Loading...
Loading...
Found 1,683 Skills
Structured research summarization agent skill for non-dev users. Handles academic papers, web articles, reports, and documentation. Extracts key findings, generates comparative analyses, and produces properly formatted citations. Use when: user wants to summarize a research paper, compare multiple sources, extract citations from documents, or create structured research briefs. Plugin for Claude Code, Codex, Gemini CLI, and OpenClaw.
Get web data now — fast, incremental, immediately responsive to what the user needs. The only way Claude can access live websites. USE FOR: - Fetching any URL or reading any webpage - Scraping prices, listings, reviews, jobs, stats, docs from any site - Discovering URLs on a site before bulk extraction - Calling public REST/XHR API endpoints - Web search and research (8 focus modes) - Bulk crawling website sections Must be pre-installed and authenticated. Run `nimble --version` to verify. For building reusable extraction workflows to run at scale over time, use nimble-agent-builder instead.
A cross-cutting cognitive mode for sitting with design problems before rushing to solve them. Part of the Intent design strategy system. Activates expansive brainstorming: hyperassociativity, beginner's mind, cross-domain pattern recognition, and suppression of premature idea-dismissal. Works alongside every Intent skill — strategize uses it to reframe briefs, blueprint to question structural assumptions, journey to rethink interaction models, and specify to stress-test specs. Trigger when the user invokes "expansive mode", "philosopher mode", "sit with this", "brainstorm", "explore this problem", or says things like "go weird with it", "don't filter yourself", "what connections are you not making", "think about this differently", or "I'm stuck". This is a reasoning protocol, not a persona — Claude's voice stays grounded but the cognitive process changes significantly.
Browse and compare wiki knowledge by which AI tool originally produced it. Use this skill when the user says "/memory-bridge", "browse codex memory", "what did codex know about X", "show me claude knowledge", "cross-tool memory", "what does hermes know that claude doesn't", "show me knowledge from <tool>", "compare my AI tool memories", or wants to explore knowledge gaps between tools. Works from any project. Diff mode ("what's different", "unique to codex", "gaps between tools") is the killer feature — it surfaces blind spots between tools that the user may not know exist.
Write user-facing documentation for a new or changed feature, in the project's docs site. Use when user says 'document this feature', 'write user docs', 'create feature page', 'add to the docs site', or 'write the end-user guide'. Do NOT use for internal architecture docs (use arc42 or write-doc), ADRs (use document-decision), or CLAUDE.md updates (use create-or-audit-claude-md).
Write a new doc-site page (guide, tutorial, reference, concept) following the project's docs conventions. Use when user says 'write a doc', 'add a page to the docs site', 'create a guide for X', 'write a tutorial', 'document this concept', or 'add reference for our API'. Do NOT use for feature-specific end-user docs (use document-feature), ADRs (use document-decision), or CLAUDE.md updates (use create-or-audit-claude-md).
Sync documentation with code changes. Scans for README, CLAUDE.md, docs/ pages, and skills that reference behavior the current branch modifies, and updates or flags them. Use when user says 'update docs', 'sync documentation', 'is our documentation current', 'docs are stale', or 'update READMEs after this refactor'. Do NOT use for writing a fresh feature doc (use document-feature) or a new ADR (use document-decision).
Builds new project-specific skills or audits existing ones against the seven principles. Use when user says 'build a skill', 'create a skill', 'review this skill', 'audit our skills', 'is this skill good', 'what skills should we have', or 'clean up our skills directory'. Do NOT use for CLAUDE.md files (use create-or-audit-claude-md), subagents (use create-or-audit-agent), or hooks (use create-or-audit-hook).
Guide for setting up secured VS Code dev containers for coding agents. Use when creating or hardening a DevContainer to sandbox Claude Code or other coding agents, configuring Docker socket proxies, handling VS Code IPC escape vectors, setting up git worktree support, or verifying security controls. Covers threat model, three-layer defence architecture, Node.js/pnpm setup, and verification testing.
Run Codex CLI, Claude Code, OpenCode, or Pi Coding Agent via background process for programmatic control.
Enables Claude to create and manage documents with tables and automation in Coda via Playwright MCP
Screenshot-based visual comparison and regression testing using claude-in-chrome MCP. Captures, compares, and validates UI states to detect layout shifts, visual bugs, and design regressions across viewports.