exporting environment variables. Never pass --reveal unless the user explicitly requests secret values.