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

80%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/skills-codex/idea-discovery/SKILL.md

Quality

Content

81%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 thorough, highly actionable orchestration skill with excellent workflow sequencing, explicit validation via an evidence gate, and concrete commands throughout. Its main weakness is mild verbosity from restating sub-skill behavior and inline templates that could be extracted.

Suggestions

Trim the per-phase "What this does" bullets to only the orchestration-relevant deltas, since Claude can read each sub-skill's own SKILL.md.

Move the Phase 5 final-report template and the reference-paper summary template into reference files (e.g., references/IDEA_REPORT_TEMPLATE.md) and link to them.

Drop or tighten self-evident Key Rules ("Document everything", "Be honest with the reviewer") in favor of the operational rules that remain.

Dimension	Reasoning	Score
Conciseness	Mostly efficient operational content (constants, artifact locators, checkpoint prompts), but "What this does" bullets restate each sub-skill's behavior and Key Rules includes platitudes like "Document everything" and "Be honest with the reviewer" that could be trimmed. Not a 4 because the over-explanation is more than minor.	3 / 5
Actionability	Provides copy-paste-ready sub-skill invocations (e.g., `/research-lit "$ARGUMENTS" — composed: idea-stage/IDEA_REPORT.md`), an executable gate command (`python3 <resolved-idea_discovery_gate.py> . <run_id> --report …`), concrete report templates, and specific numeric constants covering the common cases.	5 / 5
Workflow Clarity	A clearly sequenced multi-phase pipeline (Phase 0 → 5.6) with explicit 🚦 checkpoints between phases, feedback loops for user-requested changes, and a deterministic evidence gate (BLOCKED on missing evidence, re-run gate on resume). Batch GPU pilots carry validation (pilot signal + novelty check + gate), so the destructive/batch cap does not apply.	5 / 5
Progressive Disclosure	Well-organized headers with clearly-signaled one-level-deep references to `../shared-references/*.md` and `templates/RESEARCH_CONTRACT_TEMPLATE.md`; no bundle dirs (references/scripts/assets) are present. Not a 5 because several full report templates are inlined in SKILL.md rather than split into reference files.	4 / 5
	Total	17 / 20 Passed

Description

78%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 well-constructed description that explicitly covers both what the skill does and when to use it, with multiple natural trigger phrases across two languages. It could enumerate more concrete actions and tighten against overlap with sibling research-pipeline skills.

Suggestions

List 2-3 concrete pipeline actions (e.g., 'survey literature, brainstorm and pilot-test ideas, verify novelty, refine into an experiment plan') to raise specificity.

Distinguish from /research-pipeline in the description itself (e.g., note this is the idea-exploration front end, not the full end-to-end run).

Dimension	Reasoning	Score
Specificity	Names the domain and the input→output journey ("go from a broad research direction to validated, pilot-tested ideas"), implying a couple concrete actions, but does not list several specific concrete actions. Not a 4 because it describes the pipeline arc rather than enumerating distinct actions.	3 / 5
Completeness	Explicitly answers both what ("Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas") and when ("Use when user says …") with concrete trigger phrases. Voice is third-person with no first/second-person penalty.	5 / 5
Trigger Term Quality	Includes several natural trigger phrases in two languages ("找idea全流程", "idea discovery pipeline", "从零开始找方向", "complete idea exploration workflow") with good synonym coverage. Not a 5 because a few natural variants are missing and no file-extension-style triggers apply.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (idea discovery) with distinctive multi-language triggers; minor overlap risk with closely related research-pipeline skills. Not a 5 because the "complete idea exploration workflow" phrasing is somewhat broad relative to sibling research skills.	4 / 5
	Total	16 / 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: 4 suspicious	Warning

	Total	15 / 16 Passed

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