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
  • 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.

Back to skills

Quick

ASecurity

One-shot workflow for simple tasks and bug fixes that fit in a single context window. Skips artifacts and fresh-session requirements.

8 stars
0 votes
0 copies
0 views
Added 9/20/2026
testinggit

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add tstapler/dotfiles --skill quick --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Quick?

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

Security grade badge for Quick
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/tstapler-quick-dotfiles/badge)](https://www.skillsdirectory.com/skills/tstapler-quick-dotfiles)

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

Download Zip
Files
SKILL.md
---
description: "One-shot workflow for simple tasks and bug fixes that fit in a single context window. Skips artifacts and fresh-session requirements."
argument-hint: "[task description]"
user-invocable: true
---

# sdd:quick

Lightweight end-to-end workflow for tasks simple enough to complete in one context window. No artifacts written, no phase gates, no fresh session required.

## When to use this

- Bug fixes (1–3 files)
- Small, well-scoped tasks ("add this field", "fix this edge case")
- Refactors within a single module
- Anything you can describe in one sentence

**When NOT to use this**: new services, multi-epic features, anything touching more than ~5 files, or anything requiring architecture decisions. Use `/sdd:1-ideate` instead.

## Instructions

1. **Clarify the task.**

   If `$1` was provided, use it as the task description and skip this step. Otherwise use `AskUserQuestion`:
   ```
   header: "Task type"
   question: "What needs to be done?"
   options:
     - "Fix a bug (I'll describe it via Other)"
     - "Add a small feature or field"
     - "Refactor or clean up existing code"
     - "Other — I'll describe it"
   ```

   Ask ONE follow-up via `AskUserQuestion` if genuinely needed (e.g. which file, which behaviour is expected). Do not interview — this is a quick path.

2. **Read before touching.**

   Read the relevant files. Form a clear mental model of what exists before proposing any change. For bugs:
   - Read the error/stack trace fully
   - Check `git log --oneline -10` for recent related changes
   - State the root cause hypothesis explicitly: "The root cause is X because Y"

3. **Plan inline (no file written).**

   State in 2–5 bullet points exactly what you will change and why. Confirm with the user if the scope is larger than expected.

4. **Implement.**

   Make the changes. For bugs, write a regression test that would have caught this. For features, write tests covering the happy path and one error path.

5. **Verify.**

   Run the relevant tests using the appropriate command for the stack. Show the output. Only claim success after seeing green.

   **For refactors only — architecture smell-check** (does not block, but must be acknowledged):
   Review the diff for these three signals:
   - A class or function now has more than one reason to change (Single Responsibility violated)
   - A primitive (string, int) is used where a domain type would clarify meaning or prevent bugs
   - New coupling introduced between packages that didn't exist before

   If any signal is present, note it explicitly in the summary under "Architecture notes." These are not failures — they are conscious trade-offs to document.

6. **Output a brief summary:**

   ```
   ✅ Done

   What changed: <1–2 sentences>
   Files touched: <list>
   Tests: <N> passing
   Root cause (if bug): <one sentence>
   ```

   Then use `AskUserQuestion`:
   ```
   header: "Next step"
   question: "Ready to commit and push?"
   options:
     - "Yes — commit and push now"
     - "Let me review the diff first"
     - "Commit locally but don't push yet"
   ```

Attribution

tstaplertstapler
View sourceMore from tstapler →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

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

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Screen Reader Testing

Practical guide to testing web applications with screen readers for comprehensive accessibility validation.

393431 votes

Python Testing

使用pytest、TDD方法、夹具、模拟、参数化和覆盖率要求的Python测试策略。

2456590 votes

Tdd Workflow

在编写新功能、修复错误或重构代码时使用此技能。强制执行测试驱动开发,包含单元测试、集成测试和端到端测试,覆盖率超过80%。

2456590 votes

Springboot Tdd

使用JUnit 5、Mockito、MockMvc、Testcontainers和JaCoCo进行Spring Boot的测试驱动开发。适用于添加功能、修复错误或重构时。

2456590 votes

Eval Harness

克劳德代码会话的正式评估框架,实施评估驱动开发(EDD)原则

2456590 votes
View all in testing →