skill-creator

A guide for creating and improving reusable instructions called skills for a coding agent. It covers drafting them, testing how they behave, and fixing descriptions that do not activate them when expected.

In plain words
What is it for?
Use it to build a new skill, write test prompts, run skill evaluations, review results, and improve a skill that fails to trigger.
Why use it?
It gives you a repeatable way to turn an intended workflow into instructions and check whether the agent follows them. Some evaluation tools may require supporting files from the claude-mem plugin.

Cursor rule for Cursor

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 rules/anmolnagpal/devops-skills/skill-creator
Clone the repo
git clone --depth 1 https://github.com/anmolnagpal/devops-skills

Made for: Cursor.

Per session 7,458 This file is loaded in full into every session.
When invoked 7,458 The same file — it is already loaded in full.
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 $0.07458 $0.07458
Opus 5 $0.03729 $0.03729
Sonnet 5 $0.01492 $0.01492
Haiku 4.5 $0.00746 $0.00746

Measured yesterday against content hash 8ce8c9b48762, 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 yesterday.

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.

.cursor/rules/skill-creator.mdc · 494 lines

How it starts

The opening of the file, as written. The whole thing — 494 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creator

A skill for creating new skills and iteratively improving them.

Standalone vs. full install: The core workflow — Capture Intent, Write SKILL.md, draft Test Cases, and iterate — works fully in this repo. The eval runner, benchmarking, and description-optimization loop require supporting files (eval-viewer/, scripts/, agents/, assets/, references/) that ship with the claude-mem plugin's skill-creator. If claude-mem is installed, those sections work automatically. If it is not, skip the sections marked with script invocations and use the manual inline-review approach described in the Claude.ai-specific instructions below.

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 · 494 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. yesterday First seen · 494 lines · 7,458 tokens per session scan A 8ce8c9b48762

Subscribe to this mod's changes

skill-creator is a cursor rule published in the GitHub repository anmolnagpal/devops-skills (8 stars, last pushed 2d ago), licensed MIT. It adds 7,458 tokens to every session, about $0.0373 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.