Simulates NIH study section peer review for grant proposals. Triggers.
29
22%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/grant-mock-reviewer/SKILL.mdQuality
Discovery
22%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 identifies a specific and niche domain (NIH peer review simulation) but fails to articulate concrete actions, provide explicit trigger conditions, or include sufficient natural keywords. The truncated 'Triggers.' fragment suggests an incomplete description that would leave Claude unable to reliably select this skill at the right time.
Suggestions
Add a complete 'Use when...' clause specifying trigger conditions, e.g., 'Use when the user asks for feedback on a grant proposal, NIH review, study section critique, or grant scoring.'
List specific concrete actions such as 'Scores proposals on NIH criteria (significance, innovation, approach, investigators, environment), generates summary statements, and provides critique paragraphs.'
Include additional natural trigger terms users might say, such as 'R01', 'grant application', 'specific aims', 'grant critique', 'mock review', or 'grant feedback'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain ('NIH study section peer review for grant proposals') but does not list any concrete actions such as scoring, critiquing significance, evaluating methodology, or generating summary statements. 'Simulates' is a single vague verb. | 1 / 3 |
Completeness | The 'what' is weakly stated (just 'simulates peer review') and the 'when' is entirely absent. The word 'Triggers.' appears to be a truncated or incomplete fragment rather than an explicit 'Use when...' clause, which should cap completeness at 2 at best, but since there's no actual trigger guidance, it scores 1. | 1 / 3 |
Trigger Term Quality | It includes some relevant keywords like 'NIH', 'study section', 'peer review', and 'grant proposals' that users might naturally say. However, it misses common variations like 'R01', 'grant application', 'critique', 'score', 'significance', 'innovation', or 'specific aims'. | 2 / 3 |
Distinctiveness Conflict Risk | The NIH study section context is fairly niche and unlikely to conflict with most other skills. However, it could overlap with general 'grant writing' or 'academic review' skills since it doesn't clearly delineate its boundaries or specific triggers. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is heavily padded with generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Input Validation, Response Template, Error Handling) that are not specific to grant review and waste significant token budget. The domain-specific content (NIH scoring criteria, common weaknesses) is valuable but should be in reference files rather than inline. The actual workflow for performing a grant review is missing - the generic 5-step workflow provides no guidance on how to actually evaluate a grant proposal against NIH criteria.
Suggestions
Remove all generic boilerplate sections (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template, Output Requirements, Input Validation, Error Handling) - these add no skill-specific value and consume ~40% of the token budget.
Move the NIH scoring rubric details, common weaknesses catalog, and review output format into reference files and link to them, keeping only a concise overview in SKILL.md.
Replace the generic 5-step workflow with an actual grant review workflow: e.g., 1) Read proposal, 2) Score each criterion 1-9, 3) Identify strengths/weaknesses per criterion, 4) Write detailed critique, 5) Generate summary statement, 6) Provide revision recommendations.
Remove circular self-references ('See ## Prerequisites above', 'See ## Usage above') and consolidate duplicate content (--help appears 3 times in Audit-Ready Commands).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose and repetitive. Contains massive amounts of boilerplate (Risk Assessment, Security Checklist, Lifecycle Status, Evaluation Criteria, Response Template) that add no value for Claude. Multiple sections reference each other circularly ('See ## Prerequisites above', 'See ## Usage above'). The NIH scoring rubric details, common weaknesses catalog, and parameter tables could easily be in reference files. Much content explains things Claude already knows. | 1 / 3 |
Actionability | Provides concrete CLI commands and a Python library usage example, plus a detailed parameter table. However, the commands appear to be aspirational rather than verified (no bundle files provided to confirm scripts/main.py exists or works). The actual review workflow is vague - it doesn't specify how Claude should actually perform the review if the script isn't available, which is the most likely scenario. | 2 / 3 |
Workflow Clarity | The workflow section (steps 1-5) is entirely generic boilerplate that could apply to any skill - 'Confirm the user objective', 'Validate that the request matches documented scope', etc. There are no NIH-review-specific workflow steps, no validation checkpoints for the review process itself, and no feedback loops. The 'Example run plan' is similarly generic. For a complex multi-criteria review task, this is inadequate. | 1 / 3 |
Progressive Disclosure | References to files in references/ directory are listed but no bundle files are provided to verify they exist. The SKILL.md itself is monolithic - the common weaknesses catalog, NIH scoring rubric, and parameter details are all inline when they should be in reference files. Some structure exists with clear section headers, but the organization is poor with redundant sections and circular references. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%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 | |
73f6514
Table of Contents
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.