aris-grant-proposal

Draft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.

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

70%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 is a well-structured, highly actionable multi-phase workflow with strong validation checkpoints and feedback loops. Its main weaknesses are moderate verbosity in checkpoint/decorative prose and a monolithic structure that inlines agency specs and prompt templates which would benefit from being split into reference files.

Suggestions

Extract the eight per-agency specification tables (KAKENHI, NSF, NSFC, ERC, DFG, SNSF, ARC, NWO) into one-level-deep reference files (e.g. references/agencies/KAKENHI.md) linked from a compact summary table in SKILL.md to improve progressive disclosure and reduce the main file length.

Trim the repeated 'What this does' explanatory labels and decorative emoji checkpoint blocks; keep the checkpoint prompts but consolidate the prose.

Move the Codex MCP review prompt templates (Round 1 / Round 2+) into a references/review-prompts.md file, keeping only the invocation pattern inline.

Dimension	Reasoning	Score
Conciseness	The body is dense with genuinely useful agency-specific specifics rather than concepts Claude already knows, but repeated 'What this does' labels, decorative emoji checkpoint blocks, and redundant ASCII pipeline diagrams could be tightened to reduce token load.	3 / 5
Actionability	Provides concrete sub-skill invocations (e.g. `/aris-research-lit "$ARGUMENTS"`), an explicit GRANT_STATE.json schema, a numbered drafting order, and Codex MCP call templates with exact config; minor gaps remain in placeholder-laden review prompts.	4 / 5
Workflow Clarity	Phases 0–5 are clearly sequenced with explicit 🚦 checkpoints, validation steps (/aris-novelty-check, structural review, external review), a review→revise→re-review feedback loop, and a final pre-completion checklist.	5 / 5
Progressive Disclosure	The file is well-sectioned but monolithic at ~600 lines with no bundle files (references/, scripts/, assets/ absent); the eight agency specification tables and Codex prompt templates are content that could be split into one-level-deep reference files but is inlined.	3 / 5
	Total	15 / 20 Passed

Description

95%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 strong: it names a concrete capability, comprehensively lists supported agencies with sub-types, and provides explicit multilingual trigger phrases for when to invoke the skill. Minor room for improvement lies in listing a broader set of distinct actions beyond the single 'draft' verb.

Dimension	Reasoning	Score
Specificity	Names the core action ("Draft a structured grant proposal from research ideas and literature") and comprehensively enumerates supported agencies (KAKENHI, NSF, NSFC, ERC, DFG, SNSF, ARC, NWO, GENERIC) with NSFC sub-types, but the action vocabulary is essentially a single verb (draft) rather than multiple distinct concrete actions.	4 / 5
Completeness	Clearly states what it does (draft a structured grant proposal from research ideas and literature, supporting named agencies) and explicitly states when to use it with concrete trigger phrases, satisfying both what and when.	5 / 5
Trigger Term Quality	"Use when user says 'write grant', 'grant proposal', '申請書', 'write KAKENHI', '科研費', '基金申请', '写基金', 'NSF proposal'" provides comprehensive natural trigger phrases including multilingual synonyms users would actually say.	5 / 5
Distinctiveness Conflict Risk	Targets a clear niche (multi-agency grant proposals) with agency-specific and multilingual trigger terms, making overlap with other skills minimal.	5 / 5
	Total	19 / 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
skill_md_line_count	SKILL.md is long (625 lines); consider splitting into references/ and linking	Warning
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	13 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/aris-grant-proposal/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.