Name: grants
Rating: 71.2 (1 reviews)
Author: alirezarezvani

grants

NIH grant research skill for clinical researchers. Grill-me intake (research idea + career stage + preliminary data + environment + submission posture + known institute targets) locks down the funding strategy before any search runs. Runs a 5-facet Consensus positioning analysis (with draft Significance/Innovation language), maps the research to the right NIH institutes and study sections via RePORTER, finds NOSIs and funded overlap, and produces an editable Word document (.docx) with budget/scope-aware mechanism recommendations, submission timelines, and a mandatory program officer recommendation. Use when the user asks about research funding or makes any grant-related request (e.g., 'grants for [topic]', 'find grants for my research idea', 'what grants match my research', 'help me find NIH funding', 'grant opportunities for my research'). NIH-only scope — non-NIH funders (PCORI, DOD CDMRP, VA, foundations) are out of scope and flagged at intake.

Quality

88%

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

The canonical home for this skill is grants in alirezarezvani/claude-skills

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.

The body is a well-sequenced, actionable multi-phase workflow with strong validation and error-handling loops, but it leans on three reference files and three scripts that are not present in the bundle, leaving the core DOCX-generation detail inaccessible. Tightening duplicated prose and shipping the missing bundle files would raise the weaker dimensions.

Suggestions

Add the missing bundle files (references/docx_9_sections.md, references/nih_mechanism_matching.md, references/reporter_post_patterns.md) and scripts/ so the deferred DOCX-generation and mechanism-matching detail is actually reachable.

Inline a minimal DOCX generation snippet (Node.js + docx) so the headline deliverable is executable from the body alone, keeping the full 9-section spec in the reference.

De-duplicate the program-officer recommendation and the reference list (each appears both inline and in a dedicated section) to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean instructional prose, code blocks, and tables without explaining concepts Claude already knows, but the 'Why I'm asking' rationales, the duplicated program-officer recommendation (Section 7 list plus a dedicated section), and references restated both inline and in the References list could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready RePORTER curl POST blocks with full JSON payloads and concrete script invocations with flags, but the core DOCX-generation code is deferred to references/docx_9_sections.md rather than shown inline, leaving the headline deliverable's execution under-specified in the body.	4 / 5
Workflow Clarity	Clear multi-phase sequence (intake → positioning → mapping/discovery → mechanism matching → DOCX → deliver) with an explicit stop condition after Q6, a Phase 4 zip-integrity validation step, and an error-handling table defining retry-once/3-failure-stop feedback loops for the batch Consensus/RePORTER calls.	5 / 5
Progressive Disclosure	References are well-signaled and one-level-deep (reporter_post_patterns.md, nih_mechanism_matching.md, docx_9_sections.md), but none of the referenced files or scripts actually exist in the bundle — so the deferred content, including the entire DOCX 9-section spec, is unavailable and navigation is broken.	3 / 5
	Total	16 / 20 Passed

Description

100%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 concrete, comprehensive, and clearly bounded, with an explicit 'Use when' clause and natural trigger phrases that map well to how a user would request grant help. Its only weakness is verbosity — it is longer than necessary — but no rubric dimension penalizes that strongly enough to drop a level.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Grill-me intake', '5-facet Consensus positioning analysis', 'maps the research to the right NIH institutes and study sections via RePORTER', 'finds NOSIs and funded overlap', 'produces an editable Word document (.docx) with budget/scope-aware mechanism recommendations' — covering the workflow comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (the end-to-end grant research workflow and .docx output) and 'when' via a clear 'Use when the user asks about research funding or makes any grant-related request' clause with concrete trigger phrases.	5 / 5
Trigger Term Quality	Provides several natural user phrases — 'grants for [topic]', 'find grants for my research idea', 'what grants match my research', 'help me find NIH funding', 'grant opportunities for my research' — with synonym variation a user would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear NIH-only niche with distinct grant-funding triggers, and it explicitly bounds scope ('NIH-only scope — non-NIH funders (PCORI, DOD CDMRP, VA, foundations) are out of scope and flagged at intake'), minimizing overlap with other skills.	5 / 5
	Total	20 / 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
relative_links	Relative link issues: 6 missing	Warning
referenced_paths_exist	Referenced path issues: 20 missing	Warning

	Total	14 / 16 Passed

Repository: alirezarezvani/claude-skills
Path: .gemini/skills/grants/SKILL.md
Commit: 19392f7

Reviewed: ~7 hours 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.