grant-mock-reviewer

Simulates NIH study section peer review for grant proposals. Triggers when user wants mock review, critique, or evaluation of a grant proposal before submission. Generates structured critique using official NIH scoring rubric (1-9 scale), identifies weaknesses, provides actionable revision recommendations, and produces a comprehensive review summary similar to actual NIH Summary Statement.

Install with Tessl CLI

npx tessl i github:aipoch/medical-research-skills --skill grant-mock-reviewer

What are skills?

Review — 72%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Validation — 10 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Discovery

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly defines a specific niche (NIH grant proposal review), lists concrete actions with domain-specific details (1-9 scoring rubric, Summary Statement), and includes explicit trigger conditions. The description uses proper third-person voice throughout and provides enough specificity to distinguish it from general document review or academic writing skills.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'Simulates NIH study section peer review', 'Generates structured critique using official NIH scoring rubric (1-9 scale)', 'identifies weaknesses', 'provides actionable revision recommendations', and 'produces a comprehensive review summary'.	3 / 3
Completeness	Clearly answers both what (simulates NIH peer review, generates structured critique, identifies weaknesses, provides recommendations) AND when ('Triggers when user wants mock review, critique, or evaluation of a grant proposal before submission').	3 / 3
Trigger Term Quality	Includes natural keywords users would say: 'mock review', 'critique', 'evaluation', 'grant proposal', 'NIH', 'submission', 'peer review'. These are terms researchers would naturally use when seeking this type of feedback.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with clear niche: specifically targets NIH grant proposals with NIH-specific scoring rubric (1-9 scale) and Summary Statement format. Unlikely to conflict with general document review or other academic writing skills.	3 / 3
	Total	12 / 12 Passed

Implementation

44%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill provides good reference material about NIH scoring criteria and output formats, but fails to instruct Claude on HOW to actually perform the review. It reads more like tool documentation than actionable guidance for generating critiques. The skill is bloated with boilerplate sections (security checklists, lifecycle status, evaluation criteria) that don't help Claude execute the task.

Suggestions

Add a concrete workflow section showing step-by-step how to analyze a proposal and generate scores/critiques (e.g., '1. Read Specific Aims, 2. Evaluate against significance criteria, 3. Identify 3-5 strengths/weaknesses...')

Remove boilerplate sections that don't aid task execution: Security Checklist, Lifecycle Status, Evaluation Criteria, Prerequisites - these are generic templates not specific guidance

Include an example input/output showing a sample proposal excerpt and the corresponding critique Claude should generate

Add validation checkpoints for review quality (e.g., 'Verify each criterion has at least 2 strengths and 2 weaknesses before generating Summary Statement')

Dimension	Reasoning	Score
Conciseness	The skill contains significant redundancy and sections that don't add value for Claude (e.g., generic 'Best Practices for Users', boilerplate 'Evaluation Criteria', 'Lifecycle Status', 'Security Checklist' with empty checkboxes). The NIH scoring tables are useful reference but could be more compact.	2 / 3
Actionability	Provides concrete CLI commands and library usage examples, but the actual review generation logic is not shown - it references scripts that presumably exist but doesn't demonstrate how Claude should actually perform the review critique. The 'Common Weaknesses Detected' section is helpful but the core task execution is unclear.	2 / 3
Workflow Clarity	No clear workflow for how to actually conduct a mock review. The skill describes outputs and parameters but lacks step-by-step process for generating critiques. No validation checkpoints for ensuring review quality or completeness. Missing feedback loops for iterative review refinement.	1 / 3
Progressive Disclosure	Good structure with clear references to external files (references/nih_scoring_rubric.md, etc.) that are one level deep and well-signaled. Content is organized into logical sections with clear navigation between capabilities, parameters, and output formats.	3 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

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.