Repository
evo-hq/evo agent skills
- skills
- 7
- GitHub stars
- 1.5k
GitHub description: “turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.”
- Stars
- 1,466 (115 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Apr 2026
- Homepage
- evo-hq.com
- Source
- github.com/evo-hq/evo
- agent-skills
- autonomous-agents
- autoresearch
- claude-code
- code-optimization
- codex
- evolutionary-algorithms
- llm-agents
Install all skills
npx skills add evo-hq/evoAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in evo-hq/evo, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.Discover Initialize evo for the current repository by exploring the codebase, proposing unexplored optimization dimensions, constructing the benchmark inside a baseline worktree, and running the first… | evo-hq/ | 1.5k | — | ~12k | Automated safety check: Notes | Apache-2.0 | 3 days ago |
| 2 | 2.Report Read-only evo run reporting. An agent skill from evo-hq/evo. | evo-hq/ | 1.5k | 1 repo | ~1k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 3 | This skill should be used when picking or diagnosing a training move (SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF), or when the user mentions fine-tuning, post-training, training recipe… | evo-hq/ | 1.5k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 4 | Non-user-invocable provider/setup reference for evo backend switching, prerequisite checks, and auth/install guidance. | evo-hq/ | 1.5k | 1 repo | ~1k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 5 | 5.Ship Land the winning experiment from an evo run as a clean, mergeable change -- open a PR when the repo has a remote, otherwise merge into the working branch. | evo-hq/ | 1.5k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
| 6 | 6.Subagent Protocol that evo optimization subagents follow when dispatched from /optimize. | evo-hq/ | 1.5k | 1 repo | ~7.1k | Automated safety check: Notes | Apache-2.0 | 3 days ago |
| 7 | 7.Optimize Drive structured autoresearch iteration after evo:discover and the baseline commit. | evo-hq/ | 1.5k | — | ~13k | Automated safety check: Pass | Apache-2.0 | 3 days ago |
Questions, answered from the data.
What is the best skill in evo-hq/evo?
Discover from evo-hq/evo ranks first of the 7 skills in evo-hq/evo listed here, with the highest score: its repository has 1.5k GitHub stars, its SKILL.md loads about 12k tokens and it has informational notes only in the automated safety check. Next come Report and Finetuning.
Are the skills in evo-hq/evo official?
None yet. All 7 skills in evo-hq/evo 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 evo-hq/evo?
Run npx skills add evo-hq/evo 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.