Repository
benchflow-ai/benchflow agent skills
- skills
- 8
- GitHub stars
- 353
GitHub description: “Research infra for creating RL environments, post-training, and evals.”
- Stars
- 353 (68 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Jan 2025
- Homepage
- benchflow.ai
- benchmark
- evals
Install all skills
npx skills add benchflow-ai/benchflowAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in benchflow-ai/benchflow, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | SkillsBench task authoring — walk a contributor from idea to submission-ready task following CONTRIBUTING.md and the task-implementation rubric. | benchflow-ai/ | 353 | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 2 | SkillsBench task PR review — classifies the task track (standard / research / multimodal), runs static policy checks against the track-specific rubric, benchmarks the task across oracle plus Claude… | benchflow-ai/ | 353 | — | ~4.5k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 3 | Review Benchflow or SkillsBench task-run trajectories and integration-test Benchflow code changes. | benchflow-ai/ | 353 | — | ~4k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 4 | Run agent benchmarks, create tasks, analyze results, and manage agents using BenchFlow. | benchflow-ai/ | 353 | — | ~1.9k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 5 | Operate, test, troubleshoot, and explain bench traj upload for public or trusted-direct trajectory contributions, including interactive and fully specified commands, dry runs, input validation… | benchflow-ai/ | 353 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 6 | Find a local Claude Code or Codex session, open the BenchFlow trajectory viewer, and submit it after the user reviews it. | benchflow-ai/ | 353 | — | ~1.9k | Automated safety check: Notes | Apache-2.0 | yesterday |
| 7 | Delegate complex coding tasks to a specialist model. An agent skill from benchflow-ai/benchflow. | benchflow-ai/ | 353 | — | ~225 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 8 | Incorporate feedback from an independent code reviewer to improve your solution. | benchflow-ai/ | 353 | — | ~232 | Automated safety check: Pass | Apache-2.0 | yesterday |
Questions, answered from the data.
What is the best skill in benchflow-ai/benchflow?
Task Creator from benchflow-ai/benchflow ranks first of the 8 skills in benchflow-ai/benchflow listed here, with the highest score: its repository has 353 GitHub stars, its SKILL.md loads about 4.5k tokens and it passes the automated safety check with no findings. Next come Task Review and Benchflow Experiment Review.
Are the skills in benchflow-ai/benchflow official?
None yet. All 8 skills in benchflow-ai/benchflow 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 benchflow-ai/benchflow?
Run npx skills add benchflow-ai/benchflow 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.