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.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

77%

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

The body is a highly actionable, well-sequenced multi-phase workflow with concrete commands and validation checkpoints. Its main weaknesses are mild verbosity in a few rationale/repeated sections and the absence of progressive disclosure into bundle files despite its length.

Suggestions

Consolidate the Review Tracing guidance into one section instead of restating it in both Phase 2 and the closing Review Tracing section.

Tighten the Phase 3 justification block and remove explanatory asides that restate why a step exists, trusting Claude to infer rationale.

Extract the large IDEA_REPORT.md template and the spawn_agent prompt into referenced bundle files (e.g., references/report-template.md) so SKILL.md stays an overview.

Dimension	Reasoning	Score
Conciseness	Mostly efficient for a complex multi-phase workflow, but includes tightening opportunities: a lengthy Phase 3 rationale block, a Review Tracing section that repeats guidance already stated in Phase 2, and explanatory asides like "This avoids re-discovering what the user already knows."	2 / 3
Actionability	Provides fully executable, copy-paste-ready guidance: complete spawn_agent/send_input prompt blocks, a bash wiki-resolution script, the upsert_idea command with concrete flags, and a full report template.	3 / 3
Workflow Clarity	Phases 0–7 are clearly sequenced with explicit validation checkpoints (objective feasibility gate, pilot timeout handling, "STOP and ask them to narrow it") and feedback loops (re-ranking on empirical pilot evidence).	3 / 3
Progressive Disclosure	The 317-line body is monolithic with no bundle files (references/scripts/assets absent); references to external shared-references files are clearly signaled but the skill's own detailed content (report template, prompts) is inline rather than split into one-level-deep bundle files.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 pairs a concrete capability statement with an explicit, naturally-worded trigger clause covering multiple phrasings a user would say. The only minor gap is that it lists just two actions, leaving it slightly short of fully comprehensive specificity.

Dimension	Reasoning	Score
Specificity	Names two concrete actions ("Generate and rank research ideas") tied to a clear domain, matching the anchor that names domain and some actions but is not comprehensive; the 3-anchor example lists three or more specific actions.	2 / 3
Completeness	Explicitly answers both what ("Generate and rank research ideas given a broad direction") and when ("Use when user says…") with explicit triggers, matching the top anchor.	3 / 3
Trigger Term Quality	Includes natural phrases a user would actually say ("找idea", "brainstorm ideas", "generate research ideas", "what can we work on", "explore a research area"), giving good coverage of natural trigger terms.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (research idea generation) with distinct, domain-specific triggers unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 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 17 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.