novelty-vs-feasibility-assessor

Assesses whether a medical research topic is worth starting now by separating true novelty from pseudo-novelty, auditing real feasibility under stated resource constraints, and forcing a concrete start / narrow / redesign / stop decision. Always require explicit assumptions and never fabricate references, datasets, resource availability, precedent studies, or publication claims.

Quality

71%

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 ./awesome-med-research-skills/Evidence Insight/novelty-vs-feasibility-assessor/SKILL.md

Quality

Content

67%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.

A well-structured, actionable instruction skill with a clear ordered workflow and well-signaled one-level-deep references. Its main weakness is redundancy: the same themes recur across several sections, inflating token usage.

Suggestions

Consolidate the overlapping guidance: the Mandatory Output Structure (A–K) and the 8 Execution Steps cover the same ground twice — merge them or have the steps define the process and the output structure define only the deliverable shape.

Trim the Hard Rules, 'What This Skill Should Not Do', and 'Quality Standard' sections to a single deduplicated guardrail list, since they restate the same anti-pseudo-novelty and anti-fabrication principles.

Reduce inline duplication with the reference files: point to novelty-audit-framework.md / feasibility-burden-framework.md for the dimension lists rather than re-listing every dimension in the body.

Dimension	Reasoning	Score
Conciseness	All guidance is task-specific with no basic-concept padding, but the same novelty/feasibility/decision themes are restated across the 8 Steps, Mandatory Output Structure (A–K), 15 Hard Rules, 'Should Not Do', and Quality Standard sections, which could be tightened significantly.	3 / 5
Actionability	Provides concrete assessable dimensions, a fixed 5-band decision output, a minimal-executable-version template, sample input triggers, and a defined output structure; minor gap is the absence of one fully worked example output.	4 / 5
Workflow Clarity	The 8 steps are explicitly ordered ('always run in order') with Step 8 acting as a self-critical audit checkpoint and integrity rules as guardrails; not a destructive/batch operation so the validation cap does not apply, but mid-flow checkpoints are implicit rather than explicit.	4 / 5
Progressive Disclosure	Five real one-level-deep reference files are clearly signaled with explicit 'Use for / Use when' guidance and easy navigation; minor gap is that framework content (e.g., the five novelty dimensions) is duplicated inline rather than cleanly split into the reference files.	4 / 5
	Total	15 / 20 Passed

Description

75%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 specific, third-person, distinctive description that clearly conveys what the skill does, but it lacks an explicit 'Use when...' trigger clause, capping completeness. Adding a concrete 'when' clause would round it out.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases (e.g., 'Use when a researcher asks whether a medical research idea is novel enough and feasible enough to start now, or whether to narrow, redesign, or stop it').

Include a few more natural synonyms users would say, such as 'go/no-go decision', 'worth pursuing', or 'research idea evaluation', to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('separating true novelty from pseudo-novelty, auditing real feasibility under stated resource constraints, and forcing a concrete start / narrow / redesign / stop decision'), giving comprehensive coverage of what the skill does.	5 / 5
Completeness	The 'what' is clear and explicit, but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3; the 'when' is only weakly implied via 'worth starting now'.	3 / 5
Trigger Term Quality	Good natural-term coverage ('medical research topic', 'novelty', 'feasibility', 'start / narrow / redesign / stop decision'), but a few common phrasings researchers actually say ('go/no-go', 'worth pursuing', 'research idea') are missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (medical-research topic-start decisions separating novelty from feasibility) with distinct triggers, giving minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

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

	Total	15 / 16 Passed

Repository: aipoch/medical-research-skills
Path: awesome-med-research-skills/Evidence Insight/novelty-vs-feasibility-assessor/SKILL.md
Commit: f5ef65b

Reviewed: ~12 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.