one-pr-one-issue
Enforce 1 PR = 1 Jira Issue workflow for clean project tracking
Découvrez les skills Tests et sécurité, comparez leurs dépôts et consultez leurs instructions.
Enforce 1 PR = 1 Jira Issue workflow for clean project tracking
Build production-grade applications with OpenAI APIs (direct or via Azure OpenAI). Covers structured outputs, function calling, streaming, Assistants API, Responses API, Agents SDK, cost optimization, rate limi...
Use when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file paths, complete code examples, and ve...
Use when partner provides a complete implementation plan to execute in controlled batches with review checkpoints - loads plan, reviews critically, executes tasks in batches, reports for review between batches
Algorithmic decision tree for when to follow plan exactly vs when to report STOPPED - prevents scope creep and unauthorized deviations
Dispatch N independent review agents, collate by consensus ratio, cross-check exclusive findings
Use when executing multi-step processes requiring state persistence and agent coordination - defines two-tier protocol where subagents report PASS/FAIL status and main agent handles dispatch, advancement, and f...
Execute the complete TestFlight deployment workflow for this Flutter iOS app. Use when the user asks to deploy, release, publish, or upload the app to TestFlight, or says things like "deploy to testflight", "re...
Formats and writes session documentation to the appropriate location. Use when creating session logs or documentation entries.
Wraps up a coding session by creating documentation and committing artifacts. Use when the user says "wrap up", "close session", "let's finish", or similar end-of-session language.
Process documents into RAG database. Use when user wants to chunk, embed, or index files into a vector database for semantic search.
Search RAG database for relevant content. Use for semantic queries over processed documents, code, or papers.
Execute PostgreSQL queries against the Supabase database using psql with 1Password credential retrieval
Systematically analyzes and fixes GitHub CodeQL security alerts with proper documentation and testing
Guide for developing Next.js applications using the hua-ux framework
Debug and visually verify zensical sites with Chrome DevTools. Combines zensical development best practices with Chrome MCP port management. User-invocable with /zensical-debug.
Chrome DevTools MCP for browser automation. Five servers configured for parallel agents. Auto-select available server, cleanup when done.
Best practices for developing zensical/Material for MkDocs static sites. Covers installation, virtual environments, project structure, responsive images, CSS, media embedding, and verification. Use for ANY Mate...
Set up custom Claude Code status line with Nerd Font icons, colors, git status, usage tracking, system info, and project context. NO EMOJIS - only Nerd Font icons and symbols. Use when configuring statusline, s...
Download the latest Astronomy Picture of the Day from NASA. Use when the user asks to download APOD, get today's astronomy picture, fetch NASA's picture of the day, or save astronomy images.
Guide for fixing Python strict type checking errors (Pylance/MyPy). Use this skill when resolving unknown type, missing import, or type mismatch errors in Python files. Covers common patterns for TypedDict, gen...
Analyzes and optimizes prompt files for LLM agents. Use this skill when working with .prompt files, improving agent instructions, enhancing prompt clarity, or debugging agent behavior. Helps with prompt enginee...
Generates production-grade, high-availability logging modules for any programming language (Python, TypeScript, Go, etc.). Enforces best practices like rotation, formatting, and minimal dependencies.
Generates new agent skills following the official Agent Skills specification. Use when you need to teach the AI a new capability, create reusable workflows, or document best practices in a structured format.
Le classement utilise les étoiles du dépôt GitHub indexé. Plusieurs skills peuvent partager ce nombre : ce n’est ni un nombre d’installations ni une note de qualité.