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

No new commits yet today

Open the update feed

skill-upalibaba/skill-up

Provides configurable, reproducible automated evaluation and iterative optimization for AI skills and agents,…

No ratings yet Rate this skill
Stars1.2k
Forks99
Watchers1.2k
Open Issues25

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/alibaba/skill-up.git

OverviewOverview

Key Features

Provides configurable, reproducible automated evaluation and iterative optimization for AI skills and agents, solving the problem that skill effectiveness cannot be quantified before release and capability regressions are hard to detect after iteration. Key capabilities include: 1. Skill evaluation: measures a skill's actual behavior across multiple test cases and outputs comparable evaluation results to judge whether the skill meets expectations; 2. Agent evaluation: runs the full agent pipeline on the same cases to measure overall task completion capability and locate weaknesses in skill-agent collaboration; 3. Workspace evaluation: evaluates workspace-level configuration and runtime environment to verify skill usability in real engineering environments; 4. Skill evolution: drives iterative optimization of skill content based on evaluation results, forming an evaluate-improve-reevaluate loop; 5. Declarative eval config: defines evaluation cases, judging rules and runtime parameters via declarative configuration, reducing the cost of writing and maintaining evaluations; 6. Environment provisioning: automatically sets up the runtime environment and dependencies required for evaluation, reducing manual configuration; 7. Multi-engine support: supports integrating multiple model engines for evaluation, enabling side-by-side comparison of skill performance across engines; 8. Flexible judging: offers multiple result judging methods suitable for both open-ended and structured output scenarios; 9. Structured reports: generates structured evaluation reports for aggregated analysis and continuous tracking. 2. Use Cases: Pre-release validation of AI skills, regression testing of agent capabilities, skill iteration and optimization, multi-engine comparison evaluation, automated evaluation environment provisioning. 3. Target Roles: AI / Algorithm Engineer, Test / QA Engineer, DevOps / Operations Engineer, Full-stack / Independent Developer.

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 ID1005
Data sourceGitHub
Repositoryalibaba/skill-up
CategoryAI & Agent Skills / Skill Package Management & Tooling Framework
Primary languageGo
LicenseApache License 2.0
Default branchmain
GitHub repository ID1233753464
Node IDR_kgDOSYmVeA
Rank#668 (position within the source ranking)
Site-wide popularity rank#762 (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 · 1,1202026-10-11 · 1,174
  • Now1,174
  • Previous point · 09-30 1,120
  • vs previous point +54
  • 2 data points 11 days
02550751002026-09-302026-10-112026-09-30 · 942026-10-11 · 99
  • Now99
  • Previous point · 09-30 94
  • vs previous point +5
  • 2 data points 11 days

TimelineTimeline

Repository created2026-05-09 10:09:286 months ago
Data last updated2026-10-26 12:01:5722 days ago
Last commit2026-10-10 08:29:241 months ago

CommitLatest commit

Committed by zpzjzj. Update Category: Bug Fixes & Stability Improvements. Commit details: fix(skill-upper): preserve intent and protect regression semantics (#291). This update resolves known runtime errors and enhances system reliability.

12deb53 zpzjzj 2026-10-10

Next stepsNext steps