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

Bad

by gweslab in gweslab/cerf

Course correction when the approach of the agent is bad, either a stop without a reason or work that goes the wrong way.

MITAuto-check passed

Install Bad

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

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

GitHub CLI
$ gh skill install gweslab/cerf bad --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/bad .claude/skills/bad && 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
bad
GitHub stars
104
Token cost
~475 tokens
SKILL.md length
333 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

Course correction when the approach of the agent is bad, either a stop without a reason or work that goes the wrong way.

  • Works in 6 steps: Stop the approach. Do not finish the… → Say what you did wrong. Give each wrong… → Say how you will prevent it. For each… → …
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Bad is an agent skill from gweslab/cerf. Course correction when the approach of the agent is bad, either a stop without a reason or work that goes the wrong way.

Its SKILL.md is about 480 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Universal Windows CE Emulator - CE Runtime Foundation. The licence is MIT.

Example prompts

  • “/bad”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Stop the approach. Do not finish the step that you were on. Do not defend it.
  2. Say what you did wrong. Give each wrong action with its turn, the quoted text or the file and line, and the rule that it broke. If you…
  3. Say how you will prevent it. For each item, name the action that replaces it, for example "paste the datasheet entry before I write the…
  4. Repair the damage. If you deleted or reverted work, restore it from your own earlier Write and Edit calls. Do not ask first. Revert the…
  5. Restart from the task. Quote the task as the user gave it. Find the last concrete artifact from a tool call: a log line, a decompiled…
  6. Do that step in this reply. Then continue. Do not ask whether to continue. If a decision belongs to the user, end the reply with one…

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

Bad loads about 475 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 333 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~475

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). 333 words, ~475 tokens.

Download SKILL.mdSave it as .claude/skills/bad/SKILL.md (or your agent's skills folder).
name
bad
description
Course correction when the approach of the agent is bad, either a stop without a reason or work that goes the wrong way.

/bad - your approach is bad. Restart it.

What you are doing is bad. Either you stopped work that had a clear next step, or you continued to work the wrong way. Do these steps in this reply, in this order.

  1. Stop the approach. Do not finish the step that you were on. Do not defend it.
  2. Say what you did wrong. Give each wrong action with its turn, the quoted text or the file and line, and the rule that it broke. If you stopped, quote the sentence where you stopped. Also list each bug or rule violation in your earlier work that you did not disclose. "I lost focus" and "I made mistakes" are not items.
  3. Say how you will prevent it. For each item, name the action that replaces it, for example "paste the datasheet entry before I write the handler", "add a hook, not a list of hypotheses", or "run the next step, not a question". "I will be more careful" is not an action.
  4. Repair the damage. If you deleted or reverted work, restore it from your own earlier Write and Edit calls. Do not ask first. Revert the uncommitted code of the bad approach. If you already committed a bad change, name that commit in a question to the user.
  5. Restart from the task. Quote the task as the user gave it. Find the last concrete artifact from a tool call: a log line, a decompiled function, a hook fire, or a file that you read. Your own analysis is not an artifact. From that artifact, name the next mechanical step. The new approach must not be the old approach under a new name.
  6. Do that step in this reply. Then continue. Do not ask whether to continue. If a decision belongs to the user, end the reply with one specific question about it.

The reply has no apology, no "you're right", no option list, and no plan that waits for approval.

© 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/bad of gweslab/cerf.

Open the folder on GitHubat commit 6b8df83

Compare with similar skills

Bad 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.

Bad compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Bad this skillgweslab/cerf104—~475Automated safety check: PassMIT
Correctcursor/plugins10k3 repos~612Automated safety check: PassNone
CorrectionNxcoreAI/EverRoom3k—~290Automated safety check: PassCustom licence
Bmad Correct Courseaj-geddes/claude-code-bmad-skills487—~3.1kAutomated safety check: NotesCustom licence
Testing Course Samplesmicrosoft/ai-agents-for-beginners77k—~1.1kAutomated safety check: NotesMIT
Testing Course Samplesmicrosoft/ai-agents-for-beginners77k—~1.3kAutomated safety check: NotesMIT

Similar skills

  • Correct

    cursor/plugins

    Official

    Find the mistakes agents keep repeating in this repo and make each one impossible.

    10k GitHub starsUsed in 3 repos~612 tokens
    Auto-check passed

  • Correction

    NxcoreAI/EverRoom

    Compute Room overview corrections—citation corrections as per-claim edits and general corrections as a single proposal.

    3k GitHub stars~290 tokensUpdated today
    Research & ScienceAuto-check passed

  • Bmad Correct Course

    aj-geddes/claude-code-bmad-skills

    CROSS-PHASE mid-stream scope correction. An agent skill from aj-geddes/claude-code-bmad-skills.

    487 GitHub stars~3.1k tokensUpdated 3 mo ago
    Product & Project ManagementAuto-check: notes

  • Testing Course Samples

    microsoft/ai-agents-for-beginners

    Official

    A skill your agent uses when asked to validate, test, smoke-test, or run the course's notebook and code samples against a live Microsoft Foundry / Azure OpenAI configuration.

    77k GitHub stars~1.1k tokensUpdated 19 days ago
    Testing & QAAuto-check: notes

  • Testing Course Samples

    microsoft/ai-agents-for-beginners

    Official

    Use wen dem ask you to validate, test, smoke-test, or run di course notebook and code samples against live Microsoft Foundry / Azure OpenAI configuration.

    77k GitHub stars~1.3k tokensUpdated 19 days ago
    Testing & QAAuto-check: notes

  • Fp Either Ref

    sickn33/agentic-awesome-skills

    Quick reference for Either type. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 2 repos~655 tokens
    Auto-check passed

More from gweslab/cerf

All 10 skills in this repo

  • Cerf

    gweslab/cerf

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

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

  • 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

Questions about Bad

What does Bad do?

Course correction when the approach of the agent is bad, either a stop without a reason or work that goes the wrong way. Bad is an agent skill from gweslab/cerf. Course correction when the approach of the agent is bad, either a stop without a reason or work that goes the wrong way.

How do I install Bad in Claude Code?

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

How do I install Bad in Codex?

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

Can I use Bad 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 bad -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bad, .gemini/skills/bad, .github/skills/bad and .opencode/skills/bad in your project.

What does Bad need to run?

SKILL.md names no scripts, command-line tools or credentials: Bad is instructions for the agent only.

Does Bad 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 Bad 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 Bad use?

Bad 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 Bad use?

About 475 tokens (SKILL.md is roughly 1.9k 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 Bad?

Skills that share tags, products or a category with Bad: Correct (cursor/plugins, 10k stars), Correction (NxcoreAI/EverRoom, 3k stars), Bmad Correct Course (aj-geddes/claude-code-bmad-skills, 487 stars) and Testing Course Samples (microsoft/ai-agents-for-beginners, 77k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Bad?

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.