认证鉴权
认证与授权
crawler
alpoxdev
Explore websites directly with Playwriter to design robust crawling flows. Analyze APIs, cookies, tokens, and headers, then document findings and generate crawler code.
mcp-installer
IgorWarzocha
Find, install, and configure MCP servers. Use proactively for MCP discovery, OAuth setup, env vars, stdio vs SSE transport, or troubleshooting MCP connections. Examples: - user: "Add the filesystem MCP server" → read server file, add to mcpServers in opencode.json, verify transport type - user: "How do I use MCP with GitHub?" → check catalog, install @modelcontextprotocol/server-github, configure OAuth token - user: "MCP not connecting" → check transport type (stdio/SSE), verify args/command, check env vars are passed - user: "What MCPs are available?" → run list_mcps.py, show catalog with auth types and install commands
grey-haven-project-structure
greyhaven-ai
Organize Grey Haven projects following standard structures for TanStack Start (frontend) and FastAPI (backend). Use when creating new projects, organizing files, or refactoring project layout.
grey-haven-ontological-documentation
greyhaven-ai
Create comprehensive ontological documentation for Grey Haven systems - extract domain concepts from TanStack Start and FastAPI codebases, model semantic relationships, generate visual representations of system architecture, and document business domains. Use when onboarding, documenting architecture, or analyzing legacy systems.
janee
rsdouglas
Secure API proxy that stores credentials encrypted and injects auth server-side. Use when: (1) making any external API call — "call the Stripe API", "enrich my data [from PeopleDataLabs]", "create an image [using Nano Banana API]", "use a [RapidAPI service]", (2) the user shares an API key, token, or secret — "here's my API key", "I have a token for..." — store it in Janee instead of handling it directly, (3) you see API keys in env vars, .env files, or config files — offer to migrate them into Janee, (4) you're about to put a key in a curl command or Authorization header — use execute() instead. Do NOT use for: general coding questions, local file operations, or tasks that don't involve external API calls.
supabase-audit-functions
yoanbernabeu
Discover and test Supabase Edge Functions for security vulnerabilities and misconfigurations.
vulnerability-scan
ymd38
Run an offensive security audit (OWASP-based) using Semgrep and produce a read-only vulnerability report. Use before committing code to detect Broken Access Control, Injection (SQL/NoSQL/OS/Template), Frontend Security issues (XSS/CSP/HSTS), SSRF, and hardcoded secrets or PII exposure. Triggers on requests like "security scan", "vulnerability check", "audit security", "find vulnerabilities", "/vulnerability-scan", or when asked for an offensive security review of the codebase. Does NOT modify any code — read-only inspection only.
maestro-mobile-testing
tovimx
"Maestro mobile E2E testing patterns for React Native/Expo apps: YAML test flows, testID selectors, adaptive auth state, optimistic update verification, GraalJS scripting, cross-platform stability, CI/CD integration, Maestro Cloud, and MCP server integration"
codex-code-reviewer
VCnoC
Systematic code review workflow using zen mcp's codex tool. Use this skill when the user explicitly requests "use codex to check the code", "check if the recently generated code has any issues", or "check the code after each generation". The skill performs iterative review cycles - checking code quality, presenting issues to the user for approval, applying fixes, and re-checking until no issues remain or maximum iterations (5) are reached.
session-index
lee-fuhr
Search, analyze, and synthesize across all your Claude Code sessions. Ask "what did I try last time?" and get answers with resume links.
optimize-agent-docs
petekp
Build a retrieval-optimized knowledge layer over agent documentation in dotfiles (.claude, .codex, .cursor, .aider). Use when asked to "optimize docs", "improve agent knowledge", "make docs more efficient", or when documentation has accumulated and retrieval feels inefficient. Generates a manifest mapping task-contexts to knowledge chunks, optimizes information density, and creates compiled artifacts for efficient agent consumption.
handoff
petekp
Generate a smart bootstrap prompt to continue the current conversation in a fresh session. Use when (1) approaching context limits, (2) user says "handoff", "bootstrap", "continue later", "save session", or similar, (3) before closing a session with unfinished work, (4) user wants to resume in a different environment. Outputs a clipboard-ready prompt capturing essential context while minimizing tokens.
teach
adamos486
Transforms technical documents into rigorous learning journeys with collegiate-level mastery requirements. Uses Bloom's taxonomy progression, 80%+ mastery thresholds, and multi-level verification before advancing. Treats learning as a high school to college graduation progression. Use when user wants deep understanding, not surface familiarity.
security
Tyler-R-Kendrick
Use when addressing cross-cutting security concerns that apply to all languages, frameworks, and platforms. Covers OWASP standards, threat modeling, authentication, cryptography, supply chain security, and AI security. USE FOR: application security strategy, security architecture, choosing security controls, OWASP compliance, security tool selection, secure development lifecycle DO NOT USE FOR: specific language security implementations (use language-specific skills), infrastructure hardening (use iac skills), network security appliance configuration
supabase-audit-authenticated
yoanbernabeu
Create a test user (with explicit permission) to audit what authenticated users can access vs anonymous users. Detects IDOR, cross-user access, and privilege escalation.
caido-mcp
vvvvvvvvvvel
Use Caido MCP tools to inspect captured HTTP traffic, Sitemap, WebSocket messages, Replay, scopes, findings, filters, environments, and Tamper rules with compact projections, HTTPQL filters, regex excerpts, and safe evidence-focused workflows.
elasticsearch
davidgeorgehope
Interact with Elasticsearch and Kibana via REST API using curl. Use when querying, indexing, managing indices, checking cluster health, writing aggregations, deploying dashboards, or troubleshooting Elasticsearch. Requires cluster URL and API key. Covers: search (Query DSL), CRUD operations, index management, mappings, aggregations, cluster health, ILM, ES QL, Kibana API (dashboards, data views, saved objects), OpenTelemetry data patterns, and common troubleshooting patterns.
rg_history
backnotprop
Search your conversation history using ripgrep. Use when you need to find previous messages, file edits, tool calls, or decisions from earlier in the session.
qa-use
desplega-ai
E2E testing and browser automation with qa-use CLI. Use when the user needs to run tests, verify features, automate browser interactions, or debug test failures.
encore-go-auth
encoredev
Implement authentication with Encore Go.
plan-revision
srstomp
Use when revising existing implementation plans, analyzing impact of task changes, exploring modifications to project scope or dependencies, or updating task hierarchies with full impact visibility before execution.
session-review
srstomp
Use after completing work sessions to analyze agent behavior patterns, prepare session handoffs for continuity, document completed work, identify blockers, or preserve context for the next session.
prompt-review
ssiumha
Refines user prompts through structured dialogue to produce executable prompts with delegation plans. Use when user requests are vague or multi-file, or manually via /prompt-review or /refine.
browser-use
yoloshii
Agentic browser automation with persistent sessions and ARIA snapshot-based navigation. Use when user needs to browse websites, interact with web pages, fill forms, login to sites, warm up social accounts, bypass anti-bot protection, take screenshots, execute JavaScript on pages, manage cookies, handle multi-tab workflows, extract page content as Markdown, search page text, find elements by role or text, upload files, download files, use WebMCP structured tools on Chrome 146+ pages, or perform any multi-step browser task. Three stealth tiers (Playwright, Patchright, Camoufox) with auto-escalation for anti-bot, session persistence with cookie/storage profiles, element ref system, WebMCP tool discovery, new-element detection between snapshots, action loop detection with escalating warnings, auto popup dismissal, download handling, click-by-coordinate fallback, context compaction for long sessions, idle session GC, and per-session locking.