Marketplace
SkillHub Club catalog feed.
Public marketplace mirror sourced from skillhub.club. This source view keeps the new outcome-first browsing model while filtering server-side to a single upstream feed.
cfn-cerebras-mcp
Provides access to Cerebras MCP tool for fast code generation using Z.ai glm-4.6 model. Best for creating test files, boilerplate code, and repetitive patterns where speed matters more than nuance. Requires prompts shorter than expected output.
lessons
Provides structured lesson files for the Claude Code Course, serving as a content repository for educational materials. It's designed to be read based on user progress tracking, offering a straightforward way to deliver course content through Claude's interface.
swarm-orchestration
This skill provides a framework for orchestrating multiple AI agents to work together on complex tasks. It supports different agent topologies like mesh and hierarchical, handles parallel and sequential task execution, and includes features for shared memory and load balancing. It's built on the agentic-flow library.
frontend-ui-animator
Provides a structured workflow for adding animations to Next.js/Tailwind projects, with clear phases for analysis, planning, implementation, and verification. Includes performance rules and accessibility considerations.
nanogpt-training
Train GPT-2 scale models (~124M parameters) efficiently on a single GPU. Covers GPT-124M architecture, tokenized dataset loading (e.g., HuggingFace Hub shards), modern optimizers (Muon, AdamW), mixed precision training, and training loop implementation.
Pandas Data Analysis
Master data manipulation, analysis, and visualization with Pandas, NumPy, and Matplotlib
understanding-flow
This skill explains the core architectural pattern of walkerOS with clear diagrams and TypeScript examples. It focuses on the Source→Collector→Destination event flow, separation of concerns, and the universal push interface. Helps developers understand how to compose modular pipelines for event processing.
paper-notes
Write structured notes for each paper in the core set into `papers/paper_notes.jsonl` (summary/method/results/limitations). **Trigger**: paper notes, structured notes, reading notes, 论文笔记, paper_notes.jsonl. **Use when**: survey 的 evidence 阶段（C3），已有 `papers/core_set.csv`（以及可选 fulltext），需要为后续 claims/citations/writing 准备可引用证据。 **Skip if**: 还没有 core set（先跑 `dedupe-rank`），或你只做极轻量 snapshot 不需要细粒度证据。 **Network**: none. **Guardrail**: 具体可核对（method/metrics/limitations），避免大量重复模板；保持结构化字段而非长 prose。
cfn-edit-safety
Provides file backup before editing and validation hooks after changes. Captures file state for potential revert, validates modifications through a pipeline, and integrates backup and validation into a single workflow for safer file operations.
detector
A bash script that monitors Claude agent performance during CFN loops, detecting confidence plateaus, recurring feedback patterns, and stalled deliverables. Provides JSON output with trigger types and recommended actions.
integration
A Bash script that provides task intelligence for Claude Flow Novice loop orchestration. It classifies tasks, estimates complexity, recommends specialists, and tracks execution outcomes using SQLite for persistence. The tool helps route tasks to appropriate agents based on content analysis.
cloudflare-pages
Provides documentation and guidance for Cloudflare Pages, a static site hosting platform. Includes reference files for configuration, functions, and framework guides. Offers basic command examples and structured documentation access.
security-check
Automatically runs OWASP security checks on generated code, providing validation for common vulnerabilities like SQL injection and exposed secrets. It includes auto-fix suggestions for issues and can be run via command line scripts. The tool operates silently unless unfixable security issues are found.
postmortem-writing
Provides a structured template for writing post-incident reports with sections for timeline, root cause analysis, impact assessment, and action items. Emphasizes blameless culture and includes practical examples like the 5 Whys technique.
pipeline-design
Provides ETL/ELT pipeline design patterns with clear diagrams and SQL examples. Covers batch and streaming architectures, staging patterns, and error handling strategies for data engineers.
evaluate
A testing and review automation tool for FABER workflows that runs test suites, checks code quality, and makes GO/NO-GO decisions to control build-evaluate loops. It provides structured feedback with specific failure details for retry cycles.
refactor-git-plan
Provides concrete Git strategies for safe refactoring: branch naming patterns, commit granularity rules, message templates, and recovery procedures. Focuses on making code changes reversible and reviewable through disciplined version control practices.
ux-flow-diagram
Creates ASCII diagrams for user flows and screen transitions. Defines symbols for screens, actions, decisions, and connections. Useful for documenting navigation paths and conditional branching in early design phases.
code-review
Enforces strict code review protocols with three core practices: receiving feedback without performative agreement, requesting reviews via subagent, and requiring verification evidence before completion claims. Provides concrete decision trees and response patterns.
lsp-setup
Automates detection, installation, and configuration of Language Server Protocol (LSP) servers for multiple programming languages. Prioritizes official Claude plugins, provides installation commands for 20+ languages, and enables LSP operations like go-to-definition and find-references directly within Claude Code.
healthcheck
Host security hardening and risk-tolerance configuration for OpenClaw deployments. Use when a user asks for security audits, firewall/SSH/update hardening, risk posture, exposure review, OpenClaw cron scheduling for periodic checks, or version status checks on a machine running OpenClaw (laptop, workstation, Pi, VPS).
django-verification
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
springboot-tdd
Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).