idea-creator
Generate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
90
87%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Quality
Discovery
89%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-structured description with strong trigger term coverage (including bilingual terms) and a clear 'Use when' clause that makes it easy for Claude to select appropriately. The main weakness is that the 'what' portion could be more specific about the concrete actions performed beyond just 'generate and rank'. Overall, it's a solid description that would perform well in skill selection.
Suggestions
Expand the capability description with more specific actions, e.g., 'Generate and rank research ideas by evaluating novelty, feasibility, and publication potential given a broad direction.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (research ideas) and two actions (generate and rank), but doesn't elaborate on specific concrete actions like evaluating novelty, assessing feasibility, comparing against existing literature, or producing structured idea summaries. | 2 / 3 |
Completeness | Clearly answers both 'what' (generate and rank research ideas given a broad direction) and 'when' (explicit 'Use when' clause with multiple trigger phrases and a general condition about exploring research areas). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including bilingual triggers ('找idea'), informal phrasing ('brainstorm ideas', 'what can we work on'), and domain-specific terms ('research ideas', 'publishable directions', 'research area'). These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The skill occupies a clear niche around research idea generation and ranking, with distinct triggers like '找idea' and 'publishable directions' that are unlikely to conflict with general brainstorming or writing 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 strong, well-structured skill that provides a comprehensive research idea generation pipeline with clear phases, validation checkpoints, and concrete output templates. Its main weakness is moderate verbosity—some sections could be tightened without losing clarity. The actionability is excellent with specific agent prompts, defined constants, and a complete report template.
Suggestions
Tighten Phase 1 and Phase 3 descriptions by removing explanatory text that a capable model would already understand (e.g., 'This avoids re-discovering what the user already knows', 'This is the key differentiator from paper-only validation').
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is quite long (~200+ lines) and includes some unnecessary elaboration (e.g., explaining what a landscape map is, restating obvious research methodology). However, much of the content is genuinely instructive and specific to the workflow, so it's not egregiously verbose—just could be tightened in several places. | 2 / 3 |
Actionability | The skill provides highly concrete, executable guidance: specific agent spawn prompts with exact message templates, clear GPU allocation commands, defined constants with override syntax, specific search strategies, and a complete output template with markdown structure. The pilot experiment design includes concrete success criteria and timeout handling. | 3 / 3 |
Workflow Clarity | The 6-phase workflow is clearly sequenced with explicit validation checkpoints: novelty quick-checks in Phase 3, deep validation in Phase 4, pilot experiments with defined success metrics and timeout handling in Phase 5, and re-ranking based on empirical evidence. Feedback loops are present (kill pilots exceeding timeout, collect partial results, re-rank based on evidence, eliminate ideas that fail checks). | 3 / 3 |
Progressive Disclosure | The skill is well-structured with clear sections and references to companion skills (/novelty-check, /research-review, /run-experiment, /auto-review-loop) without nesting references deeply. The 'Composing with Other Skills' section at the end provides a clean navigation map. Content is appropriately self-contained for the main workflow while delegating specialized tasks to other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Commit
dc00dfb
- 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.