Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Help

ASecurity

Think before typing. Root cause first, two candidate fixes, pick one, ask if still unclear, then change only the files the request needs. Edit the confidence bar and scope rules to fit the project. Use when a bug report comes in, when a previous fix did not work, or when the request is vague.

405 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsgit

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add waynesutton/builder-skills --skill help --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Help?

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

Security grade badge for Help
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/waynesutton-help/badge)](https://www.skillsdirectory.com/skills/waynesutton-help)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: help
description: Think before typing. Root cause first, two candidate fixes, pick one, ask if still unclear, then change only the files the request needs. Edit the confidence bar and scope rules to fit the project. Use when a bug report comes in, when a previous fix did not work, or when the request is vague.
---

# Help

Slow down for thirty seconds before the first edit. It saves an hour later.

## Reflect before acting

1. Why does the current code not do what the user wants? Read it. Do not guess.
2. What is missing, wrong, or incomplete relative to the request?
3. List two or three candidate causes.
4. Pick the most likely one and say why.
5. If the answer to "what is unclear" is not empty, ask one question and stop.

Never assume. A wrong assumption costs more than a question.

## Confidence bar

Do not write code below [98]% confidence in what needs to change. Below that: read more, ask, or propose a plan instead of a diff.

## Convex rules

- Mutations map form fields to document fields one to one. Field names match.
- Patch without reading when possible. Indexed queries for ownership. Idempotent with early returns. `Promise.all` for independent writes.
- Load the matching `convex-*` skill for anything deeper.

## Scope

Change:

- Files the request needs.
- The schema, if the request needs it.
- `changelog.md`, `files.md`, `task.md` after the change lands. Dates from `git log --date=short`, never invented.

Do not change:

- UI, layout, colors, or copy that the request did not mention.
- Existing sections, features, or components. Nothing gets removed without being asked.
- [Add project specific protected areas: admin dashboard, billing flow, etc.]

## UI

- Site design system for every popup, alert, modal, toast, confirmation. Never the browser default.
- Vercel Web Interface Guidelines: https://raw.githubusercontent.com/vercel-labs/web-interface-guidelines/refs/heads/main/AGENTS.md

## Docs policy

Do not create README, CONTRIBUTING, SUMMARY, or USAGE files unless asked. A short summary in the reply is enough.

## Git

Load `git-safety` before any git command that could discard work. Short version: `git status` first, `git diff` before discarding, edit files by hand to undo, never `reset --hard` / `checkout -- .` / `clean -fd` / `stash drop` without the user saying yes to that exact command.

## Checklist

Before the first edit:

- [ ] I can name the root cause
- [ ] I considered at least two fixes and picked one for a reason
- [ ] I am at or above the confidence bar
- [ ] I know which files change and which do not
- [ ] Anything unclear has been asked

Before saying done:

- [ ] The fix was verified, not just written
- [ ] Nothing outside the request changed
- [ ] Docs synced if the change was non trivial

Attribution

waynesuttonwaynesutton
View sourceMore from waynesutton →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 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', ...

695601 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →