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

Critical

Do not install without reviewing

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 highly actionable and well-sequenced workflow with strong validation checkpoints and feedback loops, but it is unusually long for a single SKILL.md and contains redundant sections plus agency-spec tables that would benefit from being split into reference files.

Suggestions

Remove redundancy: keep a single pipeline diagram and consolidate the Constants block with the Parameter Pass-Through table instead of restating both.

Move the eight Grant Type Specification tables into a references/ file (e.g., references/grant-types.md) and link to it one level deep, reducing the SKILL.md overview.

Consider moving the full Phase 4 spawn_agent/send_input message templates into a references/review-templates.md file to slim the core body.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and concrete, but the ~620-line body repeats content: the pipeline diagram appears twice, the Constants section is duplicated by the Parameter Pass-Through table, and the Composing section restates the already-shown workflow.	3 / 5
Actionability	Fully executable guidance with copy-paste-ready sub-skill invocations ("/research-lit \"$ARGUMENTS\""), concrete spawn_agent blocks specifying model and reasoning_effort, a JSON state schema, drafting order, and figure-generation commands covering the common cases.	5 / 5
Workflow Clarity	Phases 0–5 are clearly sequenced with explicit 🚦/⛔ validation checkpoints, a review→revise→resubmit feedback loop (Round 2+), state persistence for resume, and a final checks checklist, matching the anchor-5 example with explicit validation and feedback loops.	5 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ empty) and the skill is a monolithic ~620-line SKILL.md with eight inlined agency-specification tables that could live in separate reference files; internal section structure is clear, but content that should be split is inline.	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 description: it concisely states a concrete capability, enumerates supported agencies comprehensively, and provides rich multilingual trigger phrases that clearly distinguish it from related research skills. The only minor gap is that the distinct concrete actions are fewer than the anchor-5 specificity example.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ("Draft a structured grant proposal from research ideas and literature") plus a comprehensive list of supported agencies, but the distinct actions are limited compared to the anchor-5 example of multiple separate operations.	4 / 5
Completeness	Explicitly answers both "what" (draft a structured grant proposal from research ideas and literature, with supported agencies) and "when" ("Use when user says...") with concrete trigger phrases, matching the anchor-5 example.	5 / 5
Trigger Term Quality	Comprehensive multilingual trigger coverage including synonyms and agency-specific phrases ("write grant", "grant proposal", "申請書", "科研費", "基金申请", "写基金", "NSF proposal"), matching the anchor-5 example of natural terms including synonyms.	5 / 5
Distinctiveness Conflict Risk	Clear niche (grant proposals) with distinct agency-specific and multilingual triggers, minimal overlap with other skills; matches the anchor-5 example of a clear niche with distinct triggers.	5 / 5
	Total	19 / 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 (627 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 3 suspicious	Warning

	Total	14 / 16 Passed

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