✍️
AI EngineeringShell

Skill Authoring

by nyldn

Skill Authoring is an AI Engineering skill for Claude Code, published by nyldn in claude-octopus.

4K stars374 forkson nyldn/claude-octopusAdded 2026/08/16Repository updated 2026/08/16
ai-agentsai-orchestrationclaude-codeclaude-code-plugincodexcopilotdeveloper-toolsdouble-diamondgeminimulti-aimulti-llmollama
Install in seconds
Install Skill Authoring
Copy Skill Authoring into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/nyldn/claude-octopus/tree/main/skills/skill-authoring ~/.claude/skills/skill-authoring

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/nyldn/claude-octopus.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/skill-authoring/SKILL.md in nyldn/claude-octopus
Installs to
~/.claude/skills/skill-authoring
Collection
One of 25 skills cataloged from this repository
Category
AI Engineering2451 skills

What Skill Authoring does

Skill Authoring provides principles for writing skills that behave the same way every run. Use it when adding, editing, or reviewing a skill in this plugin.

Skill Authoring is cataloged under AI Engineering on DirSkills. Skill Authoring comes from a repository tagged ai-agents, ai-orchestration, claude-code, claude-code-plugin and codex.

Documentation

README

Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than /octo:* slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, see skills/blocks/codex-host-adapter.md.

Skill Authoring

A skill exists to get determinism out of a stochastic system. Predictability is the goal, and it means the agent takes the same process every run — not that it produces the same output. Every rule below serves that.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Skill Authoring

  • What else does nyldn publish alongside Skill Authoring?

    Skill Authoring is one of 25 skills that DirSkills catalogs from nyldn/claude-octopus, the repository it ships in. Its siblings there include AI Debate Hub, Agent Topology Audit and Code Review. Each one is a separate skill with its own page in this directory, installs the same way Skill Authoring does, and is maintained by nyldn in that same repository. The rest of the collection is listed on the nyldn/claude-octopus page.

  • How does Skill Authoring compare to other AI Engineering skills?

    Skill Authoring ranks #546 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Skill Authoring against them. Open each page to compare what they document and how they install.

More from nyldn/claude-octopus

Skill Authoring is one of 25 skills cataloged on DirSkills from nyldn/claude-octopus.

See all 25 skills
🐙
2w ago

AI Debate Hub

AI Debate Hub runs structured multi-provider AI debates with Claude and available advisors to help make critical decisions. Use it when you want multiple AI perspectives synthesized before choosing a technical or strategic direction.
AI Engineering
4K374
🕸️
2w ago

Agent Topology Audit

Agent Topology Audit evaluates whether a multi-agent setup earns its coordination cost. Use it before adding an agent or when a workflow feels slow or agents agree without adding signal.
AI Engineering
4K374
🐙
2w ago

Code Review

Code Review runs a multi-LLM pipeline to analyze pull requests for security vulnerabilities, code quality, performance, TDD compliance, and stubs. Use it before merging changes with security or architecture impact.
Quality
4K374
🔍
2w ago

Content Pipeline

Content Pipeline extracts patterns and anatomy from up to five URLs so you can reverse-engineer content strategies. Use it to analyze articles, X threads, newsletters, YouTube descriptions, or LinkedIn posts and generate a structural blueprint, psychological playbook, and interview questions for recreating similar content.
Writing
4K374
🧠
2w ago

Context Detection

Context Detection automatically identifies whether the current task is development or knowledge work, so agent workflows can tailor research, build, and review behavior. It checks explicit overrides, prompt indicators, and project structure before returning a confidence-scored context.
AI Engineering
4K374
🟢
2w ago

Copilot Provider

Copilot Provider integrates GitHub Copilot CLI as an optional zero-cost provider in the Claude Octopus multi-LLM ecosystem, using programmatic mode for research and exploration. Use it to supplement other providers with Copilot responses, with graceful degradation if unavailable.
AI Engineering
4K374