correct
Make a repeated agent mistake impossible with structure, types, lint or a test.
Skill by kausthubh-coder
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/kausthubh-coder-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, agent-building
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
- Make a repeated agent mistake impossible with structure, types, lint or a test. Use when I correct you for the same thing twice, or ask to stop a mistake for good (/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 kausthubh-coder/skills, MIT.
More from kausthubh-coder/skills
- 0.570score
create-verification-skill
kausthubh-coder
Set up a repo so agents can run and use the app themselves and prove a change works.
SkillAFreshness: AClaude Code +9 - 0.570score
diagnosing-bugs
kausthubh-coder
Find the real cause of a bug before fixing it.
SkillAFreshness: AClaude Code +9 - 0.567score
cloud
kausthubh-coder
Move this thread's work to my InstaBox cloud machine, or start, steer or check threads there.
SkillAFreshness: AClaude Code +9 - 0.566score
before-and-after
kausthubh-coder
Captures before/after screenshots of web pages or elements for visual comparison.
SkillAFreshness: AClaude Code +9 - 0.566score
oracle
kausthubh-coder
Run the user's agentic engineering workflow with `oracle init`, `oracle plan`, and `oracle implement`: one structured project-local `.artifacts` workspace…
SkillAFreshness: AClaude Code +9 - 0.566score
evidence-driven-testing
kausthubh-coder
Records visual proof while testing UI behavior — the agent tests the app hands-on via computer use while a screen recording with structured test/assertion…
SkillAFreshness: AClaude Code +9 - 0.565score
code-structure
kausthubh-coder
Use when multiple workflows duplicate the same operational logic, when deciding what belongs in actions vs shared services, or when refactoring repeated…
SkillAFreshness: AClaude Code +9 - 0.565score
benchmark-checklist
kausthubh-coder
Check a perf number before you report or act on it.
SkillAFreshness: AClaude Code +9 - 0.561score
create-formal-verification-skill
kausthubh-coder
Formally verify the riskiest code tests can't reach (races, retries, state machines, parsers) and leave a project skill to recheck it.
SkillAFreshness: AClaude Code +9 - 0.561score
audit-skills
kausthubh-coder
Audit how well my skills worked in my recent threads and update the skills dashboard.
SkillAFreshness: AClaude Code +9 - 0.561score
delegating
kausthubh-coder
Hand work to another agent well, whether a subagent, a T3 thread or Devin.
SkillAFreshness: AClaude Code +9 - 0.560score
cloud-pr
kausthubh-coder
Build a change in a Claude cloud thread, have Devin test the PR on real devices, loop fixes, then ship.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 20, 2026 (9 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/kausthubh-coder/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from kausthubh-coder
- 0.570score
create-verification-skill
kausthubh-coder
Set up a repo so agents can run and use the app themselves and prove a change works.
SkillAFreshness: AClaude Code +9 - 0.570score
diagnosing-bugs
kausthubh-coder
Find the real cause of a bug before fixing it.
SkillAFreshness: AClaude Code +9 - 0.567score
cloud
kausthubh-coder
Move this thread's work to my InstaBox cloud machine, or start, steer or check threads there.
SkillAFreshness: AClaude Code +9 - 0.566score
before-and-after
kausthubh-coder
Captures before/after screenshots of web pages or elements for visual comparison.
SkillAFreshness: AClaude Code +9 - 0.566score
oracle
kausthubh-coder
Run the user's agentic engineering workflow with `oracle init`, `oracle plan`, and `oracle implement`: one structured project-local `.artifacts` workspace…
SkillAFreshness: AClaude Code +9 - 0.566score
evidence-driven-testing
kausthubh-coder
Records visual proof while testing UI behavior — the agent tests the app hands-on via computer use while a screen recording with structured test/assertion…
SkillAFreshness: AClaude Code +9
Cite this page
correct skill. Agent Mart. https://agentmart.dev/skills/kausthubh-coder-correct (last updated 2026-10-24)