medical-research-algorithm-matcher

Matches a user’s biomedical research direction, disease problem, study aim, data modality, and resource constraints to the most relevant recent algorithms and method papers. Always search real recent algorithm literature first, prioritize the last 12 months, expand to 1–3 years only when needed, and add canonical baselines only when necessary. Every formal algorithm recommendation must include the verified primary method paper, plus published downstream papers that actually cite/use the algorithm when such papers are found, with DOI when available. Never fabricate papers, algorithm names, authors, journals, years, DOI, PMID, links, or benchmark claims. If no directly verified algorithm paper is found, say so explicitly.

Quality

74%

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/Protocol Design/medical-research-algorithm-matcher/SKILL.md

Quality

Content

77%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 a well-structured, instruction-rich overview with excellent workflow sequencing, validation gates, and clean one-level-deep progressive disclosure. Its principal weakness is redundancy: the core honesty/verification/recency rules are restated across three rule blocks and could be consolidated.

Suggestions

Consolidate the repeated recency/verification/no-fabrication rules so they appear once; the Hard Rules and Mandatory Behavioral Rules overlap heavily with the 4A–4D steps and the Output Structure.

Add one short worked example of a completed output section (e.g., a single verified algorithm item with a primary paper and one downstream paper) to make the field requirements copy-paste ready.

Tighten the Output Structure by relying on references/output-section-guidance.md for the repeated field lists rather than re-specifying them inline.

Dimension	Reasoning	Score
Conciseness	Largely efficient and free of concept-padding, but the recency/verification/no-fabrication rules recur across Mandatory Behavioral Rules, the 4A–4D steps, Hard Rules, and Output Structure, creating noticeable redundancy that could be tightened.	3 / 5
Actionability	Concrete field-by-field evidence-package requirements, a named taxonomy, and a required multi-section output template give actionable guidance; a worked filled-in output example would push it to fully copy-paste ready.	4 / 5
Workflow Clarity	Seven explicitly sequenced steps each map to a reference module and required output, with explicit validation gates (verification required before formal recommendation), honesty checkpoints, and downgrade/reject feedback loops.	5 / 5
Progressive Disclosure	A dedicated Reference Module Integration section signals seven real, one-level-deep reference files (all present on disk), with each step re-pointing to the relevant module, giving clear overview-to-detail navigation.	5 / 5
	Total	17 / 20 Passed

Description

71%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 specific, third-person, and well-scoped to a clear biomedical niche, with strong domain trigger terms. Its main weakness is the absence of an explicit 'Use when...' trigger clause, leaving the activation condition implied rather than stated.

Suggestions

Add an explicit 'Use when...' clause naming the trigger phrases users would naturally say (e.g., 'Use when a user asks for recent or latest algorithms/methods for a biomedical research direction, or wants to verify a named algorithm like PathHDNN').

Include a few more natural trigger variations such as 'latest methods', 'what algorithms should I use', or 'newer algorithms' to broaden keyword coverage.

Dimension	Reasoning	Score
Specificity	Enumerates multiple concrete actions — matching direction/disease/data modality/constraints to algorithm papers, verifying primary method papers, adding downstream citing papers, and including DOI — giving comprehensive domain-specific coverage.	5 / 5
Completeness	Provides a clear 'what' (matching plus verification rules) but lacks an explicit 'Use when...' trigger clause, so 'when' is only weakly implied, capping completeness at 3.	3 / 5
Trigger Term Quality	Strong natural domain keywords ('biomedical research direction', 'disease problem', 'data modality', 'recent algorithms', 'method papers', 'DOI'), but missing common user variations like 'latest methods' or 'what algorithms should I use'.	4 / 5
Distinctiveness Conflict Risk	The biomedical algorithm-and-literature matching niche is mostly distinct, with only minor overlap risk against a general scientific-literature search skill.	4 / 5
	Total	16 / 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/Protocol Design/medical-research-algorithm-matcher/SKILL.md
Commit: 63c61d3

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.