Skills
Manage reusable instructions and package resources, then use them through the enabled Skills tools.
Browse & discover
Browse metadata, find a skill for a task, and read the exact revision before using it.
| Skill | Source | Description | Revision | |
|---|---|---|---|---|
| ace-step-text-to-music | local | Generate a song with the ACE-Step 1.5 audio service from an explicit style prompt plus lyrics, then report the persisted artifact and attachment receipt. | 7c36817e11b0 |
|
| control-plane-write-skills | local | Create, revise, organize, validate, and publish skills for the LLM control plane. Use when asked to write a new skill, turn a repeated workflow into a skill, repair an existing skill package, organize a skill collection, or import finished skills through the control plane MCP endpoint. | d2b89a23c177 |
|
| csharp-coding | local | Write, review, and refactor C# code following current .NET conventions. Use when creating or editing .cs files, implementing .NET console or library code, fixing compiler or analyzer warnings, or reviewing C# projects for structure and style consistency. | fdbcf238300d |
|
| flux2-text-to-image-workflow | local | Generate an image with the Flux 2 Klein service and document the observed process. | 34fbd8ac4a3a |
|
| json-schema-helper | local | Author, validate, and troubleshoot JSON Schema documents. Use when asked to write a JSON Schema for a payload or config file, validate JSON data against a schema, explain why a document fails validation, or choose the right draft version and keywords for a schema. | 2be36a838dae |
|
| markdown-formatter | local | Normalize and lint Markdown documents for consistent structure, whitespace and heading hierarchy. Use when asked to format, tidy, clean up, or lint a Markdown file, README, changelog, or notes document; also use before publishing docs to catch broken heading levels, inconsistent list markers, trailing whitespace and malformed tables. | 30832b975ca6 |
|
| pdf-summarizer | local | Summarize a PDF attachment supplied in the conversation, using only text the user or client actually provides. Use when asked to summarize, digest, outline, or extract key points from a PDF; also use when a PDF arrives as an attachment reference, a vault path, or a URL and the agent must decide whether it can be read at all before promising a summary. | 4c11d1296990 |
|
| storyboard-creation | local | Build a storyboard end to end in Storyboarder over MCP, driven by the harness's internal LLM rather than the calling agent's own prose. Use when turning a premise or story idea into a rendered storyboard, adding a telling to an existing universe, or writing contiguous beats with image and motion prompts that stay consistent with canon. Contains a definition of done, a cost order, and the specific failure modes that have caused incomplete or overpriced runs. | 78e2ce7a774a |
|
| storyboard-lore | local | Read, audit, and extend Storyboarder canon lore over MCP without corrupting it. Use when asked to review lore for contradictions or ambiguity, to check what a downstream agent will read literally, to add a canon note that fits an existing universe, or to explain why a storyboard beat cites something canon never said. Includes a definition of done so an audit is finished before it is reported. | 0be2ed9d2b1e |
|
| toml-formatter | local | Normalize and lint TOML configuration files for consistent structure, key ordering, spacing and quoting. Use when asked to format, tidy, clean up, or lint a TOML file such as Cargo.toml, pyproject.toml, a config file, or any .toml document; also use before committing config changes to catch duplicate keys, invalid table headers and inconsistent formatting. | 3c86c285255c |
Install & edit
Import all skills in a folder, import one package ZIP or SKILL.md, or create a skill here.
External-managed sources are read-only here. Folder import supports up to 1,000 skills, 10,000 selected files and 500 MiB of eligible package content per batch. Each package uses the existing size and resource limits. The editor supports up to 1 MiB; larger instructions use the REST publisher within configured limits. Package ZIP limit: 20 MiB compressed, 40 MiB expanded, 256 entries. Archive keeps the package outside the catalog for recovery.
Agent tool access
Enable the Skills tools under Agents & Tools. Each tool checkbox is the sole agent permission for that operation across configured sources. Which skills an agent may address is governed separately by per-skill enablement on that same page.
Enable skills_catalog, skills_discover, skills_activate,
skills_read_resource, and skills_status to list, find and read skills. Enable
skills_import to import packages into application-managed sources.
No additional source, skill-name or operation grants are needed for agent tool calls. Reading a script does not execute it. Per-agent skill enablement lives under Agents & Tools.
Skill groups
Named views over published skills. A group never grants access; it only names which skills it addresses. Enablement per agent happens under Agents & Tools.
Explicit groups list members by name and report group_member_missing when a package is
renamed or deleted. Selector groups compute membership from tags and a * glob, so composition can
change without an operator action. Repository groups materialize pinned content into a managed source; hosts
must be allowlisted below and pinned content is verified before import.
Sources & policy
Choose existing mounted directories and access rules. Saving a source cannot mount a host directory.
Policy file: /persist/agent-runtime/config/skills.json. External publishers must write complete
temporary files and atomically replace published files. Local setup attests to the application's own publisher.
API access
Create a separate bearer credential for REST clients. Identity comes from this credential, never request JSON.
| Label | Principal | Management | Expires |
|---|
REST: /api/skills/status, /catalog, /discover,
/activate, /resource. Use Authorization: Bearer … and snake_case JSON.
Creating a token does not grant source access.