research-proposal-generator

Generates a comprehensive research proposal design based on input literature, including hypothesis, mechanism verification, and budget. Use when the user wants to design a research project from a paper.

Quality

53%

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-proposal-generator/SKILL.md

Quality

Content

38%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 skill has a sound procedural skeleton but is weighed down by generic filler and critically depends on a references/ bundle that is absent, making the detailed prompts unreachable. Removing boilerplate and supplying (or inlining) the referenced prompts would materially raise every dimension.

Suggestions

Delete the generic filler sections (Key Features, Dependencies, Example Usage, Implementation Details, Quick Validation) that merely restate the description, and keep only the Procedure, Usage, Input Validation, and Output Contract.

Add the referenced references/prompts.md file (or inline its prompts) so the 'Design Experiments' and per-step prompts the procedure depends on are actually reachable.

Tie the validation steps to concrete checkpoints between the proposal steps (e.g., verify hypothesis/key-info extraction before outline generation) instead of relying on generic safety boilerplate.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic boilerplate sections (Key Features, Dependencies, Example Usage, Implementation Details, Quick Validation) that restate the description or teach nothing Claude doesn't know, matching the 'noticeably verbose; several padded sections' anchor; not 1 because the Procedure section does carry real content.	2 / 5
Actionability	The Procedure gives concrete step structure and an experiment schema (Model/Groups/Sample/Method/Index/Expected Results), but it offloads the actual prompts to references/prompts.md, which does not exist on disk, leaving the guidance incomplete; between 2 and 3.	3 / 5
Workflow Clarity	A clear 5-step sequence with explicit output ordering exists, but the validation referenced is generic boilerplate not tied to concrete inter-step checkpoints, and the detailed-prompt content lives in an absent file, matching the 'steps listed but checkpoints missing or implicit' anchor.	3 / 5
Progressive Disclosure	The body signals a one-level reference to references/prompts.md, but the references/ directory does not exist on disk, so the signaled navigation is a dead end; scored against the actual (missing) bundle structure this is between the minimal-structure and partial-structure anchors.	2 / 5
	Total	10 / 20 Passed

Description

67%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 strong: it states a concrete deliverable set and an explicit trigger clause in third person. Trigger-term breadth is the main gap, with several natural user phrases (grant/write/plan) missing.

Dimension	Reasoning	Score
Specificity	Names the research-proposal domain and several concrete deliverables (hypothesis, mechanism verification, budget), matching the 'several specific actions' anchor; not 3 because it lists three distinct sub-deliverables, not 5 because coverage is bounded to these.	4 / 5
Completeness	Explicitly answers both 'what' ('Generates a comprehensive research proposal design... including hypothesis, mechanism verification, and budget') and 'when' ('Use when the user wants to design a research project from a paper'); not 5 because the 'when' is a single condition rather than the comprehensive trigger phrases of the top anchor.	4 / 5
Trigger Term Quality	Includes a natural phrase ('design a research project from a paper') and relevant terms (proposal, paper, literature) but misses common variations like 'grant proposal', 'write a proposal', or 'research plan', matching the 'some relevant keywords but missing variations' anchor.	3 / 5
Distinctiveness Conflict Risk	Targets a clear, narrow niche (research proposal generation from a paper) with minimal overlap risk; not 5 because it could conceivably overlap with general literature-analysis skills.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	13 / 16 Passed

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

Reviewed: 5 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.