artifacts

Type registry, schemas, and content guidance for development artifacts — projects, epics, stories, tasks, specs, ADRs, spikes, work-items, workstreams, milestones. Load when authoring a new artifact, validating one, or resolving the type system. For simple reads (get/list/find), read the artifact file directly without loading this skill.

Quality

92%

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

85%Scale 1-3

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

This is a well-structured registry/routing skill that efficiently organizes a complex type system with clear navigation to detailed references. Its main strength is the concise type registry table, explicit path discipline rules, and clean progressive disclosure. Its weakness is that the authoring workflow, while clearly sequenced, lacks any concrete examples or template snippets — all substantive content is delegated to referenced files, making the skill less self-contained for actionability.

Suggestions

Add a brief concrete example of a minimal artifact (e.g., a task or work-item) showing the expected frontmatter/structure, so the skill is partially self-contained without requiring a file lookup for every authoring action.

Dimension	Reasoning	Score
Conciseness	Every section earns its place. No unnecessary explanations of what artifacts are or how markdown works. The type registry table is dense and informative. The path discipline section adds genuine value by addressing a known failure mode. No padding or redundant context.	3 / 3
Actionability	The authoring workflow gives clear steps and the type registry provides concrete paths and references, but the actual content guidance is delegated entirely to per-type reference files. There are no concrete examples of artifact content, no template snippets, and no executable commands — the skill is a routing layer rather than a self-contained actionable guide.	2 / 3
Workflow Clarity	The 5-step authoring workflow is clearly sequenced with an explicit validation checkpoint ('Show before writing' in step 4) and a conflict-surfacing rule in Path Discipline that acts as a feedback loop before destructive writes. The path discipline section explicitly handles the error case of non-conforming paths.	3 / 3
Progressive Disclosure	Excellent progressive disclosure structure: a concise overview table with one-level-deep references to per-type files (project.md, epic.md, etc.) and cross-cutting references (model.md, guidelines.md). Navigation is clear and well-signaled. Content is appropriately split between the overview and detailed reference files.	3 / 3
	Total	11 / 12 Passed

Description

100%Scale 1-3

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

This is a strong skill description that clearly defines its scope around artifact type schemas and content guidance, lists comprehensive trigger terms covering many artifact types, and explicitly states both when to use it and when NOT to use it. The negative trigger guidance ('For simple reads...') is a particularly effective addition that reduces conflict risk. Uses appropriate third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions and artifact types: 'Type registry, schemas, and content guidance' for 'projects, epics, stories, tasks, specs, ADRs, spikes, work-items, workstreams, milestones.' Also specifies authoring, validating, and resolving the type system as distinct actions.	3 / 3
Completeness	Clearly answers both 'what' (type registry, schemas, content guidance for development artifacts) and 'when' ('Load when authoring a new artifact, validating one, or resolving the type system'). Also includes a helpful negative trigger ('For simple reads... read the artifact file directly without loading this skill').	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'projects, epics, stories, tasks, specs, ADRs, spikes, work-items, workstreams, milestones, authoring, validating, artifact, type system.' These are terms developers naturally use in project management contexts.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with a clear niche around artifact type schemas and validation. The explicit exclusion of simple read operations further reduces conflict risk with other skills that might handle basic file reading. The enumerated artifact types create a well-defined boundary.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 9 / 11 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: audenaert/etak
Path: develop/skills/artifacts/SKILL.md
Commit: 632c389

Reviewed: 19 days 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.