Snoozer10/synthesize-skills / templates/skill-template
skill-name
VerifiedUse when creating a new reusable skill from a proven technique, pattern, or reference that future agents must discover and apply
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.3 KB |
| references/.gitkeep | other | 0 B |
| scripts/.gitkeep | other | 0 B |
SKILL.md
View on GitHub---
name: skill-name
description: Use when creating a new reusable skill from a proven technique, pattern, or reference that future agents must discover and apply
---
# Skill Name
## Overview
One technique in 1-2 sentences. Core principle stated plainly.
## When to Use
- Symptom or trigger 1: concrete situation where this applies
- Symptom or trigger 2: error message, behavior, or request type
- When NOT to use: one-off fix, unrelated stack, or project-specific rule
Keywords: trigger, symptom, error, fallback, pattern, lifecycle
## Quick Reference
| Situation | Action |
|-----------|--------|
| Common case | Do X |
| Edge case | Do Y |
| Unsure | Read Implementation below |
## Implementation
Steps:
1. Identify the trigger from When to Use.
2. Apply the minimal pattern below.
3. Verify with the runnable example.
```python
def greet(name):
if not name:
raise ValueError("name must be non-empty")
return "hello " + name
if __name__ == "__main__":
assert greet("sam") == "hello sam"
try:
greet("")
except ValueError:
pass
else:
raise AssertionError("expected ValueError")
print("PASS")
```
## Common Mistakes
- Mistake 1: copying the pattern without checking triggers. Fix: re-read When to Use first.
- Mistake 2: adding options for later. Fix: delete them; add when a real case needs them.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |