research-grants

Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan's NSTC when you need agency-compliant narratives, budgets, and review-criteria alignment for a specific solicitation/FOA/BAA.

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Protocol Design/research-grants/SKILL.md

Quality

Content

63%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 well-structured and largely actionable with concrete commands and templates, but it suffers from redundancy between sections and bundle misalignment: referenced scripts are absent and asset templates are not linked while duplicate skeletons are inlined. Tightening the duplication and fixing the broken script references would lift the weaker dimensions.

Suggestions

Resolve the bundle mismatch: either add the referenced scripts/ files (compliance_checker.py, budget_calculator.py, deadline_tracker.py, generate_schematic.py) or remove the broken references from the Dependencies and Example Usage sections.

Replace the inline budget_justification.md skeleton with a pointer to the existing assets/budget_justification_template.md (and similarly link the NSF/NIH asset templates) to remove duplication and improve progressive disclosure.

Deduplicate the agency-specific guidance that appears in both "Key Features" and "Implementation Details §1", keeping the overview brief and deferring detail to references/<agency>_guidelines.md.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining basics Claude already knows, but the "Key Features" agency bullets duplicate the "Implementation Details §1" agency mapping, and the editorial note about requirements.txt could be trimmed, so it is mostly efficient with some tightening needed.	3 / 5
Actionability	It provides concrete, copy-paste-ready commands (e.g. `python scripts/generate_schematic.py "..." -o figures/workflow.png`) and full markdown skeletons for proposal.md and budget_justification.md, but the referenced scripts/ directory is not present in the bundle, leaving a minor execution gap.	4 / 5
Workflow Clarity	The numbered "Example Usage" workflow (generate diagrams → draft skeleton → run compliance check → produce budget) is a clear sequence with a checkpoint, but the compliance check is gated "(if available)" with no explicit fix-and-retry feedback loop, a minor validation gap.	4 / 5
Progressive Disclosure	It signals one-level-deep reference files (11 files under references/, all present), but the 4 referenced scripts/ files do not exist in the bundle, and the 3 asset templates are never linked from the body while an inline budget skeleton duplicates assets/budget_justification_template.md — content that should be separate is inline.	3 / 5
	Total	14 / 20 Passed

Description

82%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, well-targeted description that concretely states what it does and when to use it for a clearly delineated set of funding agencies. The only blemish is the second-person "when you need" phrasing, which violates the third-person-voice guideline and lowers the specificity score.

Dimension	Reasoning	Score
Specificity	Quotes "Write competitive research proposals" and "agency-compliant narratives, budgets, and review-criteria alignment" name several concrete actions across named agencies (base 4), but the second-person phrasing "when you need" triggers the rubric's -1 voice penalty, dropping it to 3.	3 / 5
Completeness	It explicitly answers both what ("Write competitive research proposals for NSF, NIH, DOE, DARPA, and Taiwan's NSTC") and when ("when you need agency-compliant narratives, budgets, and review-criteria alignment for a specific solicitation/FOA/BAA") with concrete trigger phrases, matching the anchor 5 example.	5 / 5
Trigger Term Quality	Natural terms like "research proposals", "NSF, NIH, DOE, DARPA", "NSTC", and "solicitation/FOA/BAA" match what users say, but common variations like "grant", "R01", or "grant application" are missing, so it is a notch below comprehensive.	4 / 5
Distinctiveness Conflict Risk	Naming five specific funding agencies and the artifacts "solicitation/FOA/BAA" carves a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 12 missing	Warning

	Total	14 / 16 Passed

Repository: aipoch/medical-research-skills
Path: scientific-skills/Protocol Design/research-grants/SKILL.md
Commit: 63c61d3

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.