SkillPedia Skills Encyclopedia
中文 EN
Today's updates 2026-11-18 UTC

No new commits yet today

Open the update feed

agent-skills-evaldarkrishabh/agent-skills-eval

Provides reproducible automated evaluation for AI agent skills, turning "did this skill change make it better or worse" …

No ratings yet Rate this skill
Stars799
Forks43
Watchers799
Open Issues5

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/darkrishabh/agent-skills-eval.git

OverviewOverview

Key Features

Provides reproducible automated evaluation for AI agent skills, turning "did this skill change make it better or worse" into a quantifiable, comparable score. Key capabilities include: 1. Skill eval case definition: declares test cases and expectations per skill in evals/evals.json via fields such as skill_name, evals.id and prompt, so evaluation content is versioned together with the skill; 2. Skill manifest and metadata validation: parses the YAML frontmatter of SKILL.md and checks required fields such as name and description, catching non-compliant skills early; 3. CLI batch scoring: reads the eval set and runs it case by case through a command-line interface, emitting per-case results in JSONL for scripted statistics and regression comparison; 4. OpenAI-compatible model access: connects to any model behind an OpenAI-compatible API, enabling side-by-side comparison of different models or skill versions on the same case set.

TopicsTopics

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 ID1150
Data sourceGitHub
Repositorydarkrishabh/agent-skills-eval
CategoryAI Engineering & Agent Development / Agent Evaluation & Quality Assurance
Primary languageTypeScript
LicenseMIT License
Default branchmain
GitHub repository ID1230541272
Node IDR_kgDOSViR2A
Rank#908 (position within the source ranking)
Site-wide popularity rank#1024 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

02004006008002026-09-292026-10-112026-09-29 · 7982026-10-11 · 799
  • Now799
  • Previous point · 09-29 798
  • vs previous point +1
  • 2 data points 12 days
02040602026-09-292026-10-112026-09-29 · 432026-10-11 · 43
  • Now43
  • Previous point · 09-29 43
  • vs previous point ±0
  • 2 data points 12 days

TimelineTimeline

Repository created2026-05-06 05:10:296 months ago
Data last updated2026-10-26 12:05:5723 days ago
Last commit2026-10-07 15:39:151 months ago

CommitLatest commit

Version [latest] committed by darkrishabh. Update Category: Feature Addition & Enhancement. Commit details: Merge pull request #39 from darkrishabh/codex/shared-runtime-foundation. This update introduces new capabilities and module extensions.

f10ae2b vlatest darkrishabh 2026-09-29

Next stepsNext steps