1,266 boosters for "claude-code" — open source, verified from GitHub, ready to install
Evaluate the user's ambient context artifacts for compatibility with swarm's governance rules. You are a read-only diagnostic — never modify any files. 1. CLAUDE.md files. Read the project's (working directory root). If exists, read that too. Also check (global config) — it loads into every sessi
A review finding is stuck. Structure its resolution in three steps. Identify and state aloud: After the reviewer responds:
The team can't find existing standards. Help them build a rubric. Ask: what does the output look like when it's right? Get specific, measurable answers. File sizes, response times, value ranges, visual correctness, behavioral expectations. If the user or team can't quantify it, ask what they'd check
"email": "stan001212@gmail.com" "description": "AI coding session monitor", "source": "./plugins/cctop",
"description": "Launch agent teams for any kind of work — coding, writing, diagnosis, and more", "name": "Dheer Gupta", "email": "noreply@dheer.co"
A sentence or paragraph can look fine in isolation. When the same structural shape repeats across 1,000-3,000 words, the aggregate creates a mechanical feeling — even though no single instance is wrong. Linear readers miss this because they process sequentially and each paragraph clears the "is this
Return the following mode definition verbatim to the team lead. Do not summarize or interpret — the lead needs the full specification. You are the team lead. You manage the team with patience — you do not hurry teammates along, and you do not overcommunicate. You produce the deliverable: a confidenc
Ask an opening question to gauge where the user stands: Use these question types, escalating from simple to complex: When the user arrives at the answer, ask them to summarize:
本 skill 通过 Tushare Pro API 获取中国金融市场数据，支持 220+ 个数据接口。 1. 访问 https://tushare.pro 注册 1. 查找接口：根据需求在 接口索引 找到对应接口
"name": "goast-policy", "description": "Guide for writing goast Rego policies: AST input format, Rego v1 rule contract, recipes, and testing workflow", "name": "Masayoshi Mizutani",
Full-featured preflight security scanner across 5 dimensions: Works with OpenClaw, Claude Code, Cursor, Codex, and OpenCode. LLM features auto-detect credentials — no manual configuration needed. 1. Present the total score and per-module breakdown to the user
Rebase the current branch onto the remote trunk branch. Follow these steps carefully, handling each phase before moving to the next. Determine the trunk branch name from the context above (the "Trunk branch" value). Store it mentally as . It will typically be or . If detection failed, try both and
"name": "Dheeraj Joshi", "url": "https://github.com/djadmin" "description": "Audit your Mac's security in one command from Claude Code, understand every finding in plain language, and fix what's safe. Drives the fort CLI over your shell.",
"name": "daem0nmcp", "description": "AI memory system with semantic understanding - provides persistent memory, decision trees, and outcome tracking", "homepage": "https://github.com/DasBluEyedDevil/Daem0n-MCP",
"description": "Shared development tools for Submariner repositories", "name": "Submariner Contributors", "url": "https://github.com/submariner-io"
"name": "grainulator", "description": "Research sprint orchestrator for Claude Code. Structured research with claims, evidence tiers, and compiled output.", "name": "Grainulation"
"mcpName": "io.github.sverklo/sverklo", "version": "0.29.2", "description": "Local-first repo-memory MCP for coding agents. Best for relationship-heavy edits: symbols, callers, dependencies, diff review, and git-pinned decisions before code changes. Start with a no-write proof receipt; use grep/ripg
"name": "open-plan-annotator", "description": "Interactive plan annotation UI: review, strikethrough, and comment on Claude's plans before approving. Fully local, no external services.", "homepage": "https://github.com/ndom91/open-plan-annotator",
"name": "inference-builder", "description": "Generate deployable Vision AI pipelines with high-performance video and streaming capabilities on NVIDIA GPUs. Create GPU-accelerated inference microservices using DeepStream, Triton, vLLM, TensorRT-LLM, or PyTorch backends.",
Launch background tasks for parallel execution. Enables concurrent work on independent tasks with result aggregation. Launch a background task or manage running tasks. Start a new background task:
你是 Relic 引擎，一个能把万物锻造成可交互数字灵魂的系统。 如果用户说"让我跟奶奶聊天""让我跟咪咪互动""模拟星火工作室群聊"或类似的体验请求： 2. 根据蒸馏对象类型，从 选择合适的模板
A unified initialization booster that streamlines project setup by routing to specialized commands for documentation, preferences, and design tokens—ideal for developers standardizing new projects and maintaining consistent configurations.
"name": "director-mode-lite", "description": "Use Claude Code like a Director, not a Programmer. Complete toolkit with 26 commands, 14 agents, 31 skills, and TDD-based Auto-Loop.", "name": "Lucas Wang",
This is a Shell/Markdown toolkit for Claude Code Director Mode. Keep shell scripts POSIX-compatible where possible. Markdown files are the primary deliverable.
