发现 Skills
为真实工作流程挑选经过整理的 Skill,连接、安装并开始使用。
copywriting
Use this skill when writing, rewriting, or improving marketing copy for any page (homepage, landing page, pricing, feature, product, or about page). This skill produces clear, compelling, and testable copy while enforcing alignment, honesty, and conversion best practices.
File Path Traversal Testing
This skill should be used when the user asks to "test for directory traversal", "exploit path traversal vulnerabilities", "read arbitrary files through web applications", "find LFI vulnerabilities", or "access files outside web root". It provides comprehensive file path traversal attack and testing methodologies.
monorepo-architect
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development. Use proactively to set up monorepos.
superpowers-lab
Lab environment for Claude superpowers
teamcamp-automation
Automate Teamcamp tasks via Rube MCP (Composio). Always search tools first for current schemas.
mcp-builder
MCP (Model Context Protocol) server building principles. Tool design, resource patterns, best practices.
prompt-optimizer
This skill should be used when the user asks to "optimize my image prompt", "improve this prompt", "make this prompt better", "rewrite my prompt for Gemini", "enhance my image description", "fix my prompt", "why isn't my prompt working", "optimize for Nano Banana", "convert my Midjourney prompt", "translate my DALL-E prompt", or when the user provides a rough/vague image description that needs transformation into a production-quality Nano Banana prompt. Also triggers when a generated image doesn't match expectations and the prompt needs debugging.
ROS2 Lifecycle Nodes
ROS2 Managed (Lifecycle) Node implementation with Clean Architecture (Python & C++)
image
Generate images using AI providers (OpenAI DALL-E 3, Google Gemini 3.0, xAI Aurora)
qmd
Search personal Markdown knowledge bases, notes, meeting transcripts, and documentation using QMD - a local hybrid search engine. Combines BM25 keyword search, vector semantic search, and LLM re-ranking. Use when users ask to search notes, find documents, look up information in their knowledge base, retrieve meeting notes, or search documentation. Triggers on "search my notes", "find in docs", "look up", "what did I write about", "meeting notes about".
multi-scope-skill
Present in multiple scopes to demonstrate shadowing
specification-engine
Generates specifications using SpecKit before implementation tasks.
segmentation-mask-qc
Validates segmentation masks in NIfTI format by checking label values, detecting empty masks, finding connected components, and identifying small spurious regions.
triad-signal-filter
Prevent message looping and hallucination by enforcing "speak only on update" discipline. Use when agents are echoing identical messages, spamming status variants, or posting rate-limit errors repeatedly. This skill filters outbound messages to require genuine progress, status changes, or novel information before posting.
json-canvas
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
prot-msa
Multiple sequence alignment, conservation analysis, and position-specific mutation risk scoring. Uses mmseqs2/hhblits for real MSA when available, with ESM-2 pseudo-conservation as a zero-dependency fallback. Provides family-calibrated conservation scores, consensus sequences, coevolution signals, and low-risk mutation suggestions. Triggers whenever you need to assess how conserved a position is, build a consensus sequence, identify coevolving positions, or calibrate ESM-2 LLR with family context.
prd-to-spec
Convert PRD.md into structured SPEC.md with atomic development tasks. Use when user has a PRD and says "convert to spec", "create spec from PRD", "PRD to tasks", "prepare for Ralph Loop", or wants a development-ready task breakdown with user stories, acceptance criteria, and INVEST-compliant atomic tasks.
build-diagrams
Use when creating technical diagrams for documentation, architecture, processes, or data models. Supports Mermaid.js with C4, flowcharts, sequence, block-beta grids, ER, state, class, Gantt, and mindmap diagrams.
hitpop-rendervid
Programmatic template-based video generation using Rendervid. Free, open-source, AI-agent-native. Create marketing videos, social content, and data-driven videos from JSON templates. Built-in MCP server with 100+ templates.
prepare-task
Use when user says "/evolve prepare", "prepare toolkit", "check toolkit gaps", "do I have the right agents", "what tools do I need", "analyze my toolkit", "what workflow should I follow", or before complex tasks that might need specialized agents, skills, or workflow guidance. To manage an ACTIVE workflow (advance, skip, check status), use the workflow skill instead.
market-ads
Ad Creative & Copy Generation
paperclip-lead-enrichment-engine
Paperclip lead enrichment — takes daily lead sweep results, enriches via Apollo/Vibe/WebSearch, logs to Paperclip BDM project
repo_infographic
Generates a crisp, clear full infographic of the repository with a unique theme based on the repo's content. Saves the infographic to the assets folder and links it in the README.md file.
devops-judge
Infrastructure, CI/CD, and deployment perspective. Plans deployment impact in plan phase, verifies infra/pipeline changes in review phase.