ard-registry-builder

Build, validate, test, and update registries and catalogs that follow the Agentic Resource Discovery (ARD) specification. Use this whenever the user works with an ai-catalog.json, a capability manifest, an ARD/AIR catalog or Agent Registry, urn:air: identifiers, trustManifest/attestations, representativeQueries, or an Agent Finder / discovery service — including authoring a new manifest, scaffolding one, fixing schema or URN errors, running conformance/validation, probing a registry's /search, /explore, or /agents REST endpoints, reviewing trust and federation metadata, or preparing to publish at /.well-known/ai-catalog.json. Trigger it even when the user only says "ARD", "agentic resource discovery", "AI catalog manifest", "agent registry", or "make agents discoverable" without naming the file.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A high-quality, action-oriented skill body with executable commands, well-sequenced validation-gated workflows, and clean one-level-deep reference structure. The only gaps are minor conciseness trim opportunities and a dangling reference to a non-existent evals file.

Suggestions

Tighten the introductory framing and "Golden rules" section so each line is directive rather than explanatory, trimming the rationale that does not change Claude's behavior.

Remove or fix the "evals/evals.json" reference — the file is not present in the bundle, so the pointer currently leads nowhere and degrades navigation.

Dimension	Reasoning	Score
Conciseness	Lean and assumes Claude's intelligence — no padding about what JSON Schema or registries are — but the introductory conceptual framing and the "Golden rules (the why behind the checks)" rationale add a few explanatory tokens beyond pure instruction.	4 / 5
Actionability	Fully executable, copy-paste-ready commands with exact flags and arguments (e.g. "python scripts/new_catalog.py --template enterprise --publisher mycorp.com --host \"MyCorp AI\" --out ./ai-catalog.json") plus concrete code-to-fix mappings covering the common cases.	5 / 5
Workflow Clarity	Four clearly sequenced numbered workflows with explicit validation checkpoints and error-recovery feedback loops ("Run the validator first... Re-run until clean", "Re-validate... Treat 'passes validation' as the definition of done").	5 / 5
Progressive Disclosure	Clear overview body with well-signaled one-level-deep references (data-model.md, registry-api.md, validation-rules.md, publishing.md) whose paths all resolve to real bundle files, but the body references "evals/evals.json" which is not present in the bundle.	4 / 5
	Total	18 / 20 Passed

Description

100%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

An exceptionally complete description: third-person, concise yet specific, with a clear what-and-when structure and rich natural trigger terms including file names, identifiers, and endpoints. It is comprehensive and clearly distinguishable from other skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Build, validate, test, and update registries and catalogs", "authoring a new manifest, scaffolding one, fixing schema or URN errors", "probing a registry's /search, /explore, or /agents REST endpoints" — giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what ("Build, validate, test, and update registries and catalogs") and when ("Use this whenever...", "Trigger it even when the user only says 'ARD'...") with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms including synonyms and specifiers a user would actually say — "ai-catalog.json", "urn:air: identifiers", "ARD", "agentic resource discovery", "AI catalog manifest", "agent registry", "make agents discoverable", and "/.well-known/ai-catalog.json".	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (the ARD specification) with distinct triggers, named files, and endpoint paths, giving minimal conflict risk with other skills.	5 / 5
	Total	20 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: webmaxru/ai-native-dev
Path: skills/ard-registry-builder/SKILL.md
Commit: 0ddb6a6

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.