skill-creator

A toolkit for creating and improving agent skills, which are written instructions for carrying out repeatable tasks.

In plain words
What is it for?
It is for drafting skills, updating existing ones, creating test prompts, and measuring their results.
Why use it?
It provides a way to test whether a skill works well instead of relying only on informal review.

Skill for Claude CodeCodex

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/cratis/ai/skill-creator
Any agent
npx skills add Cratis/AI --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/Cratis/AI

Made for: Claude Code, Codex.

Per session 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,372 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 88% copy Near-identical to another mod 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 $0.00063 $0.07372
Opus 5 $0.00032 $0.03686
Sonnet 5 $0.00013 $0.01474
Haiku 4.5 $0.00006 $0.00737

Measured 2d ago against content hash 1ba874c5ab0e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skill-creator 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 2d ago.

The scan reads SKILL.md. This mod also ships 11 executable files (eval-viewer/generate_review.py, scripts/__init__.py, scripts/aggregate_benchmark.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.

Origin

This is a copy

88% identical to skill-creator — 68 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.ai/skills/skill-creator/SKILL.md · 489 lines

How it starts

The opening of the file, as written. The whole thing — 489 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creator

Cratis note: this is a vendored upstream skill (its LICENSE.txt is Apache-2.0, unlike the MIT headers elsewhere in this repo). In Cratis, skills are the canonical source at .ai/skills/<name>/SKILL.md, surfaced to each tool via folder symlinks — see managing-ai-rules.md. When you finish authoring a skill here, make sure it lives at .ai/skills/<name>/SKILL.md and run .ai/hooks/scripts/validate-ai-setup.sh. (This skill's name collides with the tools' built-in skill-creator — invoke the one you intend. We deliberately keep the upstream name rather than rename: its scripts/ self-reference skill-creator, so renaming would break the vendored tooling and diverge from upstream.)

A skill for creating new skills and iteratively improving them.

At a high level, the process of creating a skill goes like this:

  • Decide what you want the skill to do and roughly how it should do it
  • Write a draft of the skill
  • Create a few test prompts and run claude-with-access-to-the-skill on them
  • Help the user evaluate the results both qualitatively and quantitatively
    • While the runs happen in the background, draft some quantitative evals if there aren't any (if there are some, you can either use as is or modify if you feel something needs to change about them). Then explain them to the user (or if they already existed, explain the ones that already exist)
    • Use the eval-viewer/generate_review.py script to show the user the results for them to look at, and also let them look at the quantitative metrics
  • Rewrite the skill based on feedback from the user's evaluation of the results (and also if there are any glaring flaws that become apparent from the quantitative benchmarks)
  • Repeat until you're satisfied
  • Expand the test set and try again at larger scale

Your job when using this skill is to figure out where the user is in this process and then jump in and help them progress through these stages. So for instance, maybe they're like "I want to make a skill for X". You can help narrow down what they mean, write a draft, write the test cases, figure out how they want to evaluate, run all the prompts, and repeat.

On the other hand, maybe they already have a draft of the skill. In this case you can go straight to the eval/iterate part of the loop.

Of course, you should always be flexible and if the user is like "I don't need to run a bunch of evaluations, just vibe with me", you can do that instead.

Then after the skill is done (but again, the order is flexible), you can also run the skill description improver, which we have a whole separate script for, to optimize the triggering of the skill.

Cool? Cool.

Read the full file on GitHub · 489 lines

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. 2d ago First seen · 489 lines · 63 tokens per session scan A 1ba874c5ab0e

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository Cratis/AI (2 stars, last pushed 4d ago), licensed MIT. It adds 63 tokens to every session and 7,372 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to skill-creator, differing in 68 lines, and is treated as a copy.

Related

Other skills, from other repositories

skill-creator

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Cratis/VerticalSlices · 63 tokens

ship-changes

Ship staged or unstaged local changes: create a branch, make logical commits, push to origin, open a PR with the correct description and label, merge it, close the issues it resolves, and delete the branch locally and on origin. Use whenever the user asks to commit, push, create a PR, ship, or land changes.

Cratis/VerticalSlices · 72 tokens

add-concept

Use this skill when asked to create a strongly-typed domain identifier or value (such as ProjectId, AuthorName, InvoiceNumber) in a Cratis-based project. Produces a ConceptAs record with the correct conversions and sentinel values.

Cratis/VerticalSlices · 54 tokens

cratis-command

Step-by-step guidance for creating a Cratis Arc command — [Command] record, Handle() method, CommandValidator, proxy generation, and React .use() hook with CommandDialog. Use when adding or creating a command, wiring up a form or button to the backend, working with IEventLog, CommandResult, CommandValidator…

Cratis/VerticalSlices · 80 tokens

cratis-readmodel

Step-by-step guidance for creating a Cratis Chronicle read model from scratch — defining events, choosing between projection and reducer, [ReadModel] record with static query methods, and the generated TypeScript proxy in React. Use when creating a read model, working with [EventType], [ReadModel], IProjectionFor…

Cratis/VerticalSlices · 100 tokens

add-traces

Use this skill when asked to add OpenTelemetry tracing to a class in a Cratis Chronicle Kernel project. Produces Traces.cs companion files using the [Span] source-generator pattern from Cratis.Traces, registers IActivitySource as a keyed DI service, and injects it into the target class.

Cratis/VerticalSlices · 73 tokens