Sigistry Plugin Catalog (formerly Claude Registry)

Get a verified skill (with portable source)

get_skill

Read-onlyIdempotent

Get one Sigistry skill by name, including the full raw SKILL.md source. The source is portable: it can be applied directly in any SKILL.md-aware agent (Claude Code, Claude Desktop, and others) without installing anything, or installed natively in Claude Code via the parent plugin, which keeps it verified and updated. The returned skill passed the Sigistry skill-safety check at the parent plugin's verification date.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`name`	Yes	the skill name, e.g. "assessment-scoring" (find names via search_skills)

Output Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	stable skill name, e.g. "assessment-scoring"
`repo`	No	author repo (owner/name), when externally hosted
`commit`	No	pinned commit the source is served from, when externally hosted
`plugin`	Yes	parent plugin id that ships this skill
`source`	Yes	the complete raw SKILL.md (frontmatter + body); null only if the fetch failed
`hosting`	Yes	"registry" (vendored here) or "external" (author repo, verified at a pinned commit)
`detailUrl`	Yes	human-readable page for this skill
`sourceUrl`	Yes	GitHub location of the skill directory
`description`	Yes	the skill trigger: when an agent should load it
`verification`	Yes	verification status of the parent plugin; prefer "verified"
`verifiedDate`	Yes	date of the verification run covering this skill
`installCommand`	Yes	Claude Code command installing the parent plugin (skill loads automatically)
`pluginCategory`	Yes	category of the parent plugin

TDQS

A4.3/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as read-only and idempotent, and the description adds meaningful behavior: returns the full portable source, is safe for direct use in any SKILL.md-aware agent, and has passed the Sigistry safety check. This goes beyond the schema and annotations without contradicting them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded with the core action, and each sentence earns its place by explaining the returned content, how to use it, and the verification guarantee. There is no fluff or repetition of schema details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter read-only tool with a rich output schema, the description covers what the tool returns, how portable the result is, how to discover valid names, and what verification status means. An agent has enough to decide when and how to call this correctly without further digging.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter 'name' already includes an example and guidance to use search_skills for discovery. The description adds little parameter semantics beyond 'by name' and does not need to, given the schema already carries the necessary detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the specific verb ('Get'), the resource ('one Sigistry skill'), and the key content ('full raw SKILL.md source'), making the purpose immediately clear. It also differentiates from sibling tools like search_skills and get_plugin by emphasizing portability and verification.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly explains how the result can be used (applied directly or installed natively) and references search_skills for finding skill names. It does not explicitly state when to prefer siblings like get_plugin over get_skill, but the context strongly implies the distinction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Sigistry Plugin Catalog (formerly Claude Registry) tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0

Disambiguation5/5

Each tool targets a distinct resource/action: plugin details, skill details, category listing, plugin search, skill search, and verification recipe. There is no meaningful overlap between tools, and the descriptions reinforce the boundaries clearly.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern (get_, list_, search_, verify_). The singular/plural variation is conventional and does not create confusion.

Tool Count5/5

Six tools is well-scoped for a plugin and skill catalog: discovery, detail retrieval, category browsing, and verification guidance are all represented without redundancy. Each tool earns its place.

Completeness5/5

This covers the core catalog workflow: browse categories, search plugins/skills, fetch details or portable skill source, and obtain verification instructions. The verify_plugin handoff to a local script is intentional and provides explicit next steps rather than a dead end.

Resources

Need Help?