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
Advisory
Suggest reviewing before use
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 the full pipeline orchestration capability, names each step in the workflow, and provides explicit bilingual trigger terms. It effectively distinguishes itself from individual sub-skills by emphasizing the end-to-end nature of the workflow. The description is concise yet comprehensive.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: orchestrates a named pipeline of four distinct steps (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 a four-step pipeline from broad research 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 user queries. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific named sub-tools (research-lit, idea-creator, novelty-check, research-review), the bilingual trigger terms, and the clear niche of full-pipeline idea discovery. Unlikely to conflict with individual step skills or other workflows. | 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 strong orchestration skill that clearly sequences a complex multi-phase pipeline with concrete invocation commands, well-defined checkpoints with feedback loops, and explicit constants/defaults. The progressive disclosure is excellent, delegating details to sub-skills and shared references. The main weakness is moderate verbosity — the checkpoint dialogue templates and 'What this does' sections could be tightened without losing clarity.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly long (~200 lines) and includes some redundancy — e.g., the checkpoint dialogue templates are verbose and the 'What this does' bullet lists partially repeat what the sub-skill names already convey. However, most content is pipeline-specific configuration and sequencing that Claude wouldn't inherently know, 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 markdown template. The constants section provides specific numeric thresholds. This is highly actionable and copy-paste ready. | 3 / 3 |
Workflow Clarity | The 5-phase pipeline is clearly sequenced with explicit checkpoints (🚦) at Phases 1, 2, and 4.5, including feedback loops (user requests changes → re-run phase, user unhappy → collect feedback and retry). Error recovery paths are specified (e.g., go back to Phase 1, re-run Phase 2, lite mode for weak results). Validation is built into the pipeline structure via novelty checks and reviewer scoring. | 3 / 3 |
Progressive Disclosure | The skill serves as a clear orchestration overview, delegating to sub-skills (`/research-lit`, `/idea-creator`, `/novelty-check`, `/research-review`, `/research-refine-pipeline`) and referencing shared protocols via one-level-deep links (output-versioning.md, output-manifest.md, output-language.md). Content is well-structured with headers and the pipeline diagram at the top provides immediate orientation. | 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
700fbe2
- 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.