Repository

openJiuwen-ai/agent-core agent skills

Every skill in the openJiuwen-ai/agent-core repository on GitHub, ranked by score, with the commands to install them.
skills
10
GitHub stars
446

GitHub description: “openJiuwen agent-core provides a complete set of SDK capabilities related to AI Agent development, running, optimization, and evolution.”

Stars
446 (126 forks)
Licence
Apache-2.0
Last push
Oct 2026
Created
Feb 2026

Install all skills

skills CLI (any agent)
npx skills add openJiuwen-ai/agent-core

Add --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).

Skills in openJiuwen-ai/agent-core, ranked

Ranked by score. Sort bymost stars,trending,newest,recently updated

Skills in openJiuwen-ai/agent-core, ranked
#SkillRepositoryStarsUsed inTokensAuto-checkLicenceUpdated
1

Static safety audit of a SKILL.md that scores five dimensions and acts as a gate: skills below the pass line do not ship, whatever else they score.

openJiuwen-ai/agent-core446—~3.5kAutomated safety check: WarnApache-2.0today
2

Runs a read-only assessment in one of two modes, a repository health check or a runtime extension gap review, and reports findings as a markdown table.

openJiuwen-ai/agent-core446—~613Automated safety check: PassApache-2.0today
3

Chinese-language rules for how an agent writes commit messages, PR descriptions, session journals, handoff issues and requests for help.

openJiuwen-ai/agent-core446—~625Automated safety check: PassApache-2.0today
4

Reference for idiomatic Python in the agent-core codebase: immutability, protocols, exception hierarchies, context managers and async patterns.

openJiuwen-ai/agent-core446—~2.1kAutomated safety check: PassApache-2.0today
5

Pytest patterns for the agent-core codebase: a red-green-refactor workflow, conftest fixtures, custom marks, monkeypatch and patch mocking, and async tests.

openJiuwen-ai/agent-core446—~2.3kAutomated safety check: PassApache-2.0today
6

A ten-category security checklist for the agent-core codebase, to run before any security-sensitive change or pull request: secrets, input validation, SQL, access control and prompt injection.

openJiuwen-ai/agent-core446—~1.7kAutomated safety check: NotesApache-2.0today
7

Formalizes agent-core's make check/type-check/test/fix pipeline into a structured 6-phase verification skill.

openJiuwen-ai/agent-core446—~818Automated safety check: PassApache-2.0today
8

实现阶段主操作手册 — 指导 agent 完成改码与局部验证,并把提交留给独立 commit phase. An agent skill from openJiuwen-ai/agent-core.

openJiuwen-ai/agent-core446—~481Automated safety check: PassApache-2.0today
9

基于 commit skill 的自主提交流程。适用于 implement 阶段在提交前规划范围并通过 bash 完成 git 提交。

openJiuwen-ai/agent-core446—~196Automated safety check: PassApache-2.0today
10

验证规范 — 定义实现阶段应满足的验证等级与通过标准

openJiuwen-ai/agent-core446—~283Automated safety check: PassApache-2.0today

Questions, answered from the data.

What is the best skill in openJiuwen-ai/agent-core?

Skill Safety Evaluator from openJiuwen-ai/agent-core ranks first of the 10 skills in openJiuwen-ai/agent-core listed here, with the highest score: its repository has 446 GitHub stars, its SKILL.md loads about 3.5k tokens and it has a warning in the automated safety check worth reviewing. Next come Repository Health and Gap Assessor and Engineering Communication Rules.

Are the skills in openJiuwen-ai/agent-core official?

None yet. All 10 skills in openJiuwen-ai/agent-core 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 openJiuwen-ai/agent-core?

Run npx skills add openJiuwen-ai/agent-core 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.