Every Agent Skill,
One Registry
curl -fsSL askill.sh | shBrowse
Search the registry for skills built by the community.
AI Score
AI scores Safety, Clarity, Reusability, Completeness, and Actionability to filter risky skills.
Install
One command. Works with your agent automatically.
Works with 40+ agents
Pytest fixture patterns for Textual TUI application testing. Creates reusable test setup code including app factories, Pilot wrappers, mock fixtures, and async patterns. Use when: setting up test infrastructure for Textual apps, creating reusable tes...
Implements Google Cloud Pub/Sub integration in Python by configuring topics, subscriptions, publishing/subscribing, dead letter queues, and local emulator setup. Use when building event-driven architectures, implementing message queuing, or managing...
Set up uv (Rust-based Python package manager) in CI/CD pipelines. Use when configuring GitHub Actions workflows, GitLab CI/CD, Docker builds, or matrix testing across Python versions. Includes patterns for cache optimization, frozen lockfiles, multi-...
Model quantization for efficient inference and training. Covers precision types (FP32, FP16, BF16, INT8, INT4), BitsAndBytes configuration, memory estimation, and performance tradeoffs.
Direct Preference Optimization for learning from preference pairs. Covers DPOTrainer, preference dataset preparation, implicit reward modeling, and beta tuning for stable preference learning without explicit reward models. Includes thinking quality p...
Expert guidance for Zod v4 schema validation in TypeScript. Use when designing schemas, migrating from Zod 3, handling validation errors, generating JSON Schema/OpenAPI, using codecs/transforms, or integrating with React Hook Form, tRPC, Hono, or Nex...
Turborepo monorepo 构建系统指导。触发词：turbo.json、task pipelines、dependsOn、caching、remote cache、turbo CLI、--filter、--affected、CI optimization、environment variables、internal packages、monorepo structure/best practices、boundaries。
使用 squirrelscan CLI（squirrel）对网站进行审计，覆盖 SEO、技术、内容、性能、安全等 140+ 规则。当需要分析网站健康、排查技术 SEO、检查死链、校验 meta 与结构化数据、生成站点审计报告、对比改版前后，或提到「网站审计」「audit website」「squirrel」「站点健康检查」时使用。
Read-only CLI access to ServiceNow Table, Attachment, Aggregate, and Service Catalog APIs; includes schema inspection and history retrieval (read-only).
Use when AI systems fail or behave unexpectedly. Use after incident detected. Produces incident classification, immediate response actions, rollback procedures, and post-mortem templates.
Use when organizing and sharing prompts across teams. Use after prompts developed. Produces prompt registry, versioning system, quality ratings, and usage guidelines.
Use when deciding if a workflow step should be automated, AI-assisted, or left human-only. Use when stakeholders are enthusiastic about automation, when evaluating high-volume tasks, or when assessing automation candidates in regulated environments.
Use when evaluating whether a proposed AI capability is achievable with current LLM technology. Use before committing development resources, when stakeholders propose AI solutions, or when validating automation candidates from workflow analysis.
Use when evaluating AI capability test results against acceptance criteria for production deployment decision. Use after development complete and test results available. Produces structured go/no-go verdict with gap analysis and mitigation requiremen...
Comprehensive methodology for conducting technical reviews of Rust projects. Use when: (1) reviewing unfamiliar Rust codebases, (2) conducting project health assessments, (3) evaluating code quality and architecture, (4) preparing project audits or d...
Find the gaps in your plan before your stakeholders do. Pressure tests plans, strategies, and communications. Domain-smart advisor, not nitpicker.
Build deterministic, verifiable data visualizations with D3.js (v6). Generate standalone HTML/SVG (and optional PNG) from local data files without external network dependencies. Use when tasks require charts, plots, axes/scales, legends, tooltips, or...
Use when about to claim work is complete, fixed, or passing. Invoke BEFORE committing, creating PRs, or making any success claims. The Iron Law - evidence before assertions, always.
Use when implementing payment flows with Stripe or Polar. Covers checkout integration, webhooks, subscriptions, and error handling.
Use when deploying software to production or staging environments to ensure complete traceability of what was deployed, when, by whom, and from which source. Essential for audit compliance, incident investigation, and rollback decisions.
Tiered context management for multi-agent workflows. Use when: - Starting a new session and need to load project context - Context window approaching capacity (>70% usage) - Switching between different parts of a codebase - Preparing context for suba...
Extracts and analyzes competitors' ads from ad libraries (Facebook, LinkedIn, etc.) to understand what messaging, problems, and creative approaches are working. Helps inspire and improve your own ad campaigns.
Implement an RFC-compliant OAuth 2.1 authorization server in Rails applications. Use when building apps that need to authorize third-party clients (like MCP clients, API consumers, or external integrations) using industry-standard OAuth flows with PK...
Use when creating design systems or styling components with Tailwind CSS v4 and Class Variance Authority (CVA) - provides type-safe component variants with CSS variables for design tokens
Showing 49 to 72 of 214.4k results
Command Palette
Search for a command to run...