计划执行与检查节点
executing-plans
按既定实施计划完成工作,保持过程检查和反馈。
一个技能,一个新的可能。找到适合你的 AI 工作流。
executing-plans
按既定实施计划完成工作,保持过程检查和反馈。
using-git-worktrees
使用独立工作树隔离开发任务,减少分支切换和冲突。
cangjie-skill
将书籍、长视频转写、播客及课程中的方法论提炼成可执行技能。官方 v2.5.0 刷新 ZIP 已通过作者 SHA256 与 BUILD_INFO 文件校验。
subagent-driven-development
效率与协作技能,来自 obra/superpowers,查看原文获取完整用途和操作说明。
git-guardrails-claude-code
【开发与工程】Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
wizard
【效率与协作】Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
agent-host-chat-contributions
【开发与工程】Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
spec
【效率与协作】Turn vague intent into a precise, executable spec in five phases. (gstack)
delegate-work
【效率与协作】Delegate user-requested work to an existing Paperclip agent, with a durable task reference and clear execution expectations.
reflection-coach
【开发与工程】Reflect on another agent's recent execution record and propose the smallest durable instruction, skill, or tool-description change. Use for evidence-backed coaching proposals, never hot-swaps.
task-planning
【效率与协作】Write or revise a useful Paperclip plan with a clear outcome and verification. Use when a plan is requested or uncertainty needs resolving before execution.
first-task
【效率与协作】Guide the user's first Paperclip task when its description invokes /first-task. Interpret the opening answer, clarify their goal, propose a plan or a single task, and wait for approval before hiring agents or executing approved work.
kernel-microbenchmark
【开发与工程】Build, debug, and interpret vLLM GPU kernel microbenchmarks for CUDA, ROCm/HIP, Triton, and CuteDSL, including CUPTI timing, correctness checks, generated-code inspection, multi-GPU measurements, and SOL sanity checks.
Shortcut Automation
【效率与协作】Automate project management workflows in Shortcut -- create stories, manage tasks, track epics, and organize workflows through natural language commands.
Snowflake Automation
【数据与研究】Automate Snowflake data warehouse operations -- list databases, schemas, and tables, execute SQL statements, and manage data workflows via the Composio MCP integration.
cutt-ly-automation
【开发与工程】Automate Cutt Ly tasks via Rube MCP (Composio). Always search tools first for current schemas.
googlebigquery-automation
【数据与研究】Automate Google BigQuery tasks via Rube MCP (Composio): run SQL queries, explore datasets and metadata, execute MBQL queries via Metabase integration. Always search tools first for current schemas.
langsmith-fetch
【开发与工程】Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.