correct
Find the mistakes agents keep repeating in this repo and make each one impossible.
Skill by FireTheDevil
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/firethedevil-correct
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
correct- Description
- Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /skill:correct.
- License
- MIT
- Instructions
- 30 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Correct The operator keeps correcting agents in this repo for the same mistakes. Change the repo so the next agent can't 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. Invoke explicitly with /skill:correct. This skill grants no write, commit, CI, or instruction-file authority. A read-only role returns mistake classes and recommendations only. Make changes, commits, CI runs or configuration edits, and agent-rule edits only when the assignment authorizes each action. If history or CI evidence is unavailable, report the gap instead of claiming proof. ## Find the mistake classes First, 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 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. 2. **Enforce it with types so the bad state can't be written.** If bad code still compiles, add a lint or CI check whose error names the file, type, or function to use instead. If the pattern is already common, fail only when a change adds more. 3. **Test the behavior.** Fix or delete any test that still passes when the behavior it checks breaks, or that fails when only the internals change. 4. **Write docs or agent rules last, only for judgment calls.** Nothing fails when an agent skips them. ## Fix and prove Then fix the most frequent classes within the authorized scope. When commits are authorized, use one commit per class. Prove each new check fails on a real past mistake. Run the same command locally and in CI when authorized and available. Otherwise name the missing CI proof. Exceptions go on the offending line with a reason, an expiry date, and a human's approval. ## Keep the rule table When instruction-file edits are authorized, keep a table in the agent instruction file that pairs each rule with what enforces it. When the operator corrects you, fix the mistake and add the rule. If the rule was already there and nothing enforces it, that's a repeat, so fix it at the highest level in the same change. Drop a rule once its mistake can't happen. **Reply:** each class with its evidence, the level you picked, and why a higher level didn't work.
From FireTheDevil/pi-pstack-herdsman, MIT.
More from FireTheDevil/pi-pstack-herdsman
- 0.606score
poteto-help
FireTheDevil
Answer questions about Pi pstack setup, workflow selection, and prompt wording without starting the work.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
ketchup
FireTheDevil
Catch up on what changed in this chat in plain words and small evidence-backed visuals, with concise human decisions.
SkillAFreshness: A★ 3Claude Code +9 - 0.581score
interrogate
FireTheDevil
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: A★ 3Claude Code +9 - 0.581score
how
FireTheDevil
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
automate-me
FireTheDevil
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how…
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
benchmark-checklist
FireTheDevil
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
SkillAFreshness: A★ 3Claude Code +9 - 0.578score
no-comments
FireTheDevil
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: A★ 3Claude Code +9 - 0.576score
blast-radius
FireTheDevil
Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of…
SkillAFreshness: A★ 3Claude Code +9 - 0.576score
figure-it-out
FireTheDevil
Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work reviewed after stepping away.
SkillAFreshness: A★ 3Claude Code +9 - 0.568score
in-your-own-words
FireTheDevil
Restate the user's goals and the problem they are trying to solve.
SkillAFreshness: A★ 3Claude Code +9
Signals
- Stars
- 3
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 4, 2026 (25 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.643score
correct
dsebban
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: A★ 68Claude Code +9 - 0.337score
correct
benkraus
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: A★ 1Claude Code +9 - 0.324score
correct
qapquiz
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: AClaude Code +9 - 0.324score
correct
slappcard
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: AClaude Code +9
More from FireTheDevil
- 0.606score
poteto-help
FireTheDevil
Answer questions about Pi pstack setup, workflow selection, and prompt wording without starting the work.
SkillAFreshness: A★ 3Claude Code +9 - 0.601score
ketchup
FireTheDevil
Catch up on what changed in this chat in plain words and small evidence-backed visuals, with concise human decisions.
SkillAFreshness: A★ 3Claude Code +9 - 0.581score
interrogate
FireTheDevil
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: A★ 3Claude Code +9 - 0.581score
how
FireTheDevil
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
automate-me
FireTheDevil
Use for "automate me", "create/update/refresh my -mode skill", "turn/capture my preferences or working style into a skill", or wanting agents to follow how…
SkillAFreshness: A★ 3Claude Code +9 - 0.579score
benchmark-checklist
FireTheDevil
Vet a perf measurement (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
SkillAFreshness: A★ 3Claude Code +9
Cite this page
correct skill. Agent Mart. https://agentmart.dev/skills/firethedevil-correct (last updated 2026-10-24)