correct
Find the mistakes that agents repeat in a repo, and make each one impossible with architecture, types, a lint, or a test.
Skill by VanTanev
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/vantanev-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
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/correct
What's inside
- Skill name
correct- Description
- Find the mistakes that agents repeat in a repo, and make each one impossible with architecture, types, a lint, or a test.
- License
- MIT
- Metadata
- opencode/autoinvoke: false
- Instructions
- 28 lines in SKILL.md · view on GitHub
Files (5)
- LICENSE
- SKILL.md
- UPSTREAM.md
- openai.yaml · agents/
- design-red-flags.md · references/
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, agent memory of past corrections, the rule table, 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. Screen the repo for each flag in [`references/design-red-flags.md`](references/design-red-flags.md). 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 would still pass if every function it calls returned nothing. 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 `docs/agents/corrections.md` 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 VanTanev/skills, MIT.
More from VanTanev/skills
- 0.570score
hillclimb
VanTanev
Improve one measured number in a loop against a target: one change, one measurement, keep or revert.
SkillAFreshness: AClaude Code +9 - 0.567score
why
VanTanev
Find why code has its shape.
SkillAFreshness: AClaude Code +9 - 0.565score
risk-first
VanTanev
Risk-first implementation: hunt the risks before code, settle each with an oracle, pin it with a discriminating check.
SkillAFreshness: AClaude Code +9 - 0.565score
benchmark-checklist
VanTanev
Vet a measured number (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
SkillAFreshness: AClaude Code +9 - 0.564score
interrogate
VanTanev
Reviewers from different model families challenge changes from independent angles.
SkillAFreshness: AClaude Code +9 - 0.564score
no-comments
VanTanev
Spawn Comment Sicko on the scoped diff, act on accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: AClaude Code +9 - 0.560score
bash
VanTanev
Write, review, or debug Bash script files in a repository.
SkillAFreshness: AClaude Code +9 - 0.558score
build-spec
VanTanev
Implement the result of /to-spec and /to-tickets in code, building each ticket risk-first.
SkillAFreshness: AClaude Code +9 - 0.556score
expert-test
VanTanev
Run the decision at hand through the best expert in its field, kill the choice that expert would reject, and state every trade-off.
SkillAFreshness: AClaude Code +9 - 0.550score
build
VanTanev
Implement a spec or tickets risk-first, then /code-review
SkillAFreshness: AClaude Code +9 - 0.541score
create-verification-skill
VanTanev
Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.
SkillAFreshness: AClaude Code +9 - 0.539score
unslop
VanTanev
Cut AI tells from any writing.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 14, 2026 (16 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/VanTanev/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from VanTanev
- 0.570score
hillclimb
VanTanev
Improve one measured number in a loop against a target: one change, one measurement, keep or revert.
SkillAFreshness: AClaude Code +9 - 0.567score
why
VanTanev
Find why code has its shape.
SkillAFreshness: AClaude Code +9 - 0.565score
benchmark-checklist
VanTanev
Vet a measured number (limiter, tuning, limits, errors, repeatability, relevance, and whether the work happened) before you report or act on it.
SkillAFreshness: AClaude Code +9 - 0.565score
risk-first
VanTanev
Risk-first implementation: hunt the risks before code, settle each with an oracle, pin it with a discriminating check.
SkillAFreshness: AClaude Code +9 - 0.564score
interrogate
VanTanev
Reviewers from different model families challenge changes from independent angles.
SkillAFreshness: AClaude Code +9 - 0.564score
no-comments
VanTanev
Spawn Comment Sicko on the scoped diff, act on accepted findings, and offer encodings for claimed constraints.
SkillAFreshness: AClaude 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/vantanev-correct (last updated 2026-10-24)