Skip to content
Back to skills

Templates

ASecurity

One paragraph — leads with "when to use" / trigger phrases. Stays ≤ 1536 chars. Example "Use when... User says... Auto-triggers on..." patterns work best.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 9, 2026
ai-agentsgitsecurity

Works with

  • mcp

Security analysis

A100/100

Pro scans all 9 files and shows the line behind each finding

Scanned October 9, 2026

npx -y skills add qyndex/claude-init --skill templates --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Templates?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Templates
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/qyndex-templates/badge)](https://www.skillsdirectory.com/skills/qyndex-templates)

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

Download with Pro
SKILL.md
---
name: <kebab-case-skill-name>
description: One paragraph — leads with "when to use" / trigger phrases. Stays ≤ 1536 chars. Example "Use when... User says... Auto-triggers on..." patterns work best.
when_to_use: Additional trigger phrases the model uses to decide invocation. Concrete user prompts and phrases work better than abstract descriptions.
argument-hint: "[arg-name]"
allowed-tools: Read, Glob, Grep
disable-model-invocation: false       # true = user-only (no auto-trigger)
user-invocable: true                    # false = hidden from / menu (Claude-only)
model: inherit                          # opus | sonnet | haiku | inherit
paths:                                  # optional — auto-load only on matching files
  - "src/**/*"
context: fork                           # optional — runs in forked subagent (with `agent:` below)
agent: <name>                           # required if context: fork
mcpServers: [chrome-devtools]           # optional — pre-attached MCP servers
---

# <Skill Title>

> One-sentence summary of what this skill does. Keep it crisp.

## When to use

- Specific user phrase 1
- Specific user phrase 2
- Concrete scenario 1

## When NOT to use

- Scenario where another skill is better
- Scenario where this is overkill

## Process

```
1. Read inputs from <where>
2. Do <thing>
3. Validate via <how>
4. Output to <where>
5. Hand off to <next step>
```

## Hard rules

- **Rule 1** — why it matters
- **Rule 2** — why it matters
- **Rule 3** — why it matters

## Auto-clarity escape hatch (per caveman pattern)

If the skill modifies tone or behavior, declare when it must DISABLE itself:
- Security warnings
- Irreversible action confirmations
- Multi-step sequences where fragment order matters
- Ambiguity needing clarification

## Output

```
<path-or-artifact-this-produces>
```

After save: "<one-line summary of what was done>."

## References

- Source / inspiration: <github URL>
- Related skills: `.claude/skills/<other>/SKILL.md`
- Anthropic skills spec: https://code.claude.com/docs/en/skills

Files in this skill

  • agent.md2 KB
  • consecutive-aborts.schema.json1.6 KB
  • evidence/_evidence.ts2.7 KB
  • evidence/playwright.config.ts3.5 KB
  • overnight-report.md2.3 KB
  • pivot-prompt.md1.9 KB
  • runbook.md2.3 KB
  • skill.md2 KB
  • state-registry.tsv1.2 KB

Attribution

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

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.