create-ideas
Generate ideas in one shot using creative sampling
42
28%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/sdd/skills/create-ideas/SKILL.mdQuality
Discovery
0%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 description is too vague and jargon-laden to be effective for skill selection. It fails to specify what kinds of ideas are generated, what 'creative sampling' means in practice, and when Claude should choose this skill. It would easily conflict with other creative or generative skills.
Suggestions
Specify concrete actions and outputs, e.g., 'Generates diverse brainstorming lists, creative concepts, or solution alternatives using high-temperature sampling techniques'.
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to brainstorm, generate ideas, come up with options, or needs creative suggestions in a single pass'.
Replace the jargon 'creative sampling' with a plain-language explanation or at least clarify what makes this skill distinct from general idea generation.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description is vague — 'generate ideas' is abstract and 'creative sampling' is unexplained jargon. No concrete actions like brainstorming techniques, output formats, or specific domains are listed. | 1 / 3 |
Completeness | The 'what' is vaguely stated ('generate ideas') and there is no 'when' clause or explicit trigger guidance at all. This should cap completeness at a maximum of 2 per the rubric, but the 'what' is also too weak to merit a 2. | 1 / 3 |
Trigger Term Quality | 'Generate ideas' is somewhat natural but extremely generic, and 'creative sampling' is technical jargon that users would not naturally say. Missing common variations like 'brainstorm', 'ideation', 'suggestions', etc. | 1 / 3 |
Distinctiveness Conflict Risk | 'Generate ideas' is extremely generic and could conflict with virtually any creative, brainstorming, or content generation skill. 'Creative sampling' adds slight specificity but is too opaque to serve as a distinguishing trigger. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a reasonable framework for idea generation with probability-based sampling, but suffers from ambiguous instructions (the bracketed placeholder) and lacks a concrete example of expected output format. The probability thresholds and diversity constraints are useful but would benefit from a sample input/output pair to make the skill fully actionable.
Suggestions
Add a concrete example showing a sample query and the expected 6-item output with probabilities to make the format unambiguous.
Resolve the ambiguous '[full distribution / tails of the distribution]' placeholder—choose one or explain when each applies.
Remove 'You are a helpful assistant' as it's unnecessary context Claude already knows.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary phrasing like 'You are a helpful assistant' which Claude already knows, and the bracketed '[full distribution / tails of the distribution]' is ambiguous rather than concise. Could be tightened. | 2 / 3 |
Actionability | Provides a structured format (6 items, probability thresholds, diversity constraints) but lacks a concrete example of expected output. The bracketed placeholder '[full distribution / tails of the distribution]' is vague and not actionable—it's unclear which option to use or what this means in practice. | 2 / 3 |
Workflow Clarity | The single-step task is reasonably clear with constraints on probability ranges and diversity, but there's no example output to validate against, and the ambiguous bracketed text creates confusion about the intended sampling strategy. | 2 / 3 |
Progressive Disclosure | This is a simple, single-purpose skill under 50 lines with no need for external references. The content is organized in a single clear section with bullet points, which is appropriate for its scope. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- NeoLabHQ/context-engineering-kit
- Commit
dedca19
- 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.