Repository
guanyang/open-agent-hub agent skills
- skills
- 26
- GitHub stars
- 977
GitHub description: “A lightweight, zero-dependency CLI tool to manage and activate capabilities for AI coding assistants (such as Claude Code, Cursor, Trae, etc.).”
- Stars
- 977 (164 forks)
- Licence
- MIT
- Last push
- Oct 2026
- Created
- Jan 2026
- ai-skills
- workflows
- skills
- anthropic-skills
- planning
- superpowers
- context-engineering
- ui-ux-design
- ai-agents
- claude-code
- full-stack
- agents
- cli-tool
Install all skills
npx skills add guanyang/open-agent-hubAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in guanyang/open-agent-hub, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve… | guanyang/ | 977 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | yesterday |
| 2 | This skill should be used to explain or reason about the foundational concepts of context engineering: what context is, the anatomy of a context window, how attention mechanics work, the U-shaped… | guanyang/ | 977 | 2 repos | ~4.2k | Automated safety check: Pass | MIT | yesterday |
| 3 | This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and… | guanyang/ | 977 | 2 repos | ~4.2k | Automated safety check: Pass | MIT | yesterday |
| 4 | This skill should be used when designing multi-agent systems that need context isolation, supervisor or swarm coordination, explicit handoffs, parallel execution, or a decision on whether multiple… | guanyang/ | 977 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | yesterday |
| 5 | This skill should be used for project-level decisions about LLM-powered systems: whether an LLM is the right primitive for the task at hand, the shape of a multi-stage batch or agent pipeline, token… | guanyang/ | 977 | 2 repos | ~4.7k | Automated safety check: Pass | MIT | yesterday |
| 6 | This skill should be used for the tool-interface layer of an agent system specifically: writing tool descriptions agents can route on, designing tool schemas and response formats, naming… | guanyang/ | 977 | 2 repos | ~5k | Automated safety check: Pass | MIT | yesterday |
| 7 | This skill should be used when agent work needs file-backed context: durable scratchpads, tool-output offloading, just-in-time discovery, cross-agent handoff files, filesystem memory, or cleanup… | guanyang/ | 977 | 1 repo | ~4k | Automated safety check: Pass | MIT | yesterday |
| 8 | This skill should be used when designing hosted or background agent infrastructure: sandboxed execution, remote coding environments, warm pools, session persistence, multiplayer collaboration… | guanyang/ | 977 | 1 repo | ~4.4k | Automated safety check: Pass | MIT | yesterday |
| 9 | This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated… | guanyang/ | 977 | 2 repos | ~4.2k | Automated safety check: Pass | MIT | yesterday |
| 10 | This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions, RDF-to-belief transformations, rational agency traces, cognitive agents, BDI ontologies… | guanyang/ | 977 | 2 repos | ~4.4k | Automated safety check: Pass | MIT | yesterday |
| 11 | AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs. | guanyang/ | 977 | — | ~4.6k | Automated safety check: Notes | MIT | yesterday |
| 12 | This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context poisoning, context clash, context confusion, attention-pattern issues, and agent… | guanyang/ | 977 | 2 repos | ~4.8k | Automated safety check: Pass | MIT | yesterday |
| 13 | This skill should be used for improving context efficiency: context budgeting, observation masking, prefix or KV-cache strategy, partitioning, token-cost reduction, retrieval scoping, and extending… | guanyang/ | 977 | 2 repos | ~4k | Automated safety check: Pass | MIT | yesterday |
| 14 | This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and… | guanyang/ | 977 | 2 repos | ~4.1k | Automated safety check: Pass | MIT | yesterday |
| 15 | Persistent file-based planning for multi-step AI-agent work. | guanyang/ | 977 | 2 repos | ~9.7k | Automated safety check: Notes | MIT | yesterday |
| 16 | This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens"… | guanyang/ | 977 | 1 repo | ~3.3k | Automated safety check: Pass | MIT | yesterday |
| 17 | This skill should be used when designing autonomous agent harnesses: research loops, evaluation scaffolds, locked and editable surfaces, durable logs, novelty gates, pruning, rollback, PR… | guanyang/ | 977 | 1 repo | ~2.9k | Automated safety check: Pass | MIT | yesterday |
| 18 | This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal… | guanyang/ | 977 | 1 repo | ~6.4k | Automated safety check: Pass | MIT | yesterday |
| 19 | This skill should be used when the harness, scaffold, workflow, or optimizer itself is the optimization target: recursive self-improvement (RSI) loops, meta-harnesses, self-improving harnesses that… | guanyang/ | 977 | 1 repo | ~5.6k | Automated safety check: Pass | MIT | yesterday |
| 20 | This skill should be used when a model gets read-write control over its own live context window instead of a harness-scheduled compaction policy: the context exposed as an editable file the model… | guanyang/ | 977 | 1 repo | ~6k | Automated safety check: Pass | MIT | yesterday |
| 21 | Best practices for writing Remotion React Markup. An agent skill from guanyang/open-agent-hub. | guanyang/ | 977 | 1 repo | ~2.4k | Automated safety check: Pass | MIT | yesterday |
| 22 | 22.Mediabunny Multimedia handling with the Mediabunny library. An agent skill from guanyang/open-agent-hub. | guanyang/ | 977 | 2 repos | ~191 | Automated safety check: Pass | MIT | yesterday |
| 23 | Generates infographic image card series with 12 visual styles, 8 layouts, and 3 color palettes. | guanyang/ | 977 | — | ~6.7k | Automated safety check: Pass | MIT | yesterday |
| 24 | Best practices and domain knowledge for building videos programmatically with Remotion (videos in React/TypeScript, rendered to MP4). | guanyang/ | 977 | — | ~3.1k | Automated safety check: Pass | MIT | yesterday |
| 25 | Creating a new Remotion video | guanyang/ | 977 | 1 repo | ~353 | Automated safety check: Pass | MIT | yesterday |
| 26 | Best practices for writing Remotion animations that stay intuitive for agents and editable in Remotion Studio Visual Mode. | guanyang/ | 977 | 1 repo | ~209 | Automated safety check: Pass | MIT | yesterday |
Questions, answered from the data.
What is the best skill in guanyang/open-agent-hub?
Context Compression from guanyang/open-agent-hub ranks first of the 26 skills in guanyang/open-agent-hub listed here, with the highest score: its repository has 977 GitHub stars, 2 other GitHub owners carry a copy, its SKILL.md loads about 4.6k tokens and it passes the automated safety check with no findings. Next come Context Fundamentals and Evaluation.
Are the skills in guanyang/open-agent-hub official?
None yet. All 26 skills in guanyang/open-agent-hub listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from guanyang/open-agent-hub?
Run npx skills add guanyang/open-agent-hub in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.