skill-author

skill-author is a skill for Claude Code from robium-ai/robium. It costs 179 tokens per session (2,687 once invoked), scanned A, original, MIT.

A tool for creating and improving robium skills, which are reusable instructions that guide coding agents through specific jobs.

In plain words
What is it for?
Use it to create a skill, extract patterns from an app, apply recorded learnings, audit an existing skill, or validate one before committing.
Why use it?
It keeps skills consistent with the project's template and quality rules, while making it easier to check triggers and incorporate lessons from previous work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the robium plugin — 70 skills, 1 agent, 6 hooks shipped together

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 skills/robium-ai/robium/1.1.3
Any agent
npx skills add robium-ai/robium --skill 1.1.3
Clone the repo
git clone --depth 1 https://github.com/robium-ai/robium

Made for: Claude Code.

Or install robium, the plugin that ships this one along with the rest of its 70 skills, 1 agent, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for skill-author

README.md
[![agentmods](https://agentmods.dev/badge/skills/robium-ai/robium/1.1.3.svg)](https://agentmods.dev/skills/robium-ai/robium/1.1.3)
Your own site
<a href="https://agentmods.dev/skills/robium-ai/robium/1.1.3"><img src="https://agentmods.dev/badge/skills/robium-ai/robium/1.1.3.svg" alt="Measured on agentmods" height="20"></a>
Per session 179 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,687 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 5.1 $0.00179 $0.02687
Opus 5 $0.00089 $0.01344
Sonnet 5 $0.00036 $0.00537
Haiku 4.5 $0.00018 $0.00269

Measured 6d ago against content hash 8bfaee60907c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-author 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/validate_skills.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

archive/skill-author/1.1.3/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

skill-author

The meta-skill that governs how every other robium skill gets born, mined, and hardened. It is the repo's authoring machinery: it enforces the quality bar defined in the design spec, runs the repo-level validator, and describes the three ways skill content enters the catalog — fresh authoring, mining from this repo's own apps, and hardening from post-trial learnings.

When to use this skill

  • Creating a brand-new skill under skills/<name>/ from the template.
  • Extracting reusable patterns out of this repo's own apps (or an in-house app built without robium) into a new or existing skill — external example repos are the mining skill's job.
  • Consuming learnings/YYYY-MM-DD.md files written during app-building sessions and folding them back into the affected skills.
  • Auditing an existing skill against the quality bar, or running the validator before a commit.
  • Tuning a skill's frontmatter description for better trigger accuracy, or evaluating whether a skill fires on the phrasing it should.
  • Cross-reference: for building an actual robotics application (choosing a stack, scaffolding a repo), use the architect skill and the domain skills it routes to instead — this skill only edits skills, never application code.

Key directives

  • Delegation posture: embed. This skill owns the authoring workflow outright; there is no good upstream skill for "how to write a robium skill," so the process lives here rather than being linked out.
  • Knowledge goes to the lowest skill that can hold it — a Nav2 costmap gotcha belongs in nav2, not architect; a ROS 2 launch-file quirk belongs in ros2, not a per-tool skill built on top of it. Never park knowledge one level higher than where it will actually be looked up.
  • Recurrence rule: anything appearing twice across learnings notes becomes a skill edit immediately — do not wait for a third occurrence.
  • Every absorbed learning adds one dated line to the ## Changelog section of the skill it changed. No silent edits during hardening.
  • Always run scripts/validate_skills.py before committing any skill change — fresh, mined, or hardened. A skill that fails the validator is not done.
  • For eval design and description-wording tuning, wrap Claude's own skill-creator skill rather than reinventing evals or trigger-testing machinery. skill-author supplies the robium-specific quality bar and workflow; skill-creator supplies the generic eval tooling.

Read the full file on GitHub · 181 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 6d ago First seen · 181 lines · 179 tokens per session scan A 8bfaee60907c

Subscribe to this mod's changes

skill-author is a skill published in the GitHub repository robium-ai/robium (9 stars, last pushed 8d ago), licensed MIT. It adds 179 tokens to every session and 2,687 once invoked, about $0.0009 per session on Opus 5. 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 2026-08-31.