129 boosters for "exec" — open source, verified from GitHub, ready to install
Use uv exclusively for Python package management in all projects.
"description": "Zero-config goal-to-tasks engine for Claude Code (the Atlas engine). Graded PRD validation, dependency-ordered task graph, and CDD-verified execution.", "url": "https://atlas-ai.au" "homepage": "https://github.com/anombyte93/prd-taskmaster",
1. Verify SDK initialization happens before app starts 2. Check for single initialization point (no multiple init calls) 3. Use framework-specific SDK package for your framework
"name": "axlabs-mckinsey-pptx", "description": "McKinsey-style PPTX generator with 40 production-ready slide templates (executive summary, BCG matrix, KPI dashboard, roadmap, org chart, historic-forecast, etc.). Ships with a subagent that picks the right template for each slide, defends its choice,
Custom codegen'd CDP SDK (every method from browserprotocol.json + jsprotocol.json gets a typed wrapper) plus a tiny HTTP server that holds one persistent CDP . The CLI auto-starts the server on first use and forwards JS snippets to it. The SDK lives in the skill's directory. In the rest of this d
Accessible workspace directory: !!<<<<||||workspace_dir||||>>>>!! When processing tasks, if you need to read/write local files and the user provides a relative path, you may choose to combine it with the above workspace directory to get the complete path. If you believe the task is completed, you ca
"name": "offensive-claude", "description": "Spec-driven offensive-security framework for Claude Code: 31 kill-chain skills, executable safety controls (scope/finding/OPSEC discipline), pattern-learning memory, and a bounded engagement engine — with a SessionStart dispatcher that enforces skill-invoc
"name": "orchestrator-supaconductor", "description": "Conductor v3 — Multi-agent orchestration with Evaluate-Loop, parallel execution, Board of Directors, and bundled SupaConductor skills for Claude Code", "orchestrator-supaconductor",
This is the universal AI skills library — 204 production-ready skill packages across 13 professional domains with 559 Python automation tools and 12 sample CI/CD workflows. It works with every major AI coding assistant. This is NOT a traditional application. It's a library of self-contained skill pa
A system prompt that transforms an AI assistant into a job search agent capable of managing Notion databases, filtering job opportunities, and automating application workflows. Useful for job seekers and recruiters seeking to streamline application tracking.
This skill gives you full access to a running marimo notebook. You can read cell code, create and edit cells, install packages, run cells, and inspect the reactive graph — all programmatically. The user sees results live in their
A multi-language quality validation tool that automatically runs linting, formatting, type checking, and tests across 9 programming languages to ensure code meets standards before PR submission. Developers use it to catch quality issues early and maintain consistent code standards throughout their projects.
Enables efficient searching of Zotero libraries through Python code execution, avoiding context crashes while providing multi-strategy search with automatic deduplication. Ideal for researchers and developers who need comprehensive, safe access to large reference collections.
Smart PRD generation with deterministic operations handled by . AI handles judgment (questions, content, decisions); script handles mechanics. Activate when user says: PRD, product requirements, taskmaster, task-driven development.
Automates story task orchestration by prioritizing and delegating work across subtasks, automatically advancing stories through the development workflow. Developers and project managers using Linear/Kanban boards benefit from reduced manual status management.
你是 OpenClaw 内部负责操作 Codex CLI 的执行器。你的职责不是“给用户解释 Codex 是什么”，而是基于当前仓库提供的 runtime 层，把 Codex 任务稳定启动、持续跟踪、必要时接管和汇报。 可以借鉴 的 runtime/session 思路，但不照搬 Claude 专用逻辑。 优先直接使用 Codex review，而不是自己拼一套“审查 prompt 模拟 review”：
"name": "compound-knowledge-plugin", "url": "https://every.to" "description": "Workflows for knowledge work that compounds over time",
"name": "tensorlake", "description": "Tensorlake SDK for agent sandboxes and sandbox-native orchestration. Use when building AI agents that need sandboxed execution environments, isolated tool calls, or durable workflow orchestration.", "author": "TensorLake",
ring:dev-implementation automates code development using specialized agents and enforces test-driven development (TDD) workflows across projects. Development teams benefit from consistent implementation patterns and quality gates.
This MCP server bridges n8n workflow automation with Claude by providing programmatic access to workflows, executions, and credentials through the Model Context Protocol. It's valuable for developers and automation engineers who want to integrate n8n capabilities into AI-powered applications and Claude instances.
A booster that helps developers optimize slow Python code through profiling, async/await patterns, and concurrent execution strategies. Ideal for Python developers dealing with performance bottlenecks who need guidance on measurement before optimization.
A manifest executor that automates implementation and verification of deliverables against pre-defined acceptance criteria and global invariants. Ideal for developers using structured planning workflows who want to ensure quality execution and reduce rework.
