idea-discovery
Workflow 1: Full idea discovery pipeline. Orchestrates research-lit → idea-creator → novelty-check → research-review to go from a broad research direction to validated, pilot-tested ideas. Use when user says \"找idea全流程\", \"idea discovery pipeline\", \"从零开始找方向\", or wants the complete idea exploration workflow.
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Critical
Do not install without reviewing
Quality
Discovery
100%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 communicates what the skill does (orchestrates a four-stage research idea discovery pipeline), when to use it (with explicit bilingual trigger phrases), and how it's distinct from other skills (named sub-skills, specific workflow scope). The bilingual trigger terms are a notable strength for serving a multilingual user base.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: orchestrates a named pipeline of four distinct stages (research-lit → idea-creator → novelty-check → research-review) and describes the end-to-end transformation from 'broad research direction' to 'validated, pilot-tested ideas'. | 3 / 3 |
Completeness | Clearly answers both 'what' (orchestrates four named sub-skills to go from broad direction to validated ideas) and 'when' (explicit 'Use when' clause with specific trigger phrases and a general condition about wanting the complete workflow). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms in both Chinese and English that users would actually say: '找idea全流程', 'idea discovery pipeline', '从零开始找方向', and 'complete idea exploration workflow'. Good coverage of bilingual variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific pipeline name, the enumeration of four sub-skill stages, and unique bilingual trigger terms like '找idea全流程'. Unlikely to conflict with other skills given its clear niche as a full orchestration workflow. | 3 / 3 |
Total | 12 / 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-structured orchestration skill with excellent workflow clarity, strong actionability through concrete commands and checkpoint templates, and good progressive disclosure via delegation to sub-skills. Its main weakness is moderate verbosity—the 'What this does' bullet lists and lengthy checkpoint dialogue templates could be tightened without losing clarity. Overall it's a high-quality pipeline skill that clearly guides Claude through a complex multi-phase research workflow.
Suggestions
Trim the 'What this does' bullet lists under each phase to 1-2 lines max, since the sub-skill names and descriptions already convey the purpose.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200 lines) with some redundancy—e.g., 'What this does' sections repeat information that could be inferred from the sub-skill names, and checkpoint dialogue templates are verbose. However, much of the content is genuinely necessary for orchestrating a complex multi-phase pipeline, so it's not egregiously padded. | 2 / 3 |
Actionability | Each phase has concrete invocation commands (e.g., `/research-lit "$ARGUMENTS"`), explicit checkpoint dialogue templates, clear branching logic for user responses, and a complete final report template with markdown structure. The constants section provides specific, overridable defaults. This is copy-paste ready for an orchestration skill. | 3 / 3 |
Workflow Clarity | The 5-phase pipeline is clearly sequenced with explicit checkpoints between phases, feedback loops (user requests changes → re-run phase), early termination criteria (kill ideas early, eliminate non-novel ideas), and branching logic (AUTO_PROCEED, lite mode). Validation is built into multiple phases (novelty check, reviewer scoring, pilot experiments). | 3 / 3 |
Progressive Disclosure | The skill acts as an orchestration overview that delegates to sub-skills (`/research-lit`, `/idea-creator`, `/novelty-check`, `/research-review`, `/research-refine-pipeline`) rather than inlining their details. Output files are clearly referenced (`IDEA_REPORT.md`, `refine-logs/FINAL_PROPOSAL.md`, etc.), and the 'Composing with Workflow 2' section provides clear navigation to related workflows. | 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.