ds-idea

Use when a quest needs concrete hypotheses, limitation analysis, candidate directions, or a selected idea relative to the active baseline.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/ds-idea/SKILL.md

Quality

Content

60%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 body is a thorough, well-structured research-ideation workflow with concrete tool calls, explicit gates, and well-signaled reference files. Its main weakness is heavy redundancy — the same ideation protocol is restated across multiple sections — which inflates token cost without adding guidance.

Suggestions

Consolidate the diverge/converge/refine guidance (currently restated in Stage purpose, Non-negotiable rules, Direction-shaping protocol, Creative-divergence protocol, Integrated ideation workflow, and Workflow steps) into a single canonical section; reference it from the others instead of repeating it.

Cut general methodology explanations Claude already knows (MECE, SCQA, pyramid principle, what a hypothesis is) or move them to a reference file; keep the body focused on the DeepScientist-specific artifact calls, gates, and thresholds.

Promote the inlined ideation-lens catalog and failure-mode/recovery-move lists into a reference file (alongside idea-generation-playbook.md) so the SKILL.md body stays a lean overview pointing to one-level-deep details.

Dimension	Reasoning	Score
Conciseness	Noticeably verbose: the diverge/converge/refine pattern and the '5-10' paper floor are restated nearly verbatim across seven overlapping sections, and general methodology Claude already knows (MECE, SCQA, pyramid principle) is re-explained.	2 / 5
Actionability	Provides concrete tool-call signatures (artifact.submit_idea, artifact.arxiv, memory.search), file paths, and numeric thresholds (5-10 papers, 6-12 raw ideas, 7/10 gate), with minor gaps where guidance stays abstract and delegates to references.	4 / 5
Workflow Clarity	A clear numbered 8-step workflow with explicit gates (paper floor, 7/10 selection gate, narrative defensibility precheck) and feedback loops (route back to scout, re-widen); validation is present but scattered rather than in one checklist.	4 / 5
Progressive Disclosure	Seven real one-level-deep reference files are all clearly signaled in the body; the gap is the monolithic 1290-line body inlining protocol content that overlaps the reference playbooks.	4 / 5
	Total	14 / 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 tight, well-formed description that states concrete capabilities and an explicit 'Use when' trigger tied to the active baseline. It is specific, complete, and largely distinct from sibling skills.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — 'concrete hypotheses, limitation analysis, candidate directions, or a selected idea' — but stops short of the comprehensive, fully concrete coverage of a 5.	4 / 5
Completeness	Explicitly answers both what (the listed actions) and when (a concrete 'Use when a quest needs...' trigger clause), satisfying the top anchor.	5 / 5
Trigger Term Quality	Includes natural terms a user would say (hypotheses, candidate directions, selected idea, baseline) with good coverage, but a few synonyms/variations are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear research-idea-selection niche with distinct triggers; only minor overlap risk with the companion scout skill.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1291 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/ds-idea/SKILL.md
Commit: 4b35756

Reviewed: 5 days 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.