{"data":{"slug":"foryourhealth111-pixel-vibe-skills","name":"Vibe-Skills","tagline":"all-in-one AI skills package for upgrading AI agent functionality","github_url":"https://github.com/foryourhealth111-pixel/Vibe-Skills","owner":"foryourhealth111-pixel","repo":"Vibe-Skills","owner_avatar_url":"https://avatars.githubusercontent.com/u/251585801?v=4","primary_language":"Python","stars":3366,"forks":291,"topics":["agent-framework","agent-skills","agentic-coding","ai-agents","ai-scientist","ai-skills","ai-workflow","automation","claude-code","codex","context-engineering","developer-tools","dsh-plugin","llm","multi-agent","prompt-engineering","skills","vibe-coding","vibecoding","workflow-automation"],"archived":false,"github_pushed_at":"2026-08-31T13:52:09+00:00","maintenance_label":"Active","stars_delta_30d":864,"url":"https://www.graphcanon.com/tools/foryourhealth111-pixel-vibe-skills","markdown_url":"https://www.graphcanon.com/tools/foryourhealth111-pixel-vibe-skills.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/foryourhealth111-pixel-vibe-skills","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=foryourhealth111-pixel-vibe-skills","description":"Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.","homepage_url":null,"license":"Apache-2.0","open_issues":42,"watchers":86,"ai_summary":"Vibe-Skills provides expert-level capabilities and context management to enhance any AI agent's performance by eliminating tool fragmentation.","readme_excerpt":"
\n Mean verifier reward: +21.12 pp \n Total tokens: -29.6% · Tool calls: -33.1%\n
\n\n**SkillsBench** is a benchmark designed to evaluate whether AI agents can effectively use Skills to complete professional tasks across diverse domains. Its purpose is to measure how much a model’s ability to solve complex real-world tasks improves when it is equipped with specialized Skills.\n\nTo evaluate performance in production-like environments where a large number of Skills are installed simultaneously, we adapted SkillsBench into a more realistic **large-scale multi-Skill setting**. In the original SkillsBench setup, each task is provided only with the specialized Skill associated with that task. In our modified setting, every task is evaluated in a global environment containing all **195 specialized Skills**, while all other experimental conditions remain unchanged. This setting is intended to assess whether an agent can autonomously discover, select, and orchestrate the relevant Skills from a large installed Skill pool, and organize them into an effective workflow for completing complex tasks.\n\n**vibeskills v4.1.0** was benchmarked on **SkillsBench** (https://www.skillsbench.ai/) using **DeepSeekV4Flash-VE** and **OpenHands** as the baseline evaluation setup. Compared with the baseline without vibeskills, vibeskills increased the **average task score by 21.12%**, while reducing **token consumption by 29.6%** and **tool calls by 33.1%**.\n\n\n
Resource use: 491.122M to 345.756M total tokens, with tool calls reduced from 9,954 to 6,664.
\n\nAnalysis of the","github_created_at":"2026-02-22T13:51:44+00:00","created_at":"2026-07-11T11:58:42.446533+00:00","updated_at":"2026-09-20T06:55:12.332979+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"}],"tags":[{"slug":"agent-skills","name":"agent-skills"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"context-engineering","name":"context-engineering"},{"slug":"multi-agent","name":"multi-agent"}],"trust":{"provenance":{"is_fork":false,"github_id":1164005541,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T06:55:09.626Z","maintenance":{"label":"Active","score":82,"methodology":"github_public_v1","releases_90d":3,"days_since_push":19,"last_release_at":"2026-08-31T14:26:19Z","stars_delta_30d":864,"open_issues_delta_30d":27},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:58:43.635Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T06:55:10.940Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T06:55:10.940Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-20T06:55:10.940Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"The base package is free for use and modification with commercial rights due to its open-source nature under Apache-2.0; premium services or support might come at a cost."},"requirements":{"notes":["Only requires Python for operation, making it accessible across different operating systems."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"when_to_use":["When aiming to integrate expert-level functionalities into an AI agent with minimal setup effort","For developers seeking a cohesive package that simplifies managing the various elements typically found as separate modules or packages"],"when_not_to_use":["If requiring highly specialized tools for niche cases where Vibe-Skills does not offer comprehensive coverage or customization options specific to those needs","When there is an existing integration structure that would be complicated by introducing a broad package like Vibe-Skills, thus favoring finely tailored and isolated component implementations"],"source":"enrich:decision_facts","observed_at":"2026-07-17T00:03:43.545Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - The base package is free for use and modification with commercial rights due to its open-source nature under Apache-2.0; premium services or support might come at a cost."},{"label":"Requirements","value":"Only requires Python for operation, making it accessible across different operating systems."},{"label":"Adopt for","value":"Vibe-Skills equips AI agents with advanced capabilities and context management in one package, reducing reliance on multiple fragmented tools."},{"label":"License detail","value":"Vibe-Skills is distributed under the Apache-2.0 license."}]}}
![\"VibeSkills](\"./logo.png\"){kind=logo}
\n\n![\"VibeSkills\"](\"./docs/assets/readme-wordmark-light.svg\")
\n ![\"VibeSkills](\"./docs/assets/readme-tagline-en-dark.svg\")
\n![\"Install](\"./docs/assets/install-cta-en-light.svg\")
\n ![\"VibeSkills\"](\"./docs/assets/readme-wordmark-dark.svg\")
\n ![\"SkillsBench](\"./docs/assets/skillsbench-task-outcomes.png\")
\n \n![\"SkillsBench](\"./docs/assets/skillsbench-resource-use.png\")
\n \n