Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Correct

ASecurity

Eliminate repeated repository mistakes through architecture, types, diagnostic checks, and behavior tests, with proof against real past failures.

2 stars
0 votes
0 copies
0 views
Added 10/6/2026
ai-agentsdocumentation

Security Analysis

A100/100

Scanned 10/6/2026

$npx -y skills add williamwue/oh-my-stack --skill correct --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Correct?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Correct
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/williamwue-correct/badge)](https://www.skillsdirectory.com/skills/williamwue-correct)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: correct
description: "Eliminate repeated repository mistakes through architecture, types, diagnostic checks, and behavior tests, with proof against real past failures."
disable-model-invocation: true
---

# Correct

Use for repeated mistakes in this repository. Editing a workflow Skill belongs
to [reflect](../reflect/SKILL.md) or [authoring-a-skill](../authoring-a-skill/SKILL.md).
The user's request bounds the investigation and changes; a correction does not
itself authorize unrelated edits, publication, or changes to global rules.

## Find the mistake classes

Read scoped recent commits, reverts, available review comments, repository
instructions, and workaround comments. Group mistakes by mechanism. A repeated
class needs at least two attributable occurrences, with paths or revisions.
If history is unavailable, report the gap rather than inventing occurrences.
A single observed defect can still be fixed within the user's authorized scope.

Assume a contributor sees only the files it opened, copies the nearest example,
and takes the shortest path that compiles. Prefer a structure where a change
that looks right from one file is right across the repository.

## Eliminate each class at the highest useful level

1. Architecture: give state one owner and tasks one supported path. Hide
   internals, derive duplicated lists, migrate callers, and delete obsolete ways.
2. Types: make invalid states unrepresentable. When types cannot enforce the
   constraint, add a diagnostic lint or CI check that names the supported fix.
   For an existing widespread pattern, reject new occurrences without hiding
   current debt.
3. Behavior: assert the result a user observes. Reject a test that still passes
   when every function it calls returns nothing.
4. Documentation: use instructions only for judgment calls a check cannot
   enforce. Explain why a higher level is insufficient.

## Fix and prove

Fix one class per verifiable unit. Preserve unrelated edits. Prove the new
constraint fails on a real past mistake, then passes on the correction using
local commands and the same CI command when CI exists. Keep the historical
example and observed output with the result. If no authentic failing example
is available, mark that proof incomplete; a made-up example is not history.

Maintain a scoped rule-to-enforcement table in repository instructions when
useful. Remove redundant prose only after the corresponding check proves the
mistake impossible. Exceptions name the reason, expiry, and approval required
by repository policy; do not invent approval or expand the task's authority.

Return each class, its occurrences, chosen enforcement level, why higher levels
were insufficient, actual failing and passing commands, changed paths, and gaps.

Attribution

williamwuewilliamwue
View sourceSee grades on GitHubMore from williamwue →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →