artifacts
Type registry, schemas, and content guidance for discovery artifacts — objectives, opportunities, ideas, assumptions, experiments, critiques, memos. 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.
68
85%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
85%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 well-crafted skill description that clearly defines its scope around discovery artifact type management, explicitly states when to use it (authoring, validating, resolving types) and when not to (simple reads). Its main weakness is that the trigger terms lean toward internal/technical vocabulary rather than natural user language, which could reduce discoverability when users phrase requests casually.
Suggestions
Add more natural user-facing trigger phrases like 'create a new memo', 'draft an experiment', 'write up an opportunity' to improve discoverability from casual user requests.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and artifact types: 'type registry, schemas, and content guidance' for 'objectives, opportunities, ideas, assumptions, experiments, critiques, memos' with actions like 'authoring a new artifact, validating one, or resolving the type system.' | 3 / 3 |
Completeness | Clearly answers both what ('Type registry, schemas, and content guidance for discovery artifacts') and when ('Load when authoring a new artifact, validating one, or resolving the type system'), and even includes a negative trigger ('For simple reads, read the artifact file directly without loading this skill'). | 3 / 3 |
Trigger Term Quality | Includes domain-specific terms like 'objectives, opportunities, ideas, assumptions, experiments, critiques, memos' and 'type registry, schemas,' but these are somewhat specialized. Users might naturally say 'create an experiment' or 'write a memo' but might not use terms like 'type registry' or 'resolving the type system.' Missing common user-facing variations. | 2 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche around discovery artifact type systems and schemas. The explicit enumeration of artifact types (objectives, opportunities, ideas, assumptions, experiments, critiques, memos) and the negative guidance for simple reads make it very unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
85%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-crafted entry-point skill that serves as a clean registry and routing layer for discovery artifacts. Its strengths are exceptional progressive disclosure, lean token usage, and a clear path discipline section that prevents common errors. The main gap is that the authoring workflow, while clearly sequenced, lacks a concrete inline example of what a finished artifact looks like, requiring the reader to always follow references for actionable content.
Suggestions
Consider adding one brief inline example (e.g., a minimal objective or assumption artifact with frontmatter) to make the authoring workflow more immediately actionable without requiring a reference file lookup.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Every section earns its place. The type registry table is dense and scannable, path discipline is a necessary constraint Claude wouldn't know, and the authoring workflow is minimal. No unnecessary explanations of what discovery artifacts are conceptually. | 3 / 3 |
Actionability | The authoring workflow provides clear steps but remains at a procedural level without executable code or concrete examples of artifact content. The type registry table is actionable for path resolution, but a user authoring an artifact must follow references to get actual schemas and content guidance — the skill itself doesn't show a concrete example of a completed artifact or template. | 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 guard before destructive writes. The path discipline section explicitly handles the error case of non-conforming paths with a feedback loop. | 3 / 3 |
Progressive Disclosure | Excellent hub-and-spoke structure: the type registry table provides one-level-deep references to per-type schemas, with cross-cutting concerns cleanly separated into model.md and guidelines.md. Navigation is clear and well-signaled with a table format and a dedicated cross-cutting references section. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
81%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
- Commit
632c389
- Reviewed
Table of Contents
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.