认证鉴权
认证与授权
garmin-connect
eddmann
Query Garmin Connect fitness and health data including activities, athlete stats, sleep, heart rate, stress, and body battery. Use when the user asks about Garmin data, workouts, training, or health metrics.
problem-space
open-horizon-labs
Map what we're optimizing and what constraints we treat as real. Use before jumping to solutions, when hitting repeated blockers, or when patches keep accumulating.
solution-space
open-horizon-labs
Explore candidate solutions before committing. Use when you have a problem statement and need to evaluate approaches - band-aid, optimize, reframe, or redesign.
python-testing
peopleforrester
Comprehensive Python testing patterns using pytest. Covers fixtures, parametrize, async testing, mocking, property-based testing, and coverage analysis.
problem-statement
open-horizon-labs
Define the framing of a problem. Change the statement, change the solution space. Use when starting work, when solutions feel wrong, or when you suspect an X-Y problem.
tmux
tizee
"Remote control tmux sessions for interactive CLIs by sending keystrokes and scraping output."
horse-browser
pA1nD
A dedicated, persistent CDP browser plus a tab-grouper extension that drops each agent's tabs into its own per-session group and opens them without stealing OS focus. Use whenever you drive a browser via horse-browser (a browser-harness drop-in) — opening tabs, navigating, scraping, rendering, screenshots.
Claude Code X - Autonomous Execution Subagent
ShunsukeHayashi
Miyabi Plugins for Claude Code - 25+ Agents, 22 Skills, 50+ Commands
spice-cloud-management
spiceai
Manage Spice.ai Cloud apps, deployments, secrets, API keys, and org members via the Management API. Use when creating or updating cloud apps, deploying Spicepods, managing secrets or API keys, listing regions or runtime versions, or automating Spice.ai Cloud operations.
execute
open-horizon-labs
Do the work. Pre-flight, build, detect drift, salvage if needed. Use when you have a clear aim and are ready to implement.
salvage
open-horizon-labs
Extract learning before restarting. Code is a draft; learning is the asset. Use when work is drifting, approach has reversed 3+ times, or scope is expanding while "done" keeps fuzzing.
coderabbit
indrasvat
Local AI code reviews via CodeRabbit CLI. ONLY use when (1) user explicitly requests "coderabbit"/"cr review", OR (2) code changes are high-risk (security, concurrency, complex logic). Rate-limited to 1 review/hour—be highly selective.
aim
open-horizon-labs
Clarify the outcome you want - a change in user behavior, not a feature shipped. Use at the start of any work to ground the session in strategic intent.
nextjs-patterns
peopleforrester
Next.js 15+ App Router best practices. Covers server components, data fetching, caching, middleware, and deployment patterns. Use when building Next.js applications or reviewing Next.js code.
openclaw-cli-bridge-elvatis
elvatis
Bridge local AI CLIs + web browser sessions (Grok, Gemini, Claude.ai, ChatGPT) into OpenClaw as model providers. Includes /cli-* slash commands for instant model switching and persistent browser profiles for all 4 web providers.
fastapi-patterns
peopleforrester
FastAPI 0.110+ best practices. Covers dependency injection, async endpoints, Pydantic v2 validation, middleware, background tasks, and deployment patterns. Use when building FastAPI applications or reviewing FastAPI code.
create-nextjs-ddd-auth-db
micheleangioni
Create a new fullstack Next.js. Use this skill when the user asks to create a new Next.js project or application.
teach-oh
open-horizon-labs
Project setup. Explore the codebase, ask about strategy and aims, write persistent context to AGENTS.md. Run when starting or when aims shift.
review
open-horizon-labs
Check work and detect drift before committing. A second opinion that catches misalignment early. Use at natural pause points, before PRs, or when something feels off.
django-security
peopleforrester
Django security best practices. Covers CSRF, XSS, SQL injection prevention, authentication hardening, Content Security Policy, secrets management, and Django-specific security middleware configuration.
spec-driven-development
peopleforrester
Interview-first specification workflow for feature development. Guides through 8 question categories to build comprehensive specs before coding. Use when starting new features, planning complex changes, or establishing clear requirements before implementation.
iterative-retrieval
peopleforrester
Progressive context refinement pattern for subagents. Solves the problem of agents not knowing what context they need until they start working. Uses a 4-phase loop: DISPATCH, EVALUATE, REFINE, LOOP.
springboot-security
peopleforrester
Spring Security 6.x best practices. Covers SecurityFilterChain, JWT auth, OAuth2, CORS, CSRF, method-level security, password encoding, and rate limiting for Spring Boot 3.x applications.
iterm2-driver
indrasvat
Drive iTerm2 programmatically using Python scripts to automate terminal tasks, run tests, or manage sessions. Use when the user needs to test TUIs, CLIs, terminal apps, terminal automation, interactive terminal testing, terminal UI, command-line interface automation, REPL automation, screen monitoring, or terminal screenshots. Supports iTerm2 and iterm automation.