Updated 3d ago
by DeadHead04
skillEd
Test agent Skills, catch regressions, and improve with evidence. Evaluation CLI + MCP for Codex, Claude Code, and other agents; skilled-improve included.
37 GitHub stars (37)
+24 in 3 days
| Period | New stars |
|---|---|
| Oct 22 | 0 |
| Oct 23 | +2 |
| Oct 24 | +22 |
- 7 skills (7 skills found in its SKILL.md files)
- 0 forks (0 forks)
- 3d ago last update (Last updated 3d ago)
Install
Skills CLI
npx skills add DeadHead04/skillEd
Asks which skills and agents to install. Just one: npx skills add DeadHead04/skillEd --skill code-stats — add -g for every project.
Claude Code
git clone https://github.com/DeadHead04/skillEdcp -r "skillEd/examples/code-stats" ~/.claude/skills/
Copies the code-stats skill into ~/.claude/skills/ for every project (use .claude/skills/ for one project). Repeat for the other skills listed below.
Plugin
/plugin marketplace add DeadHead04/skillEd
Run inside Claude Code if the repository ships a plugin marketplace, then pick plugins from /plugin.
Skills can run code on your machine — read the SKILL.md first.
What it does
In the author's own words, from each skill's SKILL.md.
-
code-stats
Analyzes code files and reports statistics including line counts, file counts by extension, and total size. Use this skill whenever the user wants to understand the composition of a codebase - asking about "how many lines of code", "what file types exist", "code distribution", or needing a quick audit of project size and structure. Make sure to invoke this skill when users mention analyzing codeb…
examples/code-stats/SKILL.md on GitHub (opens in a new tab) -
dsh-marker-reader
Decode the marker fixture used by the DeepSeek Harness integration example.
examples/deepseek-harness/SKILL.md on GitHub (opens in a new tab) -
hello-world
Return a short greeting when the user asks to be greeted.
examples/hello-world/SKILL.md on GitHub (opens in a new tab) -
deployment-config-guide
Ask for missing deployment settings and summarize the requested configuration without deploying it.
examples/user-simulator/SKILL.md on GitHub (opens in a new tab) -
skilled-improve
Capture and review Agent Skill observations, and create, run, diagnose, or iteratively improve Skill evaluations (evals) with the skilled CLI. Use when the user asks to record explicitly attributed Skill usage or feedback; review observations or user-supplied traces/transcripts; turn an approved observation into a regression case; evaluate, test, regress, verify, fix, improve, iterate, or evolve…
skills/skilled-improve/SKILL.md on GitHub (opens in a new tab) -
code-review-helper
帮助用户进行代码审查,识别常见代码问题并给出修改建议。
skills/skilled-improve/evals/fixtures/skills/sample-no-evals/SKILL.md on GitHub (opens in a new tab) -
todo-manager
帮助用户管理待办事项,支持添加、删除、标记完成、列出任务等操作。
skills/skilled-improve/evals/fixtures/skills/sample-with-evals/SKILL.md on GitHub (opens in a new tab)
No skill matches that filter.
Review before you install
A skill is a set of instructions and scripts your agent will follow, and it can run code on your machine. Read the SKILL.md and any scripts first — this listing is not a security review.