opencode-runner
Run coding tasks via opencode using free cloud models. Use when asked to offload work to opencode.ai or run a free model. Don't use for local models (Ollama,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-01 00:15
Coding & development
39,087 results
decisions
Guide for recording significant architectural and design decisions in docs/decisions.md. Use this skill when clearly significant architectural decisions are…
rails-webhooks
Build and review Rails webhook systems with safe delivery, retries, observability, and tenant-aware security controls. Use when adding webhook endpoints,…
prefer-type-annotations
Use when assigning values to variables with types. Use when tempted to use type assertions. Use when TypeScript flags type errors you want to silence.
matlab-create-custom-arduino-library
Use when the user wants to use Arduino sensors or peripherals from MATLAB that are not directly supported by the MATLAB Support Package for Arduino Hardware.…
api-test-generator
Generate comprehensive API endpoint tests for REST and GraphQL APIs. Creates tests for all HTTP methods, status codes, authentication, and validation.
codebase-architecture-governance
Analyze and improve a software project's module boundaries, dependency direction, file organization, code duplication, oversized modules, and unnecessary…
java-kotlin
Java and Kotlin programming patterns
mobile
Mobile development with React Native, Flutter, and native patterns
qa-report-generator
The closing stage of the QA process—aggregates the three gate artifacts: execution (completion), review (code-review), and readiness, renders the final HTML report, and gives the final readiness verdict. Triggered after qa-test-runner execution completes and qa-code-reviewer review completes. Read-only on existing gate artifacts; does not re-execute tests or review code.…
qa-risk-analyzer
Before designing test cases, first identify high-risk business paths and the required verification assertions (oracles). Analyze requirements documents, code diffs, existing test cases, and context to find high-risk areas such as money/permissions/state machines/concurrency/async/data consistency, and output each risk's businessPath, requiredAssertions, suggestedTestLayers, …
moonshine-field
Create custom MoonShine form fields with PHP classes, Blade views, Alpine.js interactivity, and proper data handling. Use when building custom input types,…
deploying-palo-alto-prisma-access-zero-trust
Deploys Palo Alto Networks Prisma Access for SASE-based zero trust network access, configuring GlobalProtect agents, ZTNA Connectors, security policy…
dag-development
Develop causal diagrams (DAGs) from social-science research questions and literature, then render publication-ready figures using Mermaid, R, or Python.
trust-builder
Analyzes web apps for free-value trust-building opportunities — features, tools, and offerings that demonstrate genuine utility before asking for commitment.…
review-orm-usage
Review ORM usage patterns for N+1 queries, connection management, migration safety, transaction handling, and query efficiency. Library-level atomic skill;…
review-python
Review Python code for language and runtime conventions: type hints, exceptions, async/await, context managers, dependencies, and testability. Language-only…
netbox-diode
Patterns for ingesting data into NetBox using the Diode SDK (Python and Go). Use when building network discovery, bulk import, or automated data population…
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code - write the test first, watch it fail, write minimal code to pass; ensures…
electron-best-practices
Guide AI agents through Electron app development with React including security patterns, type-safe IPC, React integration, packaging with code signing, and…
code-complexity-audit
Scan and analyze a software repository or project for design quality using principles from A Philosophy of Software Design by John Ousterhout. Use when user…
implement-afk-agentic
Implement and ship one agent-ready ticket unattended using its pre-agreed seams, halting instead of guessing when the ticket leaves a decision open. Use for…
raycast-extensions
Build Raycast extensions — commands, List/Form/Grid views, hooks like useFetch, AI integration, manifest. Use when the user says 'raycast extension', 'add a…
dynamic-api-integration
Discover, parse, and call external HTTP APIs at runtime using OpenAPI specs, tool templates, and iterative chaining. Adapted from UTCP (Universal Tool Calling…