Skill collection

guanyang/open-agent-hub

50 agent skills across 15 categories, read straight from the repository tree. The repo holds 107 SKILL.md files — 8 are the same skills republished elsewhere in the tree, and we count things rather than copies.

guanyang940★ across the radarProfile →
50
Skills published
15
Categories
24
Ship scripts
948
Stars on the repo
Tracked on the radar · 948★Repository facts and velocity →
AI & Agents · 9
All in category →
pdfUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting…scriptshosted-agentsThis skill should be used when designing hosted or background agent infrastructure: sandboxed execution…scriptsmulti-agent-patternsThis skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm…scriptscontext-degradationThis skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context…scriptsusing-superpowersUse when starting any conversation - establishes how to find and use skills, requiring skill invocation…bdi-mental-statesThis skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions…latent-briefingThis skill should be used when the user asks to \"share memory between agents\", \"KV cache compaction for…harness-engineeringThis skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds…replace-with-skill-name-using-hyphensUse when [describe triggering conditions, symptoms, or specific errors].
Code Review & Quality · 7
All in category →
advanced-evaluationThis skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise…scriptsevaluationThis skill should be used when building agent evaluation systems: deterministic checks, regression suites…scriptscontext-fundamentalsThis skill should be used to explain or reason about the foundational concepts of context engineering: what…scriptscontext-optimizationThis skill should be used for improving context efficiency: context budgeting, observation masking, prefix or…scriptsrequesting-code-reviewUse when completing tasks, implementing major features, or before merging to verify work meets requirementsexecuting-plansUse when you have a written implementation plan to execute in a separate session with review checkpointsreceiving-code-reviewUse when receiving code review feedback, before implementing suggestions, especially if feedback seems…
Workflow & Productivity · 4
All in category →
context-compressionThis skill should be used when long-running agent sessions need context compression, structured…scriptsfilesystem-contextThis skill should be used when agent work needs file-backed context: durable scratchpads, tool-output…scriptsmemory-systemsThis skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention…scriptsself-improvement-loopsThis skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization…
Documentation · 3
All in category →
docxUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or…scriptswriting-skillsUse when creating new skills, editing existing skills, or verifying skills work before deploymentscriptswriting-plansUse when you have a spec or requirements for a multi-step task, before touching code
Content & Marketing · 3
All in category →
pptxUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This…scriptsremotion-markupContent, animation and effects best practicesscriptsbaoyu-image-cardsGenerates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. Breaks…
Data & Analytics · 3
All in category →
xlsxUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user…scriptsui-ux-pro-maxUI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161…scriptsvercel-react-best-practicesReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when…
Testing & QA · 3
All in category →
skill-creatorCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to…scriptssystematic-debuggingUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesscriptstest-driven-developmentUse when implementing any feature or bugfix, before writing implementation code
Frontend · 3
All in category →
remotion-best-practicesBest practices and domain knowledge for building videos programmatically with Remotion (videos in…vercel-react-native-skillsReact Native and Expo best practices for building performant mobile apps. Use when building React Native…vercel-composition-patternsReact composition patterns that scale. Use when refactoring components with boolean prop proliferation…
Design & Presentation · 2
All in category →
brainstormingYou MUST use this before any creative work - creating features, building components, adding functionality, or…scriptsproject-developmentThis skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right…scripts
Security · 2
All in category →
notebooklmUse this skill to query your Google NotebookLM notebooks directly from Claude Code for source-grounded…scriptslong-horizon-promptingThis skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running…
Databases · 2
All in category →
claude-apiReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents…supabase-postgres-best-practicesPostgres best practices maintained by Supabase, for Postgres running anywhere. Load this skill BEFORE writing…
DevOps & Cloud · 1
All in category →
baoyu-imagineAI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image…scripts
Backend & API · 1
All in category →
tool-designThis skill should be used for the tool-interface layer of an agent system specifically: writing tool…scripts
Media & Video · 1
All in category →
mediabunnyMultimedia handling with the Mediabunny library
Other · 6
subagent-driven-developmentUse when executing implementation plans with independent tasks in the current sessionremotion-captionsTranscribing, displaying and animating captionsverification-before-completionUse when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires…dispatching-parallel-agentsUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesfinishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the workusing-git-worktreesUse when starting feature work that needs isolation from current workspace or before executing implementation…
For maintainers

Maintain guanyang/open-agent-hub? Drop this in your README — it shows how many of your skills are listed and updates itself.

VibeCrowd Skills badge
[![VibeCrowd Skills](https://vibecrowd.fund/api/skill-badge/guanyang--open-agent-hub)](https://vibecrowd.fund/skills/sources/guanyang--open-agent-hub)
About this collection
How many skills does guanyang/open-agent-hub publish?

50 that pass our gate — each has a real description and a SKILL.md we could read. The repository actually contains 107 SKILL.md files, but 8 of them are the same skills republished in other folders, so we count things rather than copies.

How do I install one?

Every skill page carries its own command — `npx skills add guanyang/open-agent-hub --skill <name> --agent claude-code`. Swap the agent for codex, cursor or copilot.

Keep going
All skills →
The full catalog, by category and by tool.
Open Source Radar →
The repositories these collections come from.
More from guanyang →
Everything this maker publishes.