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

71%

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/aris-idea-creator/SKILL.md

Quality

Content

63%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 skill body is a thorough, well-sequenced multi-phase workflow with strong executable guidance and real validation checkpoints for its batch GPU operations. Its main weakness is token efficiency and progressive disclosure: motivational justifications and large templates are inlined rather than split into reference files.

Suggestions

Trim motivational justifications (e.g., "This is the key differentiator from paper-only validation", "This avoids re-discovering what the user already knows") to improve conciseness — Claude can infer the rationale.

Move the full IDEA_REPORT.md template and the Codex MCP prompt blocks into separate reference files (e.g., references/idea-report-template.md, references/codex-prompts.md) and link to them one level deep, improving progressive disclosure.

Make the Phase 4→5 validation gate explicit (e.g., a checklist that novelty-check passed before launching pilots) to lift workflow_clarity to the top anchor.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient procedural guidance, but includes unnecessary justifications Claude does not need (e.g., "This is the key differentiator from paper-only validation", "This avoids re-discovering what the user already knows"), matching the mostly-efficient-but-could-be-tightened anchor.	3 / 5
Actionability	Concrete executable material is present throughout — Codex MCP prompt blocks, python3 research_wiki.py commands, and a full report template — with only minor placeholder gaps ([user's direction], [paste landscape map]) keeping it just below fully copy-paste ready.	4 / 5
Workflow Clarity	Phases 0–7 are clearly sequenced with explicit checkpoints (PILOT_TIMEOUT_HOURS kill-and-collect-partial, MAX_TOTAL_GPU_HOURS budget tracking, STOP-and-ask for over-broad directions); a few validation transitions are implicit rather than gated, so it sits just below the top anchor.	4 / 5
Progressive Disclosure	No bundle files exist, so everything lives inline in SKILL.md; the large report template and Codex prompt blocks are content that could be split into separate files, and while other-skill references are signaled in a Composing section, the inlining matches the score-3 anchor.	3 / 5
	Total	14 / 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.

The description is well-formed: it clearly states the skill's purpose and provides explicit, natural trigger phrases including a colloquial term. It is slightly thin on the full range of actions the skill performs (validate, pilot, rank), which keeps specificity and distinctiveness just below the top anchor.

Dimension	Reasoning	Score
Specificity	"Generate and rank research ideas given a broad direction" names the domain plus two concrete actions (generate, rank), but stops there rather than enumerating the broader validate/filter/pilot activities, matching the score-3 anchor.	3 / 5
Completeness	It explicitly states what the skill does ("Generate and rank research ideas given a broad direction") and when to use it via a concrete "Use when..." clause with multiple trigger phrases, satisfying the score-5 anchor.	5 / 5
Trigger Term Quality	Quotes several natural phrases users would say ("brainstorm ideas", "generate research ideas", "what can we work on", plus the colloquial "找idea"), giving good coverage though a few synonyms are absent.	4 / 5
Distinctiveness Conflict Risk	The research-ideation niche with specific triggers is mostly distinct from other skills, with only minor overlap risk against general brainstorming or literature skills.	4 / 5
	Total	16 / 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
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: 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.