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

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

88%Weight 40%Scale 1-5

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

A highly actionable, well-structured orchestration skill with explicit phase checkpoints, feedback loops, and concrete commands throughout. Its main weakness is mild template redundancy and a lack of bundled reference files to push detail off the main body.

Suggestions

Trim the Phase 5 report template and per-phase 'What this does' bullets to reduce redundancy, since the pipeline diagram and Key Rules already convey the essentials.

Extract the per-phase sub-skill behavior summaries into a references/ file linked from each phase, keeping the SKILL.md body as a lean orchestration overview.

Consolidate the checkpoint prompt templates into a single reusable block referenced once, rather than re-stating the AUTO_PROCEED handling at each checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean for its complexity, but the Phase 5 report template and the repeated 'What this does' bullets introduce some redundancy that could be trimmed.	4 / 5
Actionability	Each phase ships a concrete slash invocation ('/research-lit "$ARGUMENTS"'), specific tunable constants, and copy-paste checkpoint templates that cover the common cases.	5 / 5
Workflow Clarity	Phases 1-5 are clearly sequenced with explicit 🚦 checkpoints, feedback loops (user requests changes → refine and repeat), and validation/kill rules (timeouts, eliminate already-published ideas), satisfying the batch-operation validation requirement.	5 / 5
Progressive Disclosure	Content is well-sectioned and shared protocols are linked one level deep ('../../shared-references/...'), but most guidance is inlined and no bundle files (references/scripts/assets) exist to offload detail.	4 / 5
	Total	18 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, well-structured description that explicitly covers both what the skill does and when to trigger it, using natural multilingual phrases. It is mostly specific and distinct, with only minor coverage and overlap gaps.

Dimension	Reasoning	Score
Specificity	Names the concrete sub-skill chain ('research-lit → idea-creator → novelty-check → research-review') and the outcome ('validated, pilot-tested ideas'), but does not enumerate what each sub-skill does, leaving minor gaps in coverage.	4 / 5
Completeness	Clearly states what it does ('Orchestrates ... to go from a broad research direction to validated, pilot-tested ideas') and explicitly when to use it ('Use when user says ...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes several natural trigger phrases in both Chinese ('找idea全流程', '从零开始找方向') and English ('idea discovery pipeline') plus a descriptive fallback, though it lacks synonyms/file-extension-style terms.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (full idea discovery pipeline) with specific triggers, but 'complete idea exploration workflow' and the chained sub-skills create minor overlap risk with adjacent research-pipeline skills.	4 / 5
	Total	17 / 20 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
Path: skills/skills-codex-gemini-review/idea-discovery/SKILL.md
Commit: f4f20f9

Reviewed: 1 day 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.