Loading...
Loading...
Found 1,685 Skills
Full Caido SDK integration for Claude Code. Search HTTP history, replay/edit requests, manage scopes/filters/environments, create findings, export curl commands, and control intercept - all via the official @caido/sdk-client. PAT auth recommended.
When the user wants to optimize for AI search visibility (ChatGPT, Claude, Perplexity). Also use when the user mentions "GEO," "AEO," "generative engine optimization," "AI search visibility," "LLM optimization," "GitHub GEO," "Grokipedia," "optimize for ChatGPT," "AI Overviews," "Bing Copilot," "Yandex AI," "Perplexity optimization," "GEO strategy," or "AI search optimization." For parasite SEO strategy, use parasite-seo. For GitHub, use github-seo.
Install Claudian Obsidian plugin which embeds Claude Code as an AI collaborator in your vault. Use when the user wants to install Claudian plugin to their Obsidian vault, or mentions "Claudian", "Claude Code in Obsidian", or "install Claudian plugin".
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
Generate AGENTS.md and CLAUDE.md files for a repository. AGENTS.md provides cross-tool agent instructions (supported by Claude Code, Cursor, Windsurf, Zed, Codex, and others). CLAUDE.md adds Claude-specific configuration and references AGENTS.md via @import. Use when a repo needs agent onboarding or when starting a new project.
Configure des hooks Claude Code pour bloquer les commandes git dangereuses (push, force-push, reset --hard, clean, branch -D, checkout/restore) avant leur exécution. Empêche les opérations git destructrices au niveau de l'agent.
Create and launch benchmark test projects to exercise vercel-plugin skill injection across realistic scenarios. Sets up isolated directories, installs the plugin, and spawns WezTerm panes running Claude Code with crafted prompts.
Use Claude Code's full tool system with any OpenAI-compatible LLM — GPT-4o, DeepSeek, Gemini, Ollama, and 200+ models via environment variable configuration.
Run live eval sessions against the vercel-plugin to verify hook behavior, skill injection, dedup correctness, and coverage. Launches real Claude Code sessions via WezTerm, monitors debug logs, and produces a structured coverage report.
Set up and improve harness engineering (AGENTS.md, docs/, lint rules, eval systems, project-level prompt engineering) for AI-agent-friendly codebases. Triggers on: new/empty project setup for AI agents, AGENTS.md or CLAUDE.md creation, harness engineering questions, making agents work better on a codebase. ALSO triggers when users are frustrated or complaining about agent quality — e.g. 'the agent keeps ignoring conventions', 'it never follows instructions', 'why does it keep doing X', 'the agent is broken' — because poor agent output almost always signals harness gaps, not model problems. Covers: context engineering, architectural constraints, multi-agent coordination, evaluation, long-running agent harness, and diagnosis of agent quality issues.
Use when preparing or verifying a host for Moshi remote coding. Trigger this for SSH or preferably Mosh readiness, non-interactive shell PATH issues, tmux defaults, creating a tmux project session rooted at a chosen directory, installing Moshi agent hooks for Claude Code or Codex CLI, or offering the optional `moshi DIR` shell helper.
Run browser encrypted JS in Node.js (environment patching). env_core.js provides function disguise/prototype chain/Proxy engine, Claude writes stubs on demand in run.js according to the diagnosis report. TRIGGER when: user says "environment patching", "module extraction", "run in Node", "webpack module extraction", "environment simulation", "run JS in Node", or needs to run independently without browser after finding the encryption entry. DO NOT TRIGGER when: only debugging in browser, doing AST deobfuscation, or writing ordinary Node.js code.