inno-grant-proposal

Help professors and researchers write, revise, adapt, and polish grant proposals for US agencies (NSF, NIH, DOE, DARPA, NASA) and Chinese agencies (NSFC 国自然). Use this skill whenever the user mentions grants, proposals, funding applications, 基金申请, 本子, R01, R21, CAREER, 面上, 青年基金, specific aims, 立项依据, broader impacts, or wants to plan, draft, review, or resubmit any research funding proposal — even if they don't explicitly say "grant". Also use this skill when the user wants to adapt a previous proposal for a new submission. Six-phase workflow: profiling → planning → drafting → quality review → simulated peer review → submission prep.

Quality

84%

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

73%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-sequenced, validation-rich workflow with concrete scripts and state management, though it is long and could be tightened. Progressive disclosure is mostly well-organized with real reference files, but several referenced paths (templates/, config.yaml) are missing from the bundle.

Suggestions

Trim conceptual restatements (e.g., general reviewer-psychology advice) that Claude already knows, and move dense agency-specific tables into the existing reference guides to reduce SKILL.md length.

Add the referenced templates/us/, templates/cn/ directories, config.yaml, and CREDITS.md to the bundle, or remove those references from the body so all cited paths resolve.

Consolidate the repeated AI-flavor-checklist references (Phases 3, 4, 5) into a single canonical pointer to references/common/ai_flavor_checklist.md to avoid duplicated instructions.

Dimension	Reasoning	Score
Conciseness	The body is large (~900 lines) and re-explains context Claude already knows (e.g., what reviewers do, generic drafting advice) with some padded sections, though it stays mostly task-focused rather than teaching basic concepts.	3 / 5
Actionability	Provides concrete executable elements — JSON state schema, script invocation commands ('python3 scripts/validate_length.py ... --json'), routing pseudocode, and template paths — with only minor gaps where guidance stays abstract (e.g., figure generation).	4 / 5
Workflow Clarity	Six phases are clearly sequenced with explicit entry/exit criteria, checkpoints, validation steps (Tier 1 deterministic checks, AI-flavor checklist), and feedback loops (validate → fix → re-validate, warn-on-destructive with confirmation).	5 / 5
Progressive Disclosure	Good structure with explicit Reference Files section and one-level-deep lazy-loading guidance; references like references/cn/nsfc_guide.md and scripts/*.py are real bundle files. Minor gaps: templates/us/ and templates/cn/ directories and config.yaml/CREDITS.md are referenced but not present in the bundle.	4 / 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.

The description is comprehensive and bilingual, explicitly covering both what the skill does and when to use it with abundant natural trigger terms and agency-specific keywords. It is on the longer side but earns its length through concrete, distinguishing detail.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('write, revise, adapt, and polish grant proposals') plus a six-phase workflow, but coverage of actions is somewhat high-level rather than enumerating many discrete concrete operations.	4 / 5
Completeness	Explicitly answers both what (write/revise/adapt/polish proposals for named US and CN agencies) and when ('Use this skill whenever the user mentions...' with concrete trigger phrases and the adapt-previous-proposal case).	5 / 5
Trigger Term Quality	Comprehensive natural triggers including both English ('R01, R21, CAREER, specific aims, broader impacts') and Chinese ('基金申请, 本子, 面上, 青年基金, 立项依据') plus the 'even if they don't explicitly say grant' catch-all.	5 / 5
Distinctiveness Conflict Risk	Clear niche (grant/funding proposals for named agencies with bilingual triggers) that no other skill would match; minimal conflict risk.	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 (937 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 21 deeper-than-1-level	Warning

	Total	13 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/inno-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.