skill-creator

A guide for creating RoleX skills, which are instruction files that add a specific capability to a role-based AI system. It defines the required files, format, and connection between a skill and the procedure that uses it.

In plain words
What is it for?
Use it to create or update SKILL.md files, define their metadata and scenarios, and connect them to RoleX procedures.
Why use it?
It gives skill authors a consistent structure so the system can discover, load, and run new capabilities correctly.

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/deepractice/rolex/skill-creator
Any agent
npx skills add Deepractice/RoleX --skill skill-creator
Clone the repo
git clone --depth 1 https://github.com/Deepractice/RoleX

Made for: Claude Code, Codex.

Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,271 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 $0.00062 $0.01271
Opus 5 $0.00031 $0.00635
Sonnet 5 $0.00012 $0.00254
Haiku 4.5 $0.00006 $0.00127

Measured 2d ago against content hash b6d2a7781775, 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.

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 · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature: RoleX Skill Creator Create skills that follow the RoleX capability system. A skill is a SKILL.md file referenced by a procedure entry via ResourceX locator. Progressive disclosure: procedure summary at activate → full SKILL.md via skill(locator) → execution via use.

Scenario: What is a RoleX skill Given a role needs operational capabilities beyond its identity Then a skill is a SKILL.md file containing detailed instructions And a procedure is a Gherkin summary that references the skill via locator And the procedure is loaded at activate time — the role knows what skills exist And the full SKILL.md is loaded on demand via the skill tool

Scenario: Skill directory structure Given a skill lives under the skills/ directory Then the structure is: """ skills// ├── SKILL.md (required — detailed instructions in Gherkin) ├── resource.json (required — name, type: "skill", tag) └── references/ (optional — loaded on demand) └── .md """ And SKILL.md has YAML frontmatter with name and description And the body uses Gherkin Feature/Scenario format And references contain domain-specific details loaded only when needed

Scenario: The procedure-skill contract Given a procedure is trained to a role Then the Feature description contains the ResourceX locator for the skill And the Feature body summarizes what the skill can do And example procedure: """ Feature: Role Management https://github.com/Deepractice/DeepracticeX/tree/main/skills/role-management

    Scenario: What this skill does
      Given I need to manage role lifecycle
      Then I can born, teach, train, retire, and die roles
  """
And the description line is the locator — the skill tool resolves it via ResourceX

Feature: Skill Creation Process How to create a new RoleX skill step by step.

Scenario: Step 1 — Understand the scope Given you are creating a skill for a specific domain When you analyze what operations the skill should cover Then identify the concrete commands, parameters, and workflows And determine what the role needs to know vs what it already knows And only include information the role cannot infer on its own

Scenario: Step 2 — Write SKILL.md Given you understand the scope When you write the SKILL.md Then start with YAML frontmatter (name + description) And write the body as Gherkin Features and Scenarios And each Feature covers a logical group of operations And each Scenario describes a specific workflow or decision point And use Given/When/Then for step-by-step procedures And keep SKILL.md under 500 lines — split into references if needed

Scenario: Step 3 — Create resource.json Given SKILL.md is written When you create the resource manifest Then include name, type "skill", and tag version And example: """ { "name": "my-skill", "type": "skill", "tag": "0.1.0" } """

Scenario: Step 4 — Train the procedure Given the skill directory is ready When you train the procedure to a role Then use the train operation with Gherkin source And the Feature description MUST be the ResourceX locator for the skill And the Feature body summarizes capabilities for activate-time awareness And example: """ locator: "!individual.train" args: individual: "sean" id: "my-skill" content: "Feature: My Skill\n https://github.com/org/repo/tree/main/skills/my-skill\n\n Scenario: When to use\n Given I need to do X\n Then load this skill" """

Scenario: Step 5 — Test the skill Given the procedure is trained When you activate the role Then the procedure summary should appear in the activation output And calling skill with the locator should load the full SKILL.md And the loaded content should be actionable and complete

Read the full file on GitHub · 133 lines

Files

What ships with it

1 file 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. 2d ago First seen · 133 lines · 62 tokens per session scan A b6d2a7781775

Subscribe to this mod's changes

skill-creator is a skill published in the GitHub repository Deepractice/RoleX (35 stars, last pushed 5mo ago), licensed MIT. It adds 62 tokens to every session and 1,271 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 2026-08-30.

Related

Other skills, from other repositories

paperclip

Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.

paperclipai/paperclip · 43 tokens

omni-mcp

Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.

diegosouzapw/OmniRoute · 48 tokens

skill-creator

Create, install, or update skills in the workspace. Use when (1) installing a skill from a URL or remote source, (2) creating a new skill from scratch, (3) updating or restructuring existing skills. Always use this skill for any skill installation or creation task.

zhayujie/CowAgent · 61 tokens

add-resend

Add Resend (email) channel integration via Chat SDK.

nanocoai/nanoclaw · 16 tokens

codegen

Code generation utilities for json-render. Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props for @json-render/codegen.

vercel-labs/json-render · 38 tokens

agui-dotnet-sample-step

Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…

ag-ui-protocol/ag-ui · 168 tokens