Orkas is a desktop application for commanding a team of AI agents through one chat, with a commander model assigning work to specialist agents in parallel or in sequence. People use it to coordinate research, writing, presentations, and software tasks while keeping files on their computer. The catalogue includes skills for extending the agents available to Orkas.
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 Orkas-AI/Orkas --skill skill-creatorgit clone --depth 1 https://github.com/Orkas-AI/OrkasWrote 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/orkas-ai/orkas/skill-creator)<a href="https://agentmods.dev/skills/orkas-ai/orkas/skill-creator"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/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/orkas-ai/orkas/skill-creator"><img src="https://agentmods.dev/badge/skills/orkas-ai/orkas/skill-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00003 | $0.01563 |
| Opus 5 | $0.00002 | $0.00781 |
| Sonnet 5 | $0.00001 | $0.00313 |
| Haiku 4.5 | $0.00000 | $0.00156 |
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.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
skill-creator
Create, edit, or faithfully import a custom Skill through host-owned metadata tags, <<<skill-file>>> whole-file blocks, or the native package importer. Do not mutate the Skill directory with generic file or shell tools.
Read only the reference needed for this request
Before authoring, read the matching reference through this Skill's read ref:
- New Skill, SKILL.md body rewrite, new reference, or bundled script → authoring.md.
- Name, description, category, routing hints, or any SKILL.md frontmatter work → metadata.md.
- URL, local directory, ZIP, attachment, pasted existing Skill, or any source-preserving import → importing.md and metadata.md.
- File deletion or imported-package cleanup → file-deletion.md.
Do not read unrelated references. A category-only edit needs only metadata.md; a body-only guide edit normally needs only authoring.md; an import needs importing.md plus metadata.md.
Routing gate
Explicit creation intent required. Use this Skill only when the user explicitly asks to create, edit, convert into, or import a Skill, or when already inside a bound Skill editor. Do not consult this skill for a plain "install this URL / install this GitHub repo / add this project" request. A runnable external package belongs to package-installer unless the user explicitly wants a portable custom Skill. If that outcome is genuinely ambiguous, ask one concise clarification.
Non-negotiable protocol
- Use host-owned mutation paths only. Use
import_skill_packagefor an explicitly supplied local Skill directory/ZIP when available, metadata tags for metadata-only changes, and<<<skill-file>>>for changed file content. Never useedit_file,write_file, or shell redirects under the Skill directory. - Whole-file replacement. Every
<<<skill-file>>>block replaces one complete relative file. Read an existing file before changing it; a partial body erases omitted content. - Protocol completeness beats prose depth. Close every file block with
>>>on its own line and close the outer</skill>before optional user-visible prose. If response space is tight, shorten the Skill body; never truncate or omit a protocol delimiter. - No protocol files. Do not dump
<skill>,<skill-meta>, or file blocks into the workspace. The host parses them inline. - One container per Skill. Multiple containers are legal only when the request or source contains multiple distinct Skills. Never merge multiple source
SKILL.mdfiles into one Skill. - Skills are independent. Do not name, invoke, or read another Skill from this Skill's body, references, scripts, or examples. Orchestration belongs to the caller.
- Use the user's UI language for newly authored human-readable instructions and user-visible prose. Keep frontmatter keys, identifiers, paths, commands, and code unchanged. Imported prose remains faithful by default.
- The host owns completion. A valid
<skill>container or file block only requests a mutation. Only a successful host result proves it was applied; before that, or after a failed or omitted mutation, never say the Skill is created, updated, saved, ready, or available. If visible prose is useful, use pending wording such as “将创建” or “已提交，等待应用”.
What ships with it
4 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.
- 8d ago First seen · 108 lines · 3 tokens per session scan A 587b246c0584
skill-creator is a skill published in the GitHub repository Orkas-AI/Orkas (1,885 stars, last pushed yesterday), licensed MIT. It adds 3 tokens to every session and 1,563 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
tutti-workspace-app-factory
Create, convert, or repair one Tutti workspace app as either a self-contained publishable package under package/ or a Chrome-style local debug app under .tutti/dev-app/. Use for mention://workspace-app-factory/create handoffs, mention://workspace-app-factory handoffs, standalone app generation, adapting existing…
tutti-ui-system
Use when working with @tutti-os/ui-system components, replacing local UI with shared components, querying component ids or metadata, promoting UI into shared base or business components, or maintaining UI-system storyboard inventory.
tutti-agent-workspace-app
Build or evolve a complex agent-enabled Tutti workspace app repository. Use for Tutti apps with web/server/shared monorepos, @tutti-os/agent-acp-kit local agent runtimes, kit-owned TUTTICLI agent/composer discovery, dynamic agent catalogs, run-scoped MCP tool gateways, app-owned package builders, web-first debugging…
takt
A workflow engine that runs a task through a sequence of steps defined in a YAML file, using separate coding agents for the work.
takt
A workflow engine for coordinating multiple coding agents. It reads a YAML workflow, a text configuration format, and moves agents through its defined steps and rules.
create-coordclaw-team
A Skill for creating a CoordClaw multi-agent collaborative team. Through an 8-step standardized process, from requirement gathering to team validation, rapidly build a complete AI team.