research-hotspot-analysis

Analyze research hotspots for a disease or topic and recommend representative literature. Use when users need to identify trending directions, topic clusters, or generate hotspot review reports. Input is a disease name or research topic; output is a structured hotspot analysis report and representative literature list.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Evidence Insight/research-hotspot-analysis/SKILL.md

Quality

Content

60%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.

Well-structured content with a clear workflow, real bundle-file references, and genuine failure handling. Its main weaknesses are a partly duplicated/placeholder-heavy output template and a lack of executable invocation examples for the script functions it relies on.

Suggestions

Show one or two executable invocation examples for analysis_ops.py functions (e.g. an import + call with arguments) so Claude can run rather than describe them.

Consolidate the Output Format template into a single section or move it to a references file to remove the placeholder/filler and the duplication with the Output Contract.

Add an explicit feedback loop for unstable clustering (re-cluster with relaxed/expanded keywords before falling back to candidate-only), since the skill flags clustering instability but does not sequence a retry.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with useful tables and bullet structure, but the duplicated Output Format template plus procedural sections re-explain the report layout and contain placeholder filler ('[Topic Name]', '...') that could be trimmed without losing clarity.	3 / 5
Actionability	The workflow names concrete script functions (search_pubmed, word_frequency, match_keywords, sort_by_jif_and_select) but never shows how to invoke them — no import line, call signatures, or example invocation, leaving execution partly to inference.	3 / 5
Workflow Clarity	A clear six-step sequence with validation-oriented safeguards (PARTIAL marking, broaden-then-explain on thin results, user checkpoints before broad search and ambiguous clusters); minor gaps in explicit re-run loops for clustering instability.	4 / 5
Progressive Disclosure	Body points one level deep to real bundle files (scripts/analysis_ops.py, references/prompt_templates.md) that both exist, with a clean Tools/Scripts/References breakdown; the inlined full report template could arguably live in its own reference file.	4 / 5
	Total	14 / 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.

A solid, third-person description that covers what the skill does and when to use it with concrete trigger phrases. It is slightly held back by formal, non-colloquial trigger language and modest overlap risk with general literature-review skills.

Suggestions

Add natural synonyms users actually say, e.g. 'literature review', 'trends in', or 'what's hot in <disease> research', to broaden trigger coverage.

Sharpen the 'when' clause with concrete scenarios like 'when planning a review article, picking a thesis topic, or scoping a grant'.

Tighten the trailing input/output sentence or move it to the body, as it dilutes the trigger signal in the description.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions ('Analyze research hotspots', 'identify trending directions, topic clusters, or generate hotspot review reports', 'recommend representative literature'), though phrased more as capabilities than atomic operations.	4 / 5
Completeness	Explicitly answers both 'what' (analyze hotspots, recommend literature) and 'when' ('Use when users need to identify trending directions, topic clusters, or generate hotspot review reports'); the 'when' is clear but could name more concrete trigger scenarios.	4 / 5
Trigger Term Quality	Includes some natural terms ('research hotspots', 'trending directions', 'topic clusters', 'hotspot review reports') but relies on somewhat formal phrasing and lacks common synonyms a user would naturally utter ('literature review', 'what's hot in', 'trends').	3 / 5
Distinctiveness Conflict Risk	The biomedical research-hotspot niche is fairly distinct and unlikely to fire for generic literature search, with only minor overlap risk against broad literature-review skills.	4 / 5
	Total	15 / 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: scientific-skills/Evidence Insight/research-hotspot-analysis/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.