SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-17 UTC

No new commits yet today

Open the update feed

EvoSkillsentient-agi/EvoSkill

Lets AI agents automatically score on task datasets, read verifier rewards, and iterate to generate new skills,…

No ratings yet Rate this skill
Stars1.2k
Forks132
Watchers1.2k
Open Issues21

InstallOne-line install

Unconfirmed

Whether this repository follows the Agent Skills spec (that is, whether it contains a SKILL.md) has not been verified yet. Until that is settled, clone it and use what you need:

git clone https://github.com/sentient-agi/EvoSkill.git

OverviewOverview

Key Features

Lets AI agents automatically score on task datasets, read verifier rewards, and iterate to generate new skills, turning manual skill tuning into a data-driven skill evolution loop. Key capabilities include: 1. Dataset ingestion: supports both CSV static question/answer pairs and Harbor task sources, and can batch-load tasks by directory, removing the need to manually assemble evaluation sets; 2. Execution mode switching: offers multiple execution modes and can run tasks with different Base Agents such as claude and codex, making it easy to compare model performance on the same task batch; 3. Reward reading and feedback: automatically reads reward scores from the verifier and feeds results back to the Proposer to generate the next round of skills, forming an automatic loop of run tasks, collect rewards, revise skills; 4. Skill proposal generation: the Proposer produces new skill proposals based on historical execution results and reward signals, reducing manual prompt rewriting.

RatingUser ratings

Nobody has rated this skill yet. Yours would be the first on the site — your vote becomes the initial average.

Rate this skill

Fill it in to be included in the per-role averages below.

One vote per IP,and it cannot be changed after submitting, so choose carefully the first time. No account is collected and no sign-in is required.

RepositoryRepository

Skill ID932
Data sourceGitHub
Repositorysentient-agi/EvoSkill
CategoryAI & Agent Development / Agent Training & Evaluation
Primary languagePython
LicenseApache License 2.0
Default branchmain
GitHub repository ID1172896941
Node IDR_kgDORej8rQ
Rank#635 (position within the source ranking)
Site-wide popularity rank#726 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

05001k1.5k2026-09-302026-10-112026-09-30 · 1,2352026-10-11 · 1,248
  • Now1,248
  • Previous point · 09-30 1,235
  • vs previous point +13
  • 2 data points 11 days
0501001502026-09-302026-10-112026-09-30 · 1312026-10-11 · 132
  • Now132
  • Previous point · 09-30 131
  • vs previous point +1
  • 2 data points 11 days

TimelineTimeline

Repository created2026-03-04 20:00:308 months ago
Data last updated2026-10-26 12:01:2521 days ago
Last commit2026-08-24 23:18:462 months ago

CommitLatest commit

Committed by namanvats-dev. Update Category: Bug Fixes & Stability Improvements. Commit details: Merge pull request #51 from sentient-agi/fix/opencode-structured-output-refetch. This update resolves known runtime errors and enhances system reliability.

36f6f04 namanvats-dev 2026-07-06