Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
refactor-scope-session
This skill provides a structured checklist for defining refactoring session boundaries. It helps developers establish clear goals, in-scope/out-of-scope items, and success criteria before making code changes. The checklist format ensures systematic planning for safer refactoring.
dev-workflow-orchestrator
Orchestrates a three-phase development workflow: PRD creation using prd-writer, task generation with parent/sub-task breakdown, and gated task processing with user confirmations between phases. Enforces structured development with explicit pauses for review.
using-life-os
Life OS is an AI-powered personal operating system that helps manage daily life through integrated skills for meal planning, recipe finding, grocery shopping, task management, and WhatsApp-based briefings, adapting to your personality and preferences.
research-pipeline-runner
Run this repo’s Units+Checkpoints research pipelines end-to-end (survey/综述/review/调研/教程/系统综述/审稿), with workspaces + checkpoints. **Trigger**: run pipeline, kickoff, 继续执行, 自动跑, 写一篇, survey/综述/review/调研/教程/系统综述/审稿. **Use when**: 用户希望端到端跑流程（创建 `workspaces/<name>/`、生成/执行 `UNITS.csv`、遇到 HUMAN checkpoint 停下等待）。 **Skip if**: 用户明确要手工逐条执行（用 `unit-executor`），或你不应自动推进到 prose 阶段。 **Network**: depends on selected pipeline (arXiv/PDF/citation verification may need network; offline import supported where available). **Guardrail**: 必须尊重 checkpoints（无 Approve 不写 prose）；遇到 HUMAN 单元必须停下等待；禁止在 repo root 创建 workspace 工件。
mcp-builder
A guide for building MCP servers that connect LLMs to external services. Provides structured workflow from research to implementation, with specific advice for Python and TypeScript. Focuses on designing tools for AI agents rather than just wrapping APIs.
Verification Gates
Define checkpoints to validate work before proceeding to next phase
Design First
Think before coding - design the solution before implementing
investigation-workflow
A systematic 6-phase investigation workflow for understanding existing systems and codebases, featuring parallel agent deployment for efficient deep dives and automatic knowledge capture to prevent repeat research efforts.
tasklist-generator
Converts PRDs into structured task lists with file references and testing notes. Uses a two-phase approach with user confirmation between high-level tasks and detailed sub-tasks. Outputs markdown files with numbered checklists and co-located test file suggestions.
mcp-builder
Guides developers through building MCP servers for connecting LLMs to external APIs. Provides structured workflow from research to implementation, with language-specific guidance for Python and TypeScript. Focuses on agent-centric tool design and practical error handling.
citation-management
Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.
planning-with-files
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
extract-prd
This skill analyzes existing codebases to extract Product Requirements Document worksheets. It reads test files, API definitions, and configuration files to infer features and non-functional requirements, then outputs structured worksheets for documentation.
user-file-ops
Simple operations on user-provided text files including summarization.
technical-specification
This skill generates detailed technical specifications for software projects, including requirements, architecture, API design, and testing strategies, to ensure clear planning, comprehensive documentation, and alignment among stakeholders.
problem_framing
Frame the core customer problem, evidence, and success hypothesis before solutioning.
writing-plans
Generates detailed TDD implementation plans for engineers new to a codebase, breaking features into 2-5 minute atomic tasks with clear commit guidelines and execution handoff options.
nlp-research-repo-package-installment
Align Python version and repo-declared dependencies (requirements.txt / environment.yml) before installing packages for NLP research code reproduction.
brainstorming
Collaborative ideation for projects and writing. Ask clarifying questions, suggest angles, challenge assumptions, and help refine vague ideas into concrete requirements or topics. Use when exploring ideas before planning or drafting.
debugging
Systematic debugging that identifies root causes rather than treating symptoms. Uses sequential thinking for complex analysis, web search for research, and structured investigation to avoid circular reasoning and whack-a-mole fixes.
data-systems-architecture
Use when designing databases for data-heavy applications, making schema decisions for performance, choosing between normalization and denormalization, selecting storage/indexing strategies, planning for scale, or evaluating OLTP vs OLAP trade-offs. Also use when encountering N+1 queries, ORM issues, or concurrency problems.
consulting-analysis
Use this skill when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial analysis, industry research, competitive intelligence, investment due diligence, or any consulting-grade analytical report. This skill operates in two phases — (1) generating a structured analysis framework with chapter skeleton, data query requirements, and analysis logic, and (2) after data collection by other skills, producing the final consulting-grade report with structured narratives, embedded charts, and strategic insights.
persona-researcher
Organize research — manage references, notes, and collaboration.
researcher-hand-skill
Expert knowledge for AI deep research — methodology, source evaluation, search optimization, cross-referencing, synthesis, and citation formats