skill-development

Development rules for creating and editing skills, which are reusable instruction sets for coding agents. They define the required files, naming, descriptions, and content standards.

In plain words
What is it for?
Use them when adding or updating a skill, including its metadata file, main prompt, examples, and links to related skills.
Why use it?
They keep skills consistently organized and make it clearer when an agent should use each one.

Cursor rule for Cursor

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 rules/vibeeval/vibecosystem/skill-development
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 237 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found 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 $0.00000 $0.00237
Opus 5 $0.00000 $0.00118
Sonnet 5 $0.00000 $0.00047
Haiku 4.5 $0.00000 $0.00024

Measured 2d ago against content hash 0624159981e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-development 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 2d ago.

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.

.cursor/rules/skill-development.mdc · 46 lines

What it actually says

Skill Development Rules

Skill Directory Structure

Each skill lives in its own directory under skills/:

skills/
  coding-standards/
    SKILL.md      # Skill metadata + trigger description
    prompt.md     # Full skill content

SKILL.md Format

---
name: skill-name
description: When and why to use this skill. Used for auto-discovery.
---

Followed by the skill content in Markdown.

prompt.md Format

The full prompt/knowledge content. No frontmatter needed.

Naming Conventions

  • Directory name: kebab-case (e.g., coding-standards)
  • SKILL.md name field: same as directory name
  • Description: explains WHEN to trigger, not just WHAT it does

Quality Rules

  • Description must clearly indicate trigger conditions
  • Content should be actionable, not theoretical
  • Include code examples where applicable
  • Keep skills focused on one domain/topic
  • Cross-reference related skills in content
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. 2d ago First seen · 46 lines · 0 tokens per session scan A 0624159981e0

Subscribe to this mod's changes

skill-development is a cursor rule published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 24d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 237 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.