New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Cerf

by gweslab in gweslab/cerf

List the project skills and offer the environment doctor. An agent skill from gweslab/cerf.

MITAuto-check passedDevelopment

Install Cerf

skills CLI
$ npx skills add gweslab/cerf --skill cerf -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install gweslab/cerf cerf --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/gweslab/cerf.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/cerf .claude/skills/cerf && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cerf
GitHub stars
104
Token cost
~1.2k tokens
SKILL.md length
725 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

List the project skills and offer the environment doctor. An agent skill from gweslab/cerf.

  • Works in 3 steps: print the skill index → offer the environment doctor → run the doctor
  • Development work in your project
  • SKILL.md covers Step 1 - print the skill index, Step 2 - offer the environment…, Step 3 - run the doctor and Scope and rules
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Cerf is an agent skill from gweslab/cerf. List the project skills and offer the environment doctor.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development. It works with Git. The repository describes itself as: Universal Windows CE Emulator - CE Runtime Foundation. The licence is MIT.

When your agent uses it

  • Development work in your project

Example prompts

  • “/cerf”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. print the skill index
  2. offer the environment doctor
  3. run the doctor

What it can do on your machine

Read from SKILL.md and the folder at commit 6b8df83. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cerf loads about 1.2k tokens when it runs. Until then it costs about 16 tokens; SKILL.md has 725 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~16
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from gweslab/cerf at commit 6b8df83, republished under its MIT licence (© gweslab). 725 words, ~1,194 tokens.

Download SKILL.mdSave it as .claude/skills/cerf/SKILL.md (or your agent's skills folder).
name
cerf
description
List the project skills and offer the environment doctor.

/cerf - project skill index

Print the index of the project skills. Then offer the environment doctor. Do not run the doctor unless the user agrees.

Step 1 - print the skill index

Open with a short welcome line for the CERF Claude development environment. Use one or two lines. Do not write a paragraph.

  1. List the immediate subdirectories of .claude/skills/ in the repo root. Each subdirectory is one skill.

  2. Read the name and the description from the SKILL.md of each skill.

  3. Condense each description to one short line. The descriptions in the frontmatter are long. Write one clause that gives the purpose of the skill.

  4. Print one line for each skill:

    /<name> - <one-line explanation>

Order: print /start-board-implementation first. It is the entry point for the core work of the project, which is board bring-up. Print the other skills after it, in alphabetical order by name. If /start-board-implementation is absent, print all the skills in alphabetical order.

Step 2 - offer the environment doctor

After the index, write one short line that offers the doctor. For example: "I can run the environment doctor (setup.ps1 -Check) for a health report on this clone."

Then stop. Do not run the doctor. Do not ask more questions.

Note: git does not clone .git/hooks/. core.hooksPath lives in the local .git/config, which git also does not clone. A fresh clone runs no git hooks until setup.cmd writes this configuration.

Step 3 - run the doctor

Run this step only when the user agrees.

From the repo root, run this command:

powershell -NoProfile -ExecutionPolicy Bypass -File setup.ps1 -Check

The doctor changes nothing. It prints one line for each check, with a tab between the fields: STATUS<TAB>key<TAB>detail. STATUS is OK, WARN, or FAIL. The exit code is 1 when one check or more failed.

setup.ps1 owns the list of checks. Read the output of setup.ps1. Do not test any of these conditions directly in this skill.

A FAIL has these consequences:

keyconsequence
git-repoThis directory is not a git repo. No other check has a meaning.
git-hookscore.hooksPath is not .githooks, so .githooks/pre-commit never runs.
submodulesA declared submodule is empty, so the build fails.
pythonpy -3 does not run, so every .claude/hooks/*.py hook is a silent no-op.
claude-hooks.claude/settings.json is absent or does not parse, or a hook script that it names is absent or does not compile.
vcpkgNobody ran vcpkg integrate install, so build.ps1 refuses to build.

stale-local-hooks is a WARN. core.hooksPath shadows the leftover files in .git/hooks/, so those files cannot run. But they give wrong information to the reader. Name this warning in one line. Do not dramatize it.

Show full SKILL.md (296 more words)Show less
Report the result

If every check is OK, print one short line. For example: "Environment: healthy - the git hooks and the .claude hooks are both active." Do not print the table. Name each WARN line in one line.

If one check or more failed, give the diagnosis first:

  1. Give the consequence of each failure, not the name of the key. Read the consequence from the table above. Read .githooks/pre-commit for the rules that this hook enforces.
  2. Print the failing lines.
  3. Give the fix. setup.cmd corrects git-hooks and submodules. python and vcpkg are outside the repo. For python, install the Python launcher. For vcpkg, run vcpkg integrate install from <VS install>\VC\vcpkg\vcpkg.exe. setup.cmd reports these two conditions, but it cannot correct them.
  4. If setup.cmd corrects the failures, offer to run setup.cmd. Ask one time in plain chat. If the user agrees, run it.

CAUTION: Do not run setup.cmd without agreement from the user. It writes the git configuration and it can initialize submodules.

Scope and rules

  • Print the project skills only. List the subdirectories of .claude/skills/ in the repo root. Do not list the built-in CLI commands (/help, /clear). Do not list the global skills or the user skills that are outside this directory.
  • Read the directory in this run. Never write a fixed list of skills into this file. Skills change over time, and a fixed list becomes wrong.
  • Write one line for each skill. If a description is a paragraph, give its purpose in a few words. Keep the column short.
  • If a subdirectory has no SKILL.md, or the frontmatter does not parse, print the name of the directory with (no description). Do not omit the directory.
  • Ask no questions, except the offer in Step 2 and the offer in Step 3.

© gweslab, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/cerf of gweslab/cerf.

Open the folder on GitHubat commit 6b8df83

Compare with similar skills

Cerf next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cerf compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cerf this skillgweslab/cerf104—~1.2kAutomated safety check: PassMIT
Finishing a Development Branchobra/superpowers296k5 repos~1.9kAutomated safety check: PassMIT
Code Review ChecklistshareAI-lab/learn-claude-code78k5 repos~1.1kAutomated safety check: PassMIT
Codebase Knowledge Graph Q&AEgonex-AI/Understand-Anything86k1 repos~1.2kAutomated safety check: PassMIT
Code Design Rationale Investigatorcursor/plugins10k9 repos~2.6kAutomated safety check: PassNone
Understand Diff AnalysisEgonex-AI/Understand-Anything86k1 repos~1.4kAutomated safety check: PassMIT

Similar skills

  • Finishing a Development Branch

    obra/superpowers

    Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    296k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed

  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 5 repos~1.1k tokens
    DevelopmentAuto-check passed

  • Codebase Knowledge Graph Q&A

    Egonex-AI/Understand-Anything

    Answers questions about a codebase by searching a prebuilt knowledge graph of its files, functions, classes and dependencies, not by rereading every source file.

    86k GitHub starsUsed in 1 repo~1.2k tokens
    DevelopmentAuto-check passed

  • Code Design Rationale Investigator

    cursor/plugins

    Official

    Digs into why code is shaped the way it is by checking git history, pull requests and connected tools in parallel, then reporting a cited read on the tradeoffs.

    10k GitHub starsUsed in 9 repos~2.6k tokens
    DevelopmentAuto-check passed

  • Understand Diff Analysis

    Egonex-AI/Understand-Anything

    Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.

    86k GitHub starsUsed in 1 repo~1.4k tokens
    DevelopmentAuto-check passed

  • Understand Explain

    Egonex-AI/Understand-Anything

    Gives an in-depth explanation of one file, function or module by reading the project's knowledge graph and checking that the graph is still fresh.

    86k GitHub starsUsed in 1 repo~1.3k tokens
    DevelopmentAuto-check passed

More from gweslab/cerf

All 10 skills in this repo

  • Changelog Append

    gweslab/cerf

    Add a changelog entry for a change that was just made (only user triggered, no agent self-invocation).

    104 GitHub stars~864 tokensUpdated today
    Auto-check passed

  • Commit

    gweslab/cerf

    Create a git commit with a short message that describes the diff.

    104 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

  • Start Board Implementation

    gweslab/cerf

    Start the bring-up of a new board or ROM in CERF. An agent skill from gweslab/cerf.

    104 GitHub stars~3.2k tokensUpdated today
    Auto-check passed

  • Tracking

    gweslab/cerf

    Manage the cross-session tracking document with restore, create, update, or compact (only user triggered, no agent self-invocation).

    104 GitHub stars~22k tokensUpdated today
    Auto-check passed

  • Verify

    gweslab/cerf

    Spawn a hostile reviewer that checks a claim or a diff against the project rules.

    104 GitHub stars~5.4k tokensUpdated today
    Auto-check passed

  • Verify Options

    gweslab/cerf

    Audit a list of options for bailouts and rule violations before the user picks one.

    104 GitHub stars~11k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Cerf

What does Cerf do?

List the project skills and offer the environment doctor. An agent skill from gweslab/cerf. Cerf is an agent skill from gweslab/cerf. List the project skills and offer the environment doctor.

When should I use Cerf?

Cerf fits situations like: development work in your project.

How do I install Cerf in Claude Code?

Run `npx skills add gweslab/cerf --skill cerf -a claude-code`. Or copy the skill folder (.claude/skills/cerf in gweslab/cerf) into .claude/skills/cerf in your project. Claude Code loads it when a task matches its description.

How do I install Cerf in Codex?

Run `npx skills add gweslab/cerf --skill cerf -a codex`. Or copy the skill folder (.claude/skills/cerf in gweslab/cerf) into .agents/skills/cerf in your project. Codex loads it when a task matches its description.

Can I use Cerf in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add gweslab/cerf --skill cerf -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cerf, .gemini/skills/cerf, .github/skills/cerf and .opencode/skills/cerf in your project.

What does Cerf need to run?

SKILL.md names no scripts, command-line tools or credentials: Cerf is instructions for the agent only. Our summary lists: Python 3.

Does Cerf access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cerf safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cerf use?

Cerf is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cerf use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cerf?

Skills that share tags, products or a category with Cerf: Finishing a Development Branch (obra/superpowers, 296k stars), Code Review Checklist (shareAI-lab/learn-claude-code, 78k stars), Codebase Knowledge Graph Q&A (Egonex-AI/Understand-Anything, 86k stars) and Code Design Rationale Investigator (cursor/plugins, 10k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cerf?

gweslab (a GitHub organization) maintains it in gweslab/cerf, which has 104 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 7, 2026.

Source: gweslab/cerf on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.