From asi
Defines YAML schema, constraints, directory structure, and robustness patterns for SKILL.md files compatible across Claude Code, Cursor, Codex CLI, and future agents. Use when authoring skills.
npx claudepluginhub plurigrid/asi --plugin asiThis skill uses the workspace's default tool permissions.
Formal specification for evolutionarily robust agent skills.
Guides creation of Agent Skills with progressive disclosure, best practices, structure, and categories. Use when building new skills or understanding skill format.
Guides creation of Claude Agent Skills covering structure, progressive disclosure, categories, best practices, and file formats. Use when building new skills or understanding mechanics.
Guides authoring SKILL.md files for Claude Code, covering structure, required/optional frontmatter fields, invocation controls, argument passing, and best practices. Use when creating new skills.
Share bugs, ideas, or general feedback.
Formal specification for evolutionarily robust agent skills.
Skills that follow the spec work across:
Non-compliant skills break silently or fail validation.
---
name: skill-name # REQUIRED: lowercase, hyphens, 1-64 chars
description: What and when # REQUIRED: max 1024 chars, no < or >
license: Apache-2.0 # optional
compatibility: Requires git # optional, max 500 chars
metadata: # optional: custom key-value pairs
trit: 0
author: bmorphism
version: "1.0"
allowed-tools: Bash Read # optional, experimental
---
# Body content (Markdown)
| Field | Required | Rules |
|---|---|---|
name | ✓ | [a-z0-9-]+, no --, no leading/trailing -, max 64 |
description | ✓ | 1-1024 chars, no < or >, includes WHEN to use |
license | ✗ | Short name or file reference |
compatibility | ✗ | Environment requirements, max 500 |
metadata | ✗ | Arbitrary k:v for custom fields |
allowed-tools | ✗ | Space-delimited tool names |
Level 1: name + description (~100 tokens) - loaded at startup
Level 2: SKILL.md body (<5000 tokens) - loaded on activation
Level 3: scripts/, references/, assets/ - loaded on demand
Keep SKILL.md under 500 lines. Move details to references/.
# BAD - platform-specific
allowed-tools: claude_desktop_mcp
# GOOD - generic capability
compatibility: Requires MCP server access
Include validation in your skill:
# scripts/validate.sh
skills-ref validate "$(dirname "$0")/.."
metadata:
version: "2.1.0"
breaking-changes: "v2.0 changed API"
For plurigrid/asi skills:
metadata:
trit: -1 # MINUS: verification, constraint
trit: 0 # ERGODIC: balance, mediation
trit: +1 # PLUS: generation, exploration
Conservation: Σ trits ≡ 0 (mod 3) across compositions.
skill-name/
├── SKILL.md # Required
├── scripts/ # Executable code
│ └── main.py
├── references/ # Additional docs
│ └── REFERENCE.md
└── assets/ # Static resources
└── template.json
# Official validator
skills-ref validate ./my-skill
# Codex-rs validator
python3 codex-rs/core/src/skills/assets/samples/skill-creator/scripts/quick_validate.py ./my-skill
# Batch validate
for d in skills/*/; do skills-ref validate "$d"; done
| Error | Fix |
|---|---|
| No YAML frontmatter | Add --- delimiters |
| Unexpected keys | Move to metadata: |
| Angle brackets in description | Remove < and > |
| Name not hyphen-case | Lowercase, hyphens only |
| Description too long | Max 1024 chars |
| YAML colon in value | Quote the string |
This skill connects to the K-Dense-AI/claude-scientific-skills ecosystem:
category-theory: 139 citations in bib.duckdbThis skill maps to Cat# = Comod(P) as a bicomodule in the equipment structure:
Trit: 0 (ERGODIC)
Home: Prof
Poly Op: ⊗
Kan Role: Adj
Color: #26D826
The skill participates in triads satisfying:
(-1) + (0) + (+1) ≡ 0 (mod 3)
This ensures compositional coherence in the Cat# equipment structure.