Skip to content
Back to search

skills-vote

SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/memtensor--skills-vote/badge.svg)](/listings/memtensor--skills-vote)

HTML

<a href="/listings/memtensor--skills-vote"><img src="/api/listings/memtensor--skills-vote/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

| Integration | Best for | Requires | |:------------------ |:---------------------------------------------------------------------------------------------------------- |:----------------------------------------------------- | | `skills-vote` | Using the hosted SkillsVote service for cloud-based skill recommendation and attribution-grounded feedback. | `SKILLS_VOTE_API_KEY` | | `skills-vote-local` | Recommending skills from a local or private `SKILL.md` library without relying on the hosted index. | Local config; no SkillsVote API key for agentic search |

Option 1: Install the Hosted Skill

Use this integration when you want agents to retrieve skills from the hosted SkillsVote service and submit post-task feedback for attribution.

πŸ€– Agent Setup Prompt

Supercharge your agents (Codex, Claude Code, OpenClaw) by integrating SkillsVote directly! Just drop this prompt into your agent:

Install the `skills-vote` skill following https://raw.githubusercontent.com/MemTensor/skills-vote/main/integration/skills/INSTALL.md

Use the following values: 
- `SKILLS_VOTE_API_KEY`: "YOUR_API_KEY"
- `GH_TOKEN`: "YOUR_GITHUB_TOKEN"

πŸ”§ Manual Setup Alternative

Are you a CLI warrior? Set it up manually based on your OS:

*Windows PowerShell*

[Environment]::SetEnvironmentVariable("SKILLS_VOTE_API_KEY", "YOUR_API_KEY", "User")
npx skills add MemTensor/skills-vote --skill skills-vote

*MacOS/linux (Bash/Zsh)*

# For zsh, use ~/.zshrc instead
echo 'export SKILLS_VOTE_API_KEY="YOUR_API_KEY"' >> ~/.bashrc && source ~/.bashrc
npx skills add MemTensor/skills-vote --skill skills-vote

> [!note] > Don't forget to replace `YOUR_API_KEY` with your actual key!

Option 2: Install the Local-first Skill

Use this integration when your skills are stored in a local or private `SKILL.md` library and you want recommendation without the hosted index.

πŸ€– Agent Setup Prompt

Install the `skills-vote-local` skill following https://raw.githubusercontent.com/MemTensor/skills-vote/main/integration/skills/INSTALL.md

πŸ”§ Manual Setup Alternative

npx skills add MemTensor/skills-vote --skill skills-vote-local

After installation, open the installed skill root and configure `configs/config.yaml`. See [Install SkillsVote Skills](integration/skills/INSTALL.md) for the full configuration flow.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md Β· README Β· 165 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <div align="center">
  2. <h1>SkillsVote</h1>
  3. <p><strong>Lifecycle Governance of Agent Skills: From Collection and Recommendation to Evolution</strong></p>
  4. <p><em>Route skills just in time, learn from task execution, and evolve reusable skill libraries through attribution-grounded feedback.</em></p>
  5. <p>Powered by <a href="https://memos.openmem.net/"><b>MemTensor</b></a></p>
  6. </div>
  7. <p align="center">
  8. <a href="https://arxiv.org/abs/2605.18401">
  9. <img alt="arXiv" src="https://img.shields.io/badge/arXiv-2605.18401-b31b1b?style=for-the-badge&logo=arxiv&logoColor=white">
  10. </a>
  11. <a href="https://skills.vote">
  12. <img alt="Website" src="https://img.shields.io/badge/Website-skills.vote-blue?style=for-the-badge&logo=google-chrome">
  13. </a>
  14. <a href="https://mp.weixin.qq.com/s/fA4DbNnCVbsToOt886VcfQ">
  15. <img alt="WeChat Blog" src="https://img.shields.io/badge/WeChat-Blog_Post-07C160?style=for-the-badge&logo=wechat&logoColor=white">
  16. </a>
  17. <a href="http://xhslink.com/o/9c53b8USOxK">
  18. <img alt="rednote" src="https://img.shields.io/badge/rednote-Post-FF2442?style=for-the-badge">
  19. </a>
  20. <a href="https://opensource.org/license/mit/">
  21. <img alt="License" src="https://img.shields.io/badge/License-MIT-green?style=for-the-badge&logo=opensourceinitiative&logoColor=white">
  22. </a>
  23. <a href="#quick-start">
  24. <img alt="Quick Start" src="https://img.shields.io/badge/Quick_Start-Ready_To_Go-yellow?style=for-the-badge&logo=rocket">
  25. </a>
  26. </p>
  27. <div align="center">
  28. <img src="assets/pipeline.png" width="90%">
  29. </div>
  30. ## 🧭 What SkillsVote Governs
  31. Agent skills are becoming a reusable execution layer for coding agents, research agents, and workflow agents. SkillsVote starts from this large-scale setting: we have discovered over πŸ”₯ **1.68M** `SKILL.md` files from open-source GitHub repositories, including over πŸ’Ž **790K** format-valid skills verified with the official Anthropic skill validator, making SkillsVote the world's largest open agent skill library 🌍.
  32. At this scale, skill management is no longer about manually maintaining a short curated list. Agents face three linked problems: which skills to load before a task, how to tell whether a skill actually helped during execution, and how to update the library without accumulating noisy or unverified experience.
  33. SkillsVote treats skills as lifecycle-managed artifacts. It connects collection, profiling, just-in-time recommendation, trajectory-based attribution, and feedback-driven evolution into one loop:
  34. 1. **Collect and profile skills** from open-source or private skill libraries.
  35. 2. **Recommend relevant skills** before task execution, instead of loading a large static skill list.
  36. 3. **Attribute task outcomes** after execution using trajectories, skill usage, and verifier signals.
  37. 4. **Evolve the skill library** by updating or creating reusable skills from grounded, attributed feedback.
  38. ## πŸ“° Latest News
  39. - πŸ“„ **[2026-05-19] Technical Report.** We released the SkillsVote technical report on arXiv: [arXiv:2605.18401](https://arxiv.org/abs/2605.18401).
  40. - 🧭 **[2026-05-18] Local Skill Integration.** We released the first version of `skills-vote-local`, enabling local/private skill recommendation with configurable retrieval strategies.
  41. - πŸŒ… **[2026-04-09] Special Share.** Core contributor's share on [Linux.do](https://linux.do).
  42. - πŸ“£ **[2026-04-08] Social Launch.** Our launch announcement is now live on [WeChat Blog](https://mp.weixin.qq.com/s/fA4DbNnCVbsToOt886VcfQ) and [rednote](http://xhslink.com/o/9c53b8USOxK).
  43. - πŸš€ **[2026-04-03] Launch Day!** Published the very first open-source release of our recommendation and evaluation demos.
  44. ## πŸ—ΊοΈ Roadmap: Towards the Full Skill Lifecycle
  45. SkillsVote is being open-sourced in stages to support transparent research on agent skill collection, recommendation, attribution, and evolution.
  46. - [x] **Skill profiling and preprocessing.** Analyze skill runtime requirements, dependencies, quality, and verifiability.
  47. - [x] **Benchmark evaluation scripts.** Release scripts and configs for reproducing the main experiments reported in our paper.
  48. - [x] **Hosted SkillsVote skill integration.** Release the `skills-vote` agent skill that connects agents to the hosted SkillsVote service for cloud-based recommendation and attribution-grounded feedback.
  49. - [x] **Local SkillsVote recommendation integration.** Release `skills-vote-local` with configurable local/private skill recommendation strategies, including agentic search and vector search.
  50. - [ ] **Local SkillsVote attribution and evolution integration.** Extend `skills-vote-local` with attribution-grounded feedback and local skill library evolution.
  51. - [ ] **Main experiment trajectories and results.** Release benchmark trajectories and aggregated results to support inspection and reproduction of the reported experiments.
  52. ## πŸ“Š Evaluation Results
  53. SkillsVote is evaluated on agentic coding and terminal challenge benchmarks, including **Terminal-Bench Pro**, **Terminal-Bench 2.0**, and **SWE-Bench Pro**.
  54. <div align="center">
  55. <img src="assets/main_results.svg" width="100%">
  56. <img src="assets/main_results_tables.png" width="100%">
  57. </div>
  58. The results show that just-in-time skill recommendation and feedback-driven evolution improve agent performance on long-horizon tasks. Detailed reproduction instructions, benchmark setup configs, and scripts are documented in [`docs/experiment.md`](docs/experiment.md).
  59. ## πŸš€ Quick Start
  60. | Integration | Best for | Requires |
  61. |:------------------ |:---------------------------------------------------------------------------------------------------------- |:----------------------------------------------------- |
  62. | `skills-vote` | Using the hosted SkillsVote service for cloud-based skill recommendation and attribution-grounded feedback. | `SKILLS_VOTE_API_KEY` |
  63. | `skills-vote-local` | Recommending skills from a local or private `SKILL.md` library without relying on the hosted index. | Local config; no SkillsVote API key for agentic search |
  64. ### Option 1: Install the Hosted Skill
  65. Use this integration when you want agents to retrieve skills from the hosted SkillsVote service and submit post-task feedback for attribution.
  66. #### πŸ€– Agent Setup Prompt
  67. Supercharge your agents (Codex, Claude Code, OpenClaw) by integrating SkillsVote directly! Just drop this prompt into your agent:
  68. ```markdown
  69. Install the `skills-vote` skill following https://raw.githubusercontent.com/MemTensor/skills-vote/main/integration/skills/INSTALL.md
  70. Use the following values:
  71. - `SKILLS_VOTE_API_KEY`: "YOUR_API_KEY"
  72. - `GH_TOKEN`: "YOUR_GITHUB_TOKEN"
  73. ```
  74. #### πŸ”§ Manual Setup Alternative
  75. Are you a CLI warrior? Set it up manually based on your OS:
  76. *Windows PowerShell*
  77. ```powershell
  78. [Environment]::SetEnvironmentVariable("SKILLS_VOTE_API_KEY", "YOUR_API_KEY", "User")
  79. npx skills add MemTensor/skills-vote --skill skills-vote
  80. ```
  81. *MacOS/linux (Bash/Zsh)*
  82. ```bash
  83. # For zsh, use ~/.zshrc instead
  84. echo 'export SKILLS_VOTE_API_KEY="YOUR_API_KEY"' >> ~/.bashrc && source ~/.bashrc
  85. npx skills add MemTensor/skills-vote --skill skills-vote
  86. ```
  87. > [!note]
  88. > Don't forget to replace `YOUR_API_KEY` with your actual key!
  89. ### Option 2: Install the Local-first Skill
  90. Use this integration when your skills are stored in a local or private `SKILL.md` library and you want recommendation without the hosted index.
  91. #### πŸ€– Agent Setup Prompt
  92. ```markdown
  93. Install the `skills-vote-local` skill following https://raw.githubusercontent.com/MemTensor/skills-vote/main/integration/skills/INSTALL.md
  94. ```
  95. #### πŸ”§ Manual Setup Alternative
  96. ```bash
  97. npx skills add MemTensor/skills-vote --skill skills-vote-local
  98. ```
  99. After installation, open the installed skill root and configure `configs/config.yaml`. See [Install SkillsVote Skills](integration/skills/INSTALL.md) for the full configuration flow.
  100. ## β™₯️ Acknowledgements
  101. SkillsVote builds on the broader agent skill and agentic benchmark ecosystem. We thank the maintainers and contributors of [Anthropic Skills](https://github.com/anthropics/skills), [Harbor](https://github.com/harbor-framework/harbor), and open-source agent skill repositories for making this research possible.
  102. ## πŸ“š Citation
  103. If you find SkillsVote useful for your research or development, please cite:
  104. ```bibtex
  105. @misc{liu2026skillsvotelifecyclegovernanceagent,
  106. title={SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution},
  107. author={Hongyi Liu and Haoyan Yang and Tao Jiang and Bo Tang and Feiyu Xiong and Zhiyu Li},
  108. year={2026},
  109. eprint={2605.18401},
  110. archivePrefix={arXiv},
  111. primaryClass={cs.CL},
  112. url={https://arxiv.org/abs/2605.18401},
  113. }
  114. ```
  115. ## πŸ“„ License
  116. This repository is licensed under the MIT License. See [LICENSE](LICENSE).
  117. <div align="center">
  118. <i>Built with ❀️ by <a href="https://memos.openmem.net/"><b>MemTensor</b></a>. Ready to vote for your skills?</i>
  119. </div>

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.