Skill author

Skill Arnie016/fable-mythos/skills/skill-author

Reusable Claude Skills, evals, and repair loops for turning giant prompts into compounding AI workflows.

Install

npx -y skills add Arnie016/fable-mythos --skill skill-author

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Creates a new Claude Skill to fable-mythos standard - a tight SKILL.md plus eval cases and an example. Use when the user wants to turn a repeated workflow, a giant pasted prompt, or a recurring task into a reusable skill.

SKILL.md

2.4 KB, as published. Nobody here has run it

Skill Author

Mission

Turn a repeated workflow into a skill package a cheaper model can execute. Prompts are temporary; skills compound — but only if they're small, testable, and honest about failure.

Step zero

Confirm the workflow is actually repeated. A one-off task gets an answer, not a skill — building a skill for something done once is how prompt libraries fill with corpses.

Workflow

Description first. It does the triggering: name the task, the artifacts involved, and 3–4 phrasings a user would actually type. A skill that never fires is dead regardless of quality.
Body under 60 lines: mission (2 lines) · workflow (≤7 numbered steps, each operational — a step that can't fail isn't a step) · rule precedence (explicit user requests beat style rules; say it) · output format (≤5 sections).
Bulk goes to reference files. Voice, long examples, templates → examples.md in the skill folder, loaded on demand. If the user pasted a 2,000-word prompt, compress the logic into the skill and move the rest — never transcribe.
One skill, one job. If the workflow splits into two jobs, split the skill or build the more repeated half.
Write ≥4 evals (JSONL: id, type, input, expected, failure_to_prevent): at least one messy real-world input and one adversarial (the user asks for something the skill should resist).
Write 1 example showing input → ideal output, annotated.
Self-check before delivering: description triggerable? · every workflow step falsifiable? · body ≤60 lines? · adversarial eval present? · no "you are a world-class expert" preamble? · nothing the executor model can't follow?

Boundaries

Refuse skills engineered for dishonesty — auto-10/10 self-graders, fake-engagement generators, sycophancy by design. An evaluator that can't fail the work isn't a skill, it's a rubber stamp.

Output format

SKILL.md (complete)

evals/<name>.jsonl (complete)

examples/<name>-example.md (complete)

Handoff note

Where each file goes in the repo + the reminder: the skill gets good through the repair loop on the executor model, not through this authoring pass.