skill-authoring SKILL.md skillA

skill-authoring from rogue-dev-studio/ai-agents-rogue is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add rogue-dev-studio/ai-agents-rogue/skill-authoring@git:20261017.40c5a63

Pins git:20261017.40c5a63 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
rogue-dev-studio/ai-agents-rogue
Path
skills/skill-authoring/SKILL.md
Versions recorded
2
Latest version
git:20261017.40c5a63, committed Oct 17, 2026
First version recorded
Jul 31, 2021
Size
1,858 bytes
Repository stars
2
License
a license file GitHub does not identify

Canonical guide for authoring and validating portable agent skills (SKILL.md packs) for the agent house catalog and team local skills.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Skill Authoring (Canonical)

**Level: max.**

## When to use

- Membuat/mengubah skill portable baru di `skills/` atau `teams/*/skills/`
- Validasi struktur, description triggers, DoD, dan overlap dengan skill kanonik

## Procedure

### 1. Decide surface

| Target | Output |
|--------|--------|
| Catalog house | `skills/<name>/SKILL.md` (+ optional `reference.md`) |
| Tim spesifik | `teams/<id>/skills/<name>/SKILL.md` + entri `TEAM.yaml` |

### 2. Author SKILL.md

- Frontmatter: `name`, `description` (trigger-rich, tanpa jargon sumber luar)
- Body: when / when-not, procedure, DoD, security notes
- **Wajib** footer Attribution Rogue Development (lihat `rules/author.md`); jangan dihapus/dihide
- Progressive disclosure: detail panjang di `reference.md` bila perlu

### 3. Avoid duplication

- Cek `CATALOG.md` dan `ALIASES.md`
- Jika overlap fungsi: perluas skill kanonik, jangan buat skill paralel

### 4. Validate

- Description cukup spesifik agar host skill picker menemukan skill
- Procedure bisa dijalankan tanpa dependensi tersembunyi
- Tidak ada secret / path mesin pribadi di contoh

### 5. Document

- Entri `CATALOG.md` atau TEAM `local_skills`
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add rogue-dev-studio/ai-agents-rogue/skill-authoring@sha256:a1acf4dbba2cd1b0

The line at the top of this page pins the label git:20261017.40c5a63, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_6rsh7syufyc2vbzp.svg)](https://markdownregistry.com/a/art_6rsh7syufyc2vbzp)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Jul 31, 2021 and Oct 17, 2026, about one every 1,904 days.

versioncommittedcommitsizeaudit
git:20261017.40c5a63 latest2026-10-17 40c5a63 1,858 BA view · diff
git:20210731.7b775d22021-07-31 7b775d2 1,927 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1858 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

rogue-dev-studio/ai-agents-rogue · 2 stars · license a license file GitHub does not identify · pushed 2026-10-17 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_6rsh7syufyc2vbzp
GET https://markdownregistry.com/api/v1/resolve?ref=rogue-dev-studio/ai-agents-rogue/skill-authoring
GET https://markdownregistry.com/api/v1/blob/a1acf4dbba2cd1b0411a77b9b121e9f601e43ccbc4787fa5eaa16321bd7ca60b

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from rogue-dev-studio/ai-agents-rogue

AGENTS.md AGENTS.md file
rogue-dev-studio/ai-agents-rogue · AGENTS.md
git:20261017.a316ad9 · audit A · 2 stars
agentic-flow SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/agentic-flow/SKILL.md · Canonical multi-agent orchestration: decompose work, dependency graphs, parallel tracks, handoffs, and merge. Absorbs…
git:20260731.ddb8838 · audit A · 2 stars
agentic-qe SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/agentic-qe/SKILL.md · Canonical quality engineering: test strategy, case generation, coverage gates, exploratory checks, and security-tinged…
git:20260731.ddb8838 · audit A · 2 stars
ai-coding-assistants SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/ai-coding-assistants/SKILL.md · Canonical playbook for AI coding assistants and CLI pair-programmers (Claude Code, Kilo, Goose, OpenCode, multi-CLI…
git:20260731.ddb8838 · audit A · 2 stars
algorithmic-art SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/algorithmic-art/SKILL.md · Generative algorithmic art. Use when the project needs this capability or the user / team manifest asks for it. Use for…
git:20260731.ddb8838 · audit A · 2 stars
api-engineering SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/api-engineering/SKILL.md · Expert API design and delivery: resource modeling, versioning, consistent error envelopes, pagination/filtering…
git:20260801.aa14763 · audit A · 2 stars
auth-access-control SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/auth-access-control/SKILL.md · Expert authentication and authorization engineering: identity lifecycle, session/token handling, password/OTP flows…
git:20260801.aa14763 · audit A · 2 stars
backend-engineering SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/backend-engineering/SKILL.md · Expert backend application engineering: layered architecture, domain services, validation, transactions, caching…
git:20260801.aa14763 · audit A · 2 stars
blender SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/blender/SKILL.md · Prefer this for any 3D modeling, mesh, scene, render, or Blender request (e.g. "buat model 3D ikan", character, prop)…
git:20260731.ee74c16 · audit A · 2 stars
browser-automation SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/browser-automation/SKILL.md · Canonical browser automation and web UI verification: Playwright, agent browser CLIs, and CDP-based tooling in one…
git:20260731.dea1934 · audit A · 2 stars
canvas-design SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/canvas-design/SKILL.md · Design system framework. Use when the project needs this capability or the user / team manifest asks for it. Use for…
git:20260731.ddb8838 · audit A · 2 stars
clarity SKILL.md skill
rogue-dev-studio/ai-agents-rogue · skills/clarity/SKILL.md · Canonical spec and requirements skill: 5-phase clarity workflow plus Spec-Kit / markdown-agent spec patterns. Use for…
git:20260731.ddb8838 · audit A · 2 stars

Every file in rogue-dev-studio/ai-agents-rogue

Other files named skill-authoring

skill-authoring SKILL.md skill
nyldn/claude-octopus · .claude/skills/skill-authoring/SKILL.md · Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in…
git:20261108.8380d65 · audit A · 4,409 stars
skill-authoring SKILL.md skill
nyldn/claude-octopus · skills/skill-authoring/SKILL.md · Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in…
git:20260907.4febbb1 · audit A · 4,409 stars
skill-authoring SKILL.md skill
cbrock84/headcount · plugins/technology/skills/skill-authoring/SKILL.md · Writes and revises agent skills so they trigger at the right moments and give usable instruction when they do. Use this…
git:20260916.e72e404 · audit A · 2,543 stars
skill-authoring SKILL.md skill
uvwt/agentdock · core-skills/skill-authoring/SKILL.md · 创建、设计、修改、重构和验证 AgentDock Skill 时使用;负责 Agent Skills 兼容的 SKILL.md、可移植核心、引用、辅助脚本、测试、安全边界和本地真实验证。
git:20260925.a4848d1 · audit A · 1,295 stars
skill-authoring SKILL.md skill
mateaix/mateclaw · mateclaw-server/src/main/resources/skills/skill-authoring/SKILL.md · Author SKILL.md skills: frontmatter, validator limits, structure.
v1.0.0 · audit A · 1,185 stars
skill-authoring SKILL.md skill
tencentcloudbase/cloudbase-ai-toolkit · skills/skill-authoring/SKILL.md · Design, improve, and evaluate reusable agent skills with high-quality SKILL.md files, precise trigger descriptions…
git:20260817.2eb60da · audit A · 1,163 stars
skill-authoring Cursor rule
borghei/claude-skills · .cursor/rules/skill-authoring.mdc · Conventions for writing or editing a SKILL.md skill package.
git:20260629.ee6fb37 · audit A · 1,075 stars
skill-authoring SKILL.md skill
athola/claude-night-market · plugins/abstract/skills/skill-authoring/SKILL.md · Guide creating Claude Code skills with TDD and persuasion principles. Use for new skill development.
git:20260902.b3bb3ff · audit A · 348 stars

Browse by kind, by grade A, or by owner.