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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is a well-structured orchestration skill: highly actionable with concrete sub-skill invocations and templates, clearly sequenced phases with checkpoints and feedback loops, and clean one-level-deep references. The main weakness is verbosity from restating the pipeline and embedding full dialog/report templates that could be condensed.

Suggestions

Remove redundant restatements of the pipeline diagram — it appears in the overview, the Phase 5 report template, and the Composing section; keep one canonical version and reference it.

Condense the checkpoint dialog templates to the essential prompts rather than full scripted blocks, or move the complete report markdown template into a reference file to slim the SKILL.md body.

Tighten the repeated 'What this does' bullet lists where they duplicate information already conveyed by the invocation command and constants.

Dimension	Reasoning	Score
Conciseness	The body is task-focused and avoids explaining concepts Claude already knows, but the pipeline is restated three times (overview diagram, Phase 5 report template, Composing section) and the checkpoint dialog templates plus the full report template add bulk that could be tightened, fitting the 'mostly efficient but could be tighter' anchor rather than the lean level 3.	2 / 3
Actionability	Provides copy-paste-ready invocations (e.g. `/research-lit "$ARGUMENTS"`, `/novelty-check "[top idea 1 description]"`), concrete constants (PILOT_MAX_HOURS, MAX_TOTAL_GPU_HOURS), exact checkpoint wording, and a full markdown report template — fully executable and specific.	3 / 3
Workflow Clarity	The multi-step process is clearly sequenced into Phases 1–5 with explicit 🚦 checkpoints between phases, feedback loops for error recovery ("repeat until the user is satisfied", "repeat until the user selects at least 1 idea"), and validation gates (pilot signal, novelty elimination), matching the anchor for clear sequence with explicit validation and feedback loops.	3 / 3
Progressive Disclosure	No bundle files are present, but the body is well organized into overview/constants/phases/output sections and keeps references one level deep (the shared Output Protocols links are clearly signaled under a dedicated section), so navigation is easy and no monolithic or deeply nested references appear.	3 / 3
	Total	11 / 12 Passed

Description

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.

The description is strong: it states concrete capabilities via the named sub-skill chain, gives an explicit Use-when trigger list in both languages, and occupies a distinctive niche. It uses correct third-person voice throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions by naming the orchestrated chain "research-lit → idea-creator → novelty-check → research-review" and the end state of producing "validated, pilot-tested ideas", matching the anchor for listing several specific concrete actions.	3 / 3
Completeness	Explicitly answers both what it does (full idea discovery pipeline from broad direction to validated pilot-tested ideas) and when to use it via an explicit "Use when user says ..." clause, so it is not capped at 2.	3 / 3
Trigger Term Quality	Includes natural phrases a user would actually say in both Chinese ("找idea全流程", "从零开始找方向") and English ("idea discovery pipeline", "complete idea exploration workflow"), giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche ("Workflow 1: idea discovery pipeline") with distinctive bilingual triggers unlikely to fire for unrelated skills, so conflict risk is low.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 3 suspicious	Warning

	Total	15 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Commit: fe5963c

Reviewed: about 16 hours ago

Table of Contents

Discovery Implementation Validation

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.