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

No new commits yet today

Open the update feed

skillsbenchbenchflow-ai/skillsbench

Provides a reproducible benchmark environment for AI agent skills, measuring with a unified task set whether a skill act…

No ratings yet Rate this skill
Stars1.8k
Forks371
Watchers1.8k
Open Issues115

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/benchflow-ai/skillsbench.git

OverviewOverview

Key Features

Provides a reproducible benchmark environment for AI agent skills, measuring with a unified task set whether a skill actually gets the job done. Key capabilities include: 1. Benchmark task set: ships real-world tasks such as Discord, WeChat, and Weekly sync so skills are tested in realistic workflows; 2. Containerized evaluation environment: packages runtime dependencies with Docker so the same skill yields comparable results across machines; 3. Result comparison and regression: scores different versions of a skill or different skills on a unified scale, quickly exposing quality regressions after changes.

Use Cases

pre-release acceptance of skill packages, cross-skill selection comparison, regression testing after skill iteration, troubleshooting agent workflow stability.

Target Roles

AI / Algorithm Engineer, Test / QA Engineer, Full-stack / Indie Developer, DevOps / Operations Engineer.

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 ID488
Data sourceGitHub
Repositorybenchflow-ai/skillsbench
CategoryAI & Agent Skills / Skill Benchmarking & Evaluation
Primary languagePDDL
LicenseApache License 2.0
Default branchmain
GitHub repository ID1124479538
Node IDR_kgDOQwYyMg
Rank#478 (position within the source ranking)
Site-wide popularity rank#559 (computed live from Stars, across all 5833 entries)

GrowthStar / Fork growth

One snapshot per day, tracking how Stars and Forks changed

05001k1.5k2k2026-09-292026-10-112026-09-29 · 1,8232026-10-11 · 1,837
  • Now1,837
  • Previous point · 09-29 1,823
  • vs previous point +14
  • 2 data points 12 days
01002003004002026-09-292026-10-112026-09-29 · 3702026-10-11 · 371
  • Now371
  • Previous point · 09-29 370
  • vs previous point +1
  • 2 data points 12 days

TimelineTimeline

Repository created2025-12-29 05:04:5710 months ago
Data last updated2026-10-26 11:58:5223 days ago
Last commit2026-07-23 19:09:353 months ago

CommitLatest commit

Committed by bingran-you. Update Category: Refactoring & Structural Improvements. Commit details: Rename task metadata sections to sandbox (#1037). This update restructures internal code for better maintainability, without behavior changes.

9a1f4dd bingran-you 2026-07-23