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.
npx skills add desirecore/market --skill skill-creatorgit clone --depth 1 https://github.com/desirecore/marketWrote 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.
[](https://agentmods.dev/skills/desirecore/market/skill-creator)<a href="https://agentmods.dev/skills/desirecore/market/skill-creator"><img src="https://agentmods.dev/badge/skills/desirecore/market/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.
<a href="https://agentmods.dev/skills/desirecore/market/skill-creator"><img src="https://agentmods.dev/badge/skills/desirecore/market/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.03969 |
| Opus 5.5 | $0.00033 | $0.01588 |
| Sonnet 5.5 | $0.00017 | $0.00794 |
| Haiku 4.5 | $0.00008 | $0.00397 |
Grade A, and why
skill-creator scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -k -X POST "https://127.0.0.1:${PORT}/api/skills" \ How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-creator Skill
L0: One-line Summary
Guides users to package requirements, experience, and workflows into structured SKILL.md skill bundles.
L1: Overview and Use Cases
Capability
skill-creator is a Meta-Skill that gives an Agent the ability to create and edit Skills. Skills are modular, self-contained capability packages that, via SKILL.md, provide an Agent with domain knowledge, workflows, and tool integrations—turning the Agent from a general assistant into a domain expert.
Use Cases
- The user wants to package a repeatedly executed workflow into a reusable Skill
- The user wants to create a new Skill to teach the Agent a new capability
- The user wants to update an existing Skill and improve its effectiveness
- The user has shared reference material that needs to be organized into a structured Skill bundle
Core Value
- Distill experience: Solidify personal knowledge and workflows into reusable Skills
- Self-extension: Skills you create let the Agent's capabilities grow continuously
- Standardization: Generate standards-compliant SKILL.md files so the Skill system parses and distributes them correctly
L2: Detailed Specification
About Skills
Skills are modular, self-contained capability packages that provide an Agent with:
- Specialized workflows — multi-step processes for a specific domain
- Tool integrations — guidance for handling specific file formats or APIs
- Domain knowledge — company conventions, business logic, specialized schemas
- Bundled resources — scripts, reference docs, and asset files
Core Principles
Conciseness First
The context window is a shared resource. A Skill shares the context window with the system prompt, conversation history, other Skill metadata, and the user request.
Default assumption: the AI is already very capable. Only add what the AI does not already know. For each piece of information, ask yourself: "Does the AI really need this explained?" "Is this paragraph worth its Token cost?"
What ships with it
8 files 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.
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.
- 1mo ago Changed · +1 lines 7009264c8a46
- 1mo ago First seen · 416 lines · 83 tokens per session scan A dea036201c29
skill-creator is a skill published in the GitHub repository desirecore/market (2 stars, last pushed yesterday), licensed MIT. It adds 83 tokens to every session and 3,969 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
author-skill
Use when authoring a NEW rsc skill or editing an existing one — scoping it to one job, writing the description that decides whether it ever loads, splitting the body into references/, writing its evals, auditing it against the rubric. NOT building a product feature (that is specify) and NOT designing an agent loop…
skill-creator
Propose, test, validate, and improve Skill candidates without changing active files - generate reviewable SKILL.md and handler.js drafts, run test evaluations, and optimize descriptions for better triggering.
agent-writer
Write new agent definitions, skill files, and agent configurations. Use when someone asks to "create a new agent", "write a skill", "define an agent", or needs to create reusable AI agent instructions for any platform. This is the meta-skill for creating other skills and agents in the polyagent-skills format.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
skill-creator
Creating and authoring new AI skills with proper SKILL.md structure, YAML frontmatter validation, directory conventions, and registration workflow.
_template
Template for creating new Agentic OS skills.