correct
Find the mistakes agents keep repeating in this repo and make each one impossible.
Skill by hidenobunagai
Chalk Labs
Need help deploying correct?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/hidenobunagai-correct-3b5f0f
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 /correct.
- License
- MIT
- Instructions
- 28 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. ## 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 now, one commit each. Prove each new check fails on a real past mistake. Run the same command locally and in CI. Exceptions go on the offending line with a reason, an expiry date, and a human's approval. ## Keep the rule table Last, 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 hidenobunagai/agy-pstack, MIT.
More from hidenobunagai/agy-pstack
- 0.520score
architect
hidenobunagai
Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in.
SkillAFreshness: AClaude Code +9 - 0.520score
create-verification-skill
hidenobunagai
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: AClaude Code +9 - 0.520score
how
hidenobunagai
Use for "how does X work", code walkthroughs before changing something, and placement / ownership / layering questions ("where should this live", "which…
SkillAFreshness: AClaude Code +9 - 0.520score
interrogate
hidenobunagai
Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".
SkillAFreshness: AClaude Code +9 - 0.520score
poteto-mode
hidenobunagai
poteto's agent style for concise, detailed responses, deliberate subagents, unslopped prose, simple code, and verified work.
SkillAFreshness: AClaude Code +9 - 0.515score
arena
hidenobunagai
Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.
SkillAFreshness: AClaude Code +9 - 0.515score
maintain-verification-skill
hidenobunagai
Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature…
SkillAFreshness: AClaude Code +9 - 0.512score
no-comments
hidenobunagai
Spawn Comment Sicko, fix accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: AClaude Code +9 - 0.510score
principle-exhaust-the-design-space
hidenobunagai
Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 23, 2026 (8 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/hidenobunagai/agy-pstack
- 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.
- 0.599score
correct
mdsmithaustin
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: A★ 7Claude Code +9 - 0.344score
correct
philrenaud
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: A★ 2Claude Code +9 - 0.337score
correct
alexhatzo
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: A★ 1Claude Code +9 - 0.324score
correct
tanabe1478
Find the mistakes agents keep repeating in this repo and make each one impossible.
SkillAFreshness: AClaude Code +9
More from hidenobunagai
- 0.568score
architect
hidenobunagai
Sketch data shapes (grain, keys, schemas), function signatures, and the module or pipeline structure before code, then stay in the loop while implementation…
SkillAFreshness: A★ 1Claude Code +9 - 0.568score
astack-help
hidenobunagai
Help a user pick the right astack skill, analyst-mode playbook, or principle for a data analysis task, such as EDA, a metric move, a notebook, a pipeline, or…
SkillAFreshness: A★ 1Claude Code +9 - 0.563score
benchmark-checklist
hidenobunagai
Vet a runtime measurement for a query, dataframe transform, pipeline, or notebook before you report or act on it: limiter, tuning, data volume, warm vs cold…
SkillAFreshness: A★ 1Claude Code +9 - 0.563score
analyst-mode
hidenobunagai
Data analysis style for an analysis repo.
SkillAFreshness: A★ 1Claude Code +9 - 0.563score
blast-radius
hidenobunagai
Find what a change to a table, column, transform, metric, or notebook could break downstream (dashboards, saved queries, notebooks, consumers) before it…
SkillAFreshness: A★ 1Claude Code +9 - 0.560score
no-comments
hidenobunagai
Spawn the comment-critic agent on a data repo's code, notebooks, or SQL, act on its accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get correct running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
correct skill. Agent Mart. https://agentmart.dev/skills/hidenobunagai-correct-3b5f0f (last updated 2026-10-24)