# Skill Authoring Assistant

> >

- **Type:** Skill
- **Install:** `agentstack add skill-theshubh007-agent-skill-finder-write-a-skill`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [theshubh007](https://agentstack.voostack.com/s/theshubh007)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [theshubh007](https://github.com/theshubh007)
- **Source:** https://github.com/theshubh007/agent-skill-finder/tree/main/skills/write-a-skill

## Install

```sh
agentstack add skill-theshubh007-agent-skill-finder-write-a-skill
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Process

### Step 1 — Gather Requirements

Ask the user:
- What task or domain does this skill cover?
- What specific use cases must it handle?
- Does it need executable scripts or instructions only?
- Are there reference materials to incorporate?

### Step 2 — Draft the Skill

Produce:
- `SKILL.md` — concise instructions (target under 100 lines)
- `REFERENCE.md` — detailed documentation if content exceeds 500 lines
- `scripts/` — utility scripts for deterministic, repeatable operations

### Step 3 — Review With User

Present the draft and ask:
- Does this cover all intended use cases?
- Is anything missing or ambiguous?
- Should any section be expanded or reduced?

---

## Directory Structure

```
skill-name/
├── SKILL.md           # Primary instructions (required)
├── REFERENCE.md       # Extended documentation (if needed)
├── EXAMPLES.md        # Worked examples (if needed)
└── scripts/           # Utility scripts (if needed)
    └── helper.js
```

---

## SKILL.md Template

```markdown
---
id: skill-name
name: Human-Readable Skill Name
version: 1.0.0
description: >
  One-paragraph capability description. Specific enough for BM25 routing.
  Use when [explicit trigger conditions].
capability:
  type: data-transform|code-execution|retrieval|agentic-pipeline|ml-inference
  inputs: [...]
  outputs: [...]
graph:
  depends_on: []
  complements: [...]
  co_used_with: [...]
compatibility:
  claude_code: true
  gemini: true
  mcp: true
risk: safe|network|exec|critical|unsafe
---

## Quick Start

[Minimal working example]

## Workflows

[Step-by-step processes with checklists for complex tasks]

## Advanced Features

See REFERENCE.md
```

---

## Description Requirements

The `description` field is the sole routing signal — the agent reads it to decide whether to load this skill. It must be specific enough to distinguish this skill from all others.

**Requirements:**
- Maximum 1024 characters
- Written in third person
- First sentence: what the skill does
- Second sentence: "Use when [specific triggers, keywords, file types, or user phrases]"

**Good:**
> Extracts text, tables, and form fields from PDF files; merges and splits documents. Use when working with PDF files or when the user mentions forms, document extraction, or PDF processing.

**Poor:**
> Helps with documents.

---

## When to Add Scripts

Add a `scripts/` entry when:
- The operation is fully deterministic (validation, formatting, linting)
- The same code would be regenerated repeatedly across invocations
- Explicit error handling is required for edge cases

## When to Split Into Separate Files

Split when:
- `SKILL.md` exceeds 100 lines
- Content spans distinct domains (e.g., finance schema vs. sales schema)
- Advanced reference material is rarely needed during normal use

---

## Review Checklist

- [ ] `description` includes explicit trigger conditions ("Use when...")
- [ ] `SKILL.md` is under 100 lines
- [ ] No time-sensitive or environment-specific information embedded
- [ ] Terminology is consistent throughout
- [ ] At least one concrete example is included
- [ ] Cross-references are one level deep (no nested includes)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [theshubh007](https://github.com/theshubh007)
- **Source:** [theshubh007/agent-skill-finder](https://github.com/theshubh007/agent-skill-finder)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-theshubh007-agent-skill-finder-write-a-skill
- Seller: https://agentstack.voostack.com/s/theshubh007
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.