Pick skills → choose your agent → copy or download one rules file.
✨ Why Agents Skills
- 🧠 Senior habits, on by default. Spec first, small slices, tests that prove it and reviews before merge, written as instructions your agent actually follows.
- 🛡️ Fewer "looks right" bugs. Security hardening, debugging triage and anti-slop audits stop the agent from guessing.
- 🎨 Goes beyond CRUD. Deep libraries for modern web layout, shaders and WebGL, Three.js game dev, science and platform SDKs.
- 🔌 Works with the agent you already use. Export to Claude Code, Cursor, Windsurf, Gemini/Antigravity or ChatGPT custom instructions.
- ⚡ One command to install.
curl, npx or a plain git clone, with no build step.
📸 Tour
🚀 Quick start
Fastest: open the dashboard, pick skills and copy the rules into your editor. Nothing to install.
Install everything locally (clones into your agent's plugin folder):
curl -sSL https://raw.githubusercontent.com/satiricalguru/Agents-skills/main/install.sh | bash
Add one skill to Claude Code (folder skills such as readme-showcase):
git clone https://github.com/satiricalguru/Agents-skills.git
cp -r Agents-skills/skills/readme-showcase ~/.claude/skills/
More options, including npx and manual install, are in Installation.
🧠 How it works
flowchart LR
A["skills/*.md and skills/*/SKILL.md"] --> B["docs/generate-skills-db.js"]
B --> C["skills.json"]
C --> D["Dashboard<br/>pick + preview"]
D --> E[".cursorrules · .clauderc · .windsurfrules<br/>Gemini · ChatGPT"]
A --> F["install.sh / npx<br/>plugin install"]
📑 Contents
🛠️ Available Skills
| Skill | Description | Use When |
|---|
using-agent-skills | Maps incoming work to the right skill workflow and defines shared operating rules. | Starting a session or deciding which skill applies |
no-excuses-executor | Direct task execution with zero hedging. Forces action-first completion, suppresses over-caution. | Running direct actions/commands without hesitation |
| Skill | Description | Use When |
|---|
interview-me | One-question-at-a-time interview that extracts what the user actually wants instead of what they think they should want, until ~95% confidence. | The ask is underspecified, or the user invokes "interview me" / "grill me" |
idea-refine | Structured divergent/convergent thinking to turn vague ideas into concrete proposals. | You have a rough concept that needs exploration |
spec-driven-development | Write a PRD covering objectives, commands, structure, code style, testing, and boundaries before any code. | Starting a new project, feature, or significant change |
| Skill | Description | Use When |
|---|
planning-and-task-breakdown | Decompose specs into small, verifiable tasks with acceptance criteria and dependency ordering. | You have a spec and need implementable units |
| Skill | Description | Use When |
|---|
incremental-implementation | Thin vertical slices - implement, test, verify, commit. Feature flags, safe defaults, rollback-friendly changes. | Any change touching more than one file |
test-driven-development | Red-Green-Refactor, test pyramid (80/15/5), test sizes, DAMP over DRY, Beyonce Rule, browser testing. | Implementing logic, fixing bugs, or changing behavior |
context-engineering | Feed agents the right information at the right time - rules files, context packing, MCP integrations. | Starting a session, switching tasks, or when output quality drops |
source-driven-development | Ground every framework decision in official documentation - verify, cite sources, flag what's unverified. | You want authoritative, source-cited code for any framework or library |
doubt-driven-development | Adversarial fresh-context review of every non-trivial decision in-flight - CLAIM → EXTRACT → DOUBT → RECONCILE → STOP, with optional user-authorized cross-model escalation. | Stakes are high (production, security, irreversible), working in unfamiliar code, or verifying early is cheaper |
frontend-ui-engineering | Component architecture, design systems, state management, responsive design, WCAG 2.1 AA accessibility. |
여기까지가 README 앞부분입니다. 나머지는 원문에서 읽을 수 있습니다. README 전문 보기 ↗
