aris-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

83%

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

77%

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

A well-engineered, highly actionable multi-phase workflow with strong sequencing and validation checkpoints. It loses points on conciseness (some padding) and progressive disclosure (a long single-file body with no supporting reference files to split detail into).

Suggestions

Move the IDEA_REPORT.md template and the Phase 2 MCP brainstorm prompt into a references/ file (e.g. references/report_template.md) and link to them, shrinking SKILL.md to an overview.

Trim editorial sentences such as 'This is the key differentiator from paper-only validation' that restate what the section heading already conveys.

Extract the tools/research_wiki.py command catalog into a references/ or scripts/ file so the wiki integration steps become a short pointer rather than inline pseudocode.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's competence (no beginner explanations of what research or papers are), but the ~270-line body includes some removable editorializing ('This is the key differentiator from paper-only validation') and templated prose that could be tightened.	2 / 3
Actionability	Provides concrete executable commands (python3 tools/research_wiki.py ...), a copy-paste-ready MCP config block with a full prompt, and a complete report template; guidance is specific and actionable throughout even though it orchestrates sibling skills.	3 / 3
Workflow Clarity	The seven phases are clearly sequenced with explicit validation checkpoints (first-pass filtering, novelty check, devil's-advocate review), feedback loops (re-rank on pilot results), and budget/time guards (PILOT_TIMEOUT_HOURS, MAX_TOTAL_GPU_HOURS).	3 / 3
Progressive Disclosure	The body is well-sectioned but monolithic: everything (constants, MCP prompt, full report template, wiki commands) lives inline in a single SKILL.md with no bundle files in references/, scripts/, or assets/ to offload detail to.	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.

A strong description: concise, third-person, with explicit 'Use when...' triggers and natural keyword coverage including multilingual terms. Its only weakness is that the capability list understates the validate/pilot/report actions described in the body.

Suggestions

Expand the capability clause to mention validation and pilot experiments, e.g. 'Generate, validate, and rank research ideas... including cheap pilot experiments'.

Consider adding 'publishable research ideas' as an explicit literal trigger term to match users searching for paper-worthy directions.

Dimension	Reasoning	Score
Specificity	Names the domain ('research ideas given a broad direction') and two concrete actions ('Generate and rank'), but does not enumerate the full set of concrete actions the body actually performs (validate, pilot, report), so it is not comprehensive.	2 / 3
Completeness	Explicitly answers both what ('Generate and rank research ideas given a broad direction') and when ('Use when user says...'), with an explicit trigger clause.	3 / 3
Trigger Term Quality	Covers natural phrases a user would actually say ('找idea', 'brainstorm ideas', 'generate research ideas', 'what can we work on') plus a paraphrased intent trigger, giving broad coverage including a non-English term.	3 / 3
Distinctiveness Conflict Risk	The 'research ideas / publishable directions' niche and specific trigger phrases make it unlikely to fire for unrelated skills.	3 / 3
	Total	11 / 12 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
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

	Total	14 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-idea-creator/SKILL.md
Commit: 6da7f7c

Reviewed: about 8 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.