skill-creator

skill-creator is a skill for Claude Code, Codex from dzhokhov/markdown-agent-vault-ru. It costs 62 tokens per session (4,794 once invoked), scanned A, original, MIT.

A guide for creating or improving reusable skills for coding agents, including their instructions, descriptions, supporting files, and evaluation process.

In plain words
What is it for?
Use it to design a new skill, edit an existing one, improve its triggering description, add resources, or test how well it performs.
Why use it?
It helps make a skill easier to trigger correctly and more reliable across many conversations instead of relying on a one-off prompt.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to design a new skill, edit an existing one, improve its triggering description, add resources, or test how well it performs.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dzhokhov/markdown-agent-vault-ru/skill-creator
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.

Any agent
npx skills add dzhokhov/markdown-agent-vault-ru --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/dzhokhov/markdown-agent-vault-ru

Made for: Claude Code, Codex.

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-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/skill-creator/github.svg)](https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/skill-creator)
Your own site
<a href="https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/skill-creator"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/skill-creator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for skill-creator

Your own site · 80×15
<a href="https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/skill-creator"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,794 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00062 $0.04794
Opus 5 $0.00031 $0.02397
Sonnet 5 $0.00012 $0.00959
Haiku 4.5 $0.00006 $0.00479

Measured 8d ago against content hash 37e25dd11302, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d ago.

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.

skills/skill-creator/SKILL.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Creator

A skill for designing, writing, testing, and iterating on skills. The job here is craft — a skill is a small piece of evergreen instruction that will run thousands of times across thousands of conversations, so it has to be lean, well-aimed, and not surprising.

This skill is written to be agent-agnostic. It assumes only the minimum that any LLM agent has: the ability to read text, write text, and converse with a user. Everything else (subagents, file system, browser, bundled scripts, CLI tools) is treated as optional capability that may or may not be present. Each stage describes what to do at the methodology level, then notes how to accelerate it if specific capabilities are available.

The mental model in one paragraph

A skill is metadata plus a body. The metadata (name + description) is a router — it decides whether the skill enters context at all. The body is a working agreement with the model that fires once routed. Bundled resources (scripts/, references/, assets/) are deferred load: they cost nothing until the skill explicitly reaches for them. Your job as skill author is to put the minimum into the always-loaded layers and push everything else down. Most bad skills fail because they violate that — they leak operational detail into the body, or stuff trigger logic into prose instead of the description.


Capability profile

Before starting, take stock of what your runtime offers. Each stage uses the strongest available capability and falls back gracefully.

Capability If present If absent
File system Save artifacts (SKILL.md, evals, results) to disk Hold drafts in conversation; ask the user to copy out
Subagents / parallel tasks Run with-skill and baseline tests in parallel Run them in series, one at a time
Browser / display Open eval viewer for the user to review Present test outputs inline in the conversation
Bundled scripts (Python) Use them as accelerators where mentioned Do the equivalent work directly: write small ad-hoc scripts, or do it manually
claude CLI / programmatic agent invocation Run automated description-optimization loops Optimize description by hand using a small set of manual trials
Packaging tooling (present_files, .skill archive) Hand the user a single file Hand the user the directory path; they can zip it themselves

Read the full file on GitHub · 349 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. 8d ago First seen · 349 lines · 62 tokens per session scan A 37e25dd11302

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository dzhokhov/markdown-agent-vault-ru (2 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 4,794 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

pos-verify

Use this immediately after files are created, edited, moved, deleted, or materially rewritten inside PersonalOS. Verifies that new truth was routed to the correct owner, written in the correct file shape, and still follows POS conventions. Do NOT use for whole-vault deep audits; use system-health-check.

vincentmumme/personalos-boilerplate · 65 tokens

skillify

Use this when {{username}} asks to skillify a repeated workflow, determine whether it deserves a reusable PersonalOS skill, or harden an existing workflow into a tested resolver-reachable capability. Do NOT use for one-off notes, ordinary execution, or already-specified skill authoring; use write-skill.

vincentmumme/personalos-boilerplate · 66 tokens

write-skill

Use this when the user wants to create a new shared PersonalOS skill under skills/ or revise a specified PersonalOS skill and the scope is already clear. Do NOT use for raw workflow capture or deciding whether work should become a skill; use skillify first. Do NOT use for repo-local or agent-local skills unless…

vincentmumme/personalos-boilerplate · 78 tokens

priority-dashboard

Use this to rebuild, inspect, or temporarily steer {{username}}'s current PersonalOS priority dashboard from canonical Actions, Attention Triggers, and owner context. Do NOT use it to create, complete, or independently manage tasks; use task-manager for Action and Trigger lifecycle changes.

vincentmumme/personalos-boilerplate · 60 tokens

lint-brain

Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".

michaeljauk/brain-starter · 56 tokens

ingest-article

Ingest an article from a URL or raw text into the brain vault. Extracts key knowledge, determines placement, creates or updates notes, and links to relevant projects. Use when the user shares a URL or text and wants to absorb it into their knowledge base.

michaeljauk/brain-starter · 58 tokens