idea-discovery

Workflow 1: Full idea discovery pipeline 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

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

77%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.

The content delivers a well-sequenced, checkpointed pipeline with concrete commands and strong validation/feedback loops. Its main weaknesses are a monolithic, somewhat verbose body that inlines material (gate mechanics, output hygiene) better suited to one-level-deep reference files, and em-dash command tokens that hurt literal copy-paste executability.

Suggestions

Move the per-stage evidence-gate mechanics and the 'Output hygiene' protocol into dedicated reference files under references/ (e.g., references/evidence-gate.md, references/output-hygiene.md), leaving SKILL.md as a concise overview that links to them one level deep.

Replace the em-dash '—' used as a CLI flag separator with literal '--' (e.g., '/research-lit "$ARGUMENTS" --sources: all,gemini --composed: ...') so command strings are copy-paste executable.

Trim repeated model-name restatements ('GPT-5.6-Sol xhigh' appears across multiple phases) into a single constant reference to reduce verbosity.

Dimension	Reasoning	Score
Conciseness	The body is dense and mostly earns its tokens (phases, constants, checkpoints, gate mechanics) without explaining concepts Claude already knows, but has some repetition (e.g., repeated 'gpt-5.6-sol'/'GPT-5.6-Sol xhigh' mentions and restated output-hygiene points), placing it above the efficient midpoint but short of lean 5.	4 / 5
Actionability	Provides concrete, mostly-executable invocations with exact flags and paths (e.g., '/research-lit "$ARGUMENTS" — sources: all, gemini — composed: ...' and the gate command), but uses an em-dash '—' instead of literal '--' in several command strings and retains bracketed placeholders, creating minor copy-paste gaps versus the 5 anchor.	4 / 5
Workflow Clarity	Phases 0 through 5.5 are clearly sequenced with explicit 🚦 checkpoints, AUTO_PROCEED fallbacks, retry/regeneration feedback loops, and a per-stage evidence gate with BLOCKED handling and pilot timeouts; the batch/destructive operations (parallel pilots, idea elimination) carry explicit validation, satisfying the cap rule and reaching the top anchor.	5 / 5
Progressive Disclosure	No bundle files (references/scripts/assets) exist, so the skill is effectively monolithic; references to shared-references and templates are one-level-deep and clearly signaled, but substantial detail (constants, gate mechanics, the output-hygiene protocol) is inlined in the ~460-line SKILL.md rather than split into separate reference files, matching the 'some structure, content that should be separate is inline' anchor.	3 / 5
	Total	16 / 20 Passed

Description

87%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.

The description is specific, bilingual-trigger-aware, and explicitly answers both what the skill does and when to invoke it, with minimal overlap risk. The only minor weakness is that the action list is not maximally comprehensive, which caps specificity and trigger_term_quality just below 5.

Dimension	Reasoning	Score
Specificity	Names the domain ('Full idea discovery pipeline') and concrete end-state actions ('go from a broad research direction to validated, pilot-tested ideas'), listing several specific actions rather than a comprehensive laundry list, so it sits above the 3 anchor but short of full 5 coverage.	4 / 5
Completeness	Clearly answers both 'what' (full idea discovery pipeline from broad direction to validated, pilot-tested ideas) and 'when' ('Use when user says ... or wants the complete idea exploration workflow') with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Provides explicit natural trigger phrases users would actually say ('找idea全流程', 'idea discovery pipeline', '从零开始找方向') including bilingual synonyms, but is missing a few additional common English variations, keeping it just below the comprehensive 5 anchor.	4 / 5
Distinctiveness Conflict Risk	Scoped to a specific 'Workflow 1' idea-discovery niche with distinct bilingual triggers, making it clearly distinguishable from adjacent research skills with minimal conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 7 suspicious	Warning

	Total	13 / 16 Passed

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
Path: skills/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.