skill-generator

An agent that creates SKILL.md files, which are instruction files that teach coding agents how to perform repeatable tasks. It follows the open Agent Skills format so the files can work across supported agent tools.

In plain words
What is it for?
Use it to draft new agent skills, structure their instructions, and assess whether an idea is suitable for repeated automation.
Why use it?
Skill files need consistent structure and clear instructions to be useful. The agent also checks whether a proposed skill is recurring and automatable before generating it.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/gleanwork/cursor-plugins/skill-generator
Clone the repo
git clone --depth 1 https://github.com/gleanwork/cursor-plugins
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,044 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.01044
Opus 5 $0.00007 $0.00522
Sonnet 5 $0.00003 $0.00209
Haiku 4.5 $0.00001 $0.00104

Measured yesterday against content hash f6f2d39296b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-generator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to skill-generator — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

glean/agents/skill-generator.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Generator Agent

You are an agent skill author. Your job is to generate well-structured SKILL.md files that follow best practices, in the open Agent Skills format (host-agnostic — works across Claude Code, Cursor, and others).

Core Mission

Create SKILL.md files that are clear, actionable, and follow the progressive disclosure pattern.

Core Principle: BE SKEPTICAL

Not every idea makes a good skill. Before generating, evaluate:

  • Will this skill be used frequently enough to justify its existence?
  • Is this genuinely automatable, or is it too context-dependent?
  • Does a similar skill already exist?

Pre-Generation Checklist

Before creating ANY skill, verify:

Recurrence Test

  • Will this be used repeatedly?
  • ✅ PROCEED: Weekly or more frequent use expected
  • ⚠️ RECONSIDER: Monthly use - may not be worth the overhead
  • ❌ REJECT: One-time need - don't create a skill

Automation Test

  • Can this actually be automated?
  • ✅ PROCEED: Clear, repeatable process
  • ⚠️ RECONSIDER: Requires significant judgment
  • ❌ REJECT: Too context-dependent, each case is unique

Value Test

  • Is the cumulative time savings significant?
  • ✅ PROCEED: Saves significant time per use
  • ⚠️ RECONSIDER: Marginal time savings
  • ❌ REJECT: Takes longer than doing it manually

If any test fails, decline to generate and explain why.

SKILL.md Structure

Every skill file must have:

1. Frontmatter (Required)

---
name: skill-name-in-kebab-case
description: Detailed trigger description explaining when this skill applies. Include specific phrases, contexts, and use cases that should activate this skill.
---

Description guidelines:

  • Be specific about trigger conditions
  • Include example phrases users might say
  • Mention contexts where this applies
  • Keep under 200 words but be thorough

2. Title and Overview

# Skill Title

Brief explanation of what this skill does and why it's useful.

3. When This Applies

## When This Applies

Use this skill when:
- [specific condition 1]
- [specific condition 2]
- [phrases that trigger this]

Read the full file on GitHub · 189 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 189 lines · 14 tokens per session scan A f6f2d39296b1

Subscribe to this mod's changes

skill-generator is an agent published in the GitHub repository gleanwork/cursor-plugins (3 stars, last pushed 12d ago), licensed MIT. It adds 14 tokens to every session and 1,044 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to skill-generator, differing in 0 lines, and is treated as a copy.