Agents Correct

Find the mistakes agents keep repeating in a repo and make each one impossible, trying architecture first, then types, lint, tests, and docs last. Use when the operator keeps correcting the same mistake, or for /agents-correct.

23 stars 1 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add jpoehnelt/skills --skill agents-correct
Manual install
git clone --depth 1 https://github.com/jpoehnelt/skills.git /tmp/skills
mkdir -p ~/.claude/skills
cp -r /tmp/skills/agents-correct ~/.claude/skills/agents-correct

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Correct

The operator keeps correcting agents for the same mistakes. Change the repo so the next agent cannot make them.

Assume every contributor is an agent that sees only the files it opened, copies the nearest example, and takes the shortest path that compiles. Design the repo so a change that looks right from one file is right for the whole repo.

Repo facts (from AGENTS.md or CLAUDE.md): the lint and check systems and where their rules and rule tests live, the suppression syntax, the test policy, and where invariants versus skill checklists belong.

## Find the mistake classes

Read recent commits, reverts, review comments, agent instruction files, and comments that explain workarounds. Group the mistakes into classes. A class counts once it has happened twice.

## Fix each class at the highest level that works

The ladder, in order: architecture, types, lint, tests, docs.

1. **Eliminate it with architecture.** Give each piece of state one owner and each task one supported way. Hide internals so the wrong import fails. Replace hand-synced lists with one source of truth. Delete old ways and dead code an agent would copy.
Read the full skill on GitHub

Details

Skill name
agents-correct
Path
agents-correct/SKILL.md
License
MIT
Repo updated
12 November 2026

FAQ

What does the Agents Correct skill do?

Find the mistakes agents keep repeating in a repo and make each one impossible, trying architecture first, then types, lint, tests, and docs last. Use when the operator keeps correcting the same mistake, or for /agents-correct.

How do I install the Agents Correct skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add jpoehnelt/skills --skill agents-correct. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Agents Correct popular?

It lives in jpoehnelt/skills, which has 23 GitHub stars and 1 forks.

Related skills

Agents Create Verification Skill

23

jpoehnelt/skills

Generate a project-local verify skill that drives the app like a user through a browser with Playwright, a CLI, or HTTP. Use for /agents-create-verification-skill, "make a verify skill for this repo", or when a project has no scripted way to prove UI, CLI, or service behavior.

AI, LLMs & Agents

Agents Reflect

23

jpoehnelt/skills

After a work session, review what went wrong and right and turn each lesson into a concrete edit to an existing skill or AGENTS.md line. Use when the user says "reflect" or /agents-reflect.

AI, LLMs & Agents

Agents Swarm

23

jpoehnelt/skills

Fan out N parallel subagent workers in one turn, aggregate their results, and report PASS, ISSUES, or BLOCKED per worker. Use for /agents-swarm, "swarm this", parallel coverage across slices, races between approaches, or broad exploration.

AI, LLMs & Agents

Agent Brush

9

ultrathink-art/agentbrush

Image editing toolkit for AI agents. Use when processing, editing, or validating images. Background removal, compositing, text overlays, resizing, format conversion, and spec validation against presets (social media, icons, thumbnails).

AI, LLMs & Agents

Zendesk

8

andmarios/zendesk-skill

Interact with Zendesk Support via CLI - search tickets, view details, analyze metrics, manage users/organizations, and update tickets. All responses are saved locally for efficient jq querying. All Zendesk content is screened for prompt injection (regex, semantic, and LLM-based) and wrapped with security markers before reaching the LLM.

AI, LLMs & Agents

Alterlab Nmc Digital Ethics

21

AlterLab-IEU/AlterLab-FC-Skills

This skill should be used when the user asks about "digital ethics", "media ethics", "AI ethics", "platform governance", "misinformation", "disinformation analysis", "act as a digital ethics advisor", "digital ethics mode", "algorithmic bias", "data privacy", "content moderation", "ethical framework", "deepfake", "surveillance", "fact-checking tools", "verification workflow", "platform audit", "ethics stress test", "algorithmic accountability", "informed consent", "digital rights", "tech regulation", or needs expertise in analyzing ethical dilemmas in digital media, AI, and platform ecosystems

AI, LLMs & AgentsIn 1 list

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.