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

86%

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

77%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 multi-phase workflow with strong validation checkpoints and feedback loops. Its main weaknesses are length/redundancy and a monolithic structure that inlines substantial agency-specific reference material instead of splitting it into bundled reference files.

Suggestions

De-duplicate the pipeline diagram (keep one of the two ASCII diagrams near the top) and remove the restated funding-track explanation in 'Composing with Other Skills' to tighten conciseness.

Move the eight Grant Type Specifications tables into a bundled reference file (e.g. references/agency-specs.md) and have SKILL.md summarize agency coverage with one-line links, improving progressive disclosure.

Trim conceptual framing a user/PI already knows (e.g. 'Grant proposals argue for future work', the paper-vs-grant contrast) to leaner statements that still preserve the actionable guidance.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and much of the detail (agency templates, sub-types, review criteria) is genuinely skill-specific, but the pipeline diagram is duplicated (lines 16-19 and 25-29), the funding-track composition is restated, and some conceptual framing ("Grant proposals argue for future work") could be trimmed.	3 / 5
Actionability	Provides an executable bash resolver block for style-ref, concrete sub-skill invocation strings with arguments, a precise GRANT_STATE.json schema, MCP call patterns, and concrete output file trees — copy-paste ready guidance covering the common cases.	5 / 5
Workflow Clarity	Phases 0-5 are clearly sequenced with explicit STOP checkpoints (🚦/⛔), validation via /novelty-check and /research-review, a review→revise→re-review feedback loop, state-persistence resume logic, and a final pre-submission checklist.	5 / 5
Progressive Disclosure	Good section structure and clearly signaled shared-references links, but no bundle reference files exist and the eight agency specification tables are inlined in a single ~690-line file rather than split into per-agency reference files.	3 / 5
	Total	16 / 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.

A strong, third-person description that clearly states what the skill does and when to use it, with rich multilingual trigger phrases and broad agency coverage. Minor: the action list could enumerate a few more distinct concrete operations to fully reach the top specificity anchor.

Dimension	Reasoning	Score
Specificity	Names a concrete primary action ("Draft a structured grant proposal from research ideas and literature") and enumerates specific agency formats and sub-types, but the core action is essentially a single one rather than a list of distinct operations, so it sits below the comprehensive multi-action anchor 5.	4 / 5
Completeness	Explicitly answers both what ("Draft a structured grant proposal from research ideas and literature") and when ("Use when user says ... or wants to turn research ideas into a funding application") with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrases across multiple languages ("write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal") including synonyms and agency-specific terms a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (grant/funding applications) with highly specific agency-named triggers (KAKENHI, 科研費, NSFC 面上/青年) that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

75%

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 — 12 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (699 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
relative_links	Relative link issues: 3 suspicious	Warning

	Total	12 / 16 Passed

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