CtrlK
BlogDocsLog inGet started
Tessl Logo

medical-research-gap-finder

Identifies real, evidence-audited, topic-specific research gaps in medical research by first retrieving and verifying literature from trusted sources, then mapping the current evidence landscape, rejecting pseudo-gaps, and converting only medium/high-confidence gaps into study-ready research opportunities. Always require real literature retrieval before formal gap claims. Never fabricate references, metadata, or findings.

58

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./awesome-med-research-skills/Evidence Insight/medical-research-gap-finder/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The body is a well-structured, clearly sequenced analysis workflow with concrete actionable steps and proper progressive disclosure into real reference files. Its main weaknesses are restated constraints across multiple sections and advisory rather than enforced validation loops.

Suggestions

Collapse the redundant constraints in "Hard Rules" and "What This Skill Should Not Do" into a single concise list, since both restate the execution-step rules.

Make Step 8 an explicit verify-and-retry loop: if the self-critical review finds an incomplete audit or a pseudo-gap risk, state that you return to retrieval or re-audit before finalizing.

Either link references/workflow-step-template.md at the relevant step or remove it from the bundle so all reference files are reachable from the body.

DimensionReasoningScore

Conciseness

Mostly efficient procedural guidance with no basic-concept padding, but the Hard Rules, "What This Skill Should Not Do", and the execution steps restate the same constraints multiple times (e.g., "Never fabricate references" and "do not treat generic upgrade suggestions as real gaps"). Not a 4 because the redundancy across sections could be tightened, and not a 2 because nothing is concept-explanation padding.

3 / 5

Actionability

An instruction-only skill with concrete per-step guidance—named retrieval sources (PubMed, Google Scholar, Web of Science, arXiv), explicit audit bullets, a gap taxonomy, and confidence criteria—delegating retrieval/citation specifics to reference files. Not a 5 because the executable retrieval and citation methodology lives in bundled references rather than inline.

4 / 5

Workflow Clarity

A clearly sequenced 8-step process ("always run in order") with confidence-gating checkpoints and a Step 8 self-critical review checklist including a fallback path. Not a 5 because validation is advisory ("explicitly check") rather than an enforced verify-and-retry loop, with no explicit iteration back to retrieval when review surfaces an incomplete audit.

4 / 5

Progressive Disclosure

Well-signaled one-level-deep references placed at each relevant step, and all four referenced files exist in references/. Not a 5 because references/workflow-step-template.md is present in the bundle yet never linked from the body, a minor navigation gap.

4 / 5

Total

15

/

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 specific, comprehensive, and clearly distinct, but it omits an explicit "Use when..." trigger clause and leans on domain jargon over natural user phrasing. It caps at middling completeness and trigger-term quality despite strong specificity and distinctiveness.

Suggestions

Add an explicit "Use when..." clause naming concrete trigger phrases (e.g., "Use when the user asks to find or map research gaps, identify what remains unresolved, or convert gaps into study ideas in a medical topic").

Soften jargon with natural synonyms users actually say—"find what's missing in the literature", "what's still unanswered", "study ideas"—alongside "research gaps".

Optionally mention common input shapes (disease/gene/therapy) in the description so the trigger surface is broader.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—"retrieving and verifying literature", "mapping the current evidence landscape", "rejecting pseudo-gaps", "converting only medium/high-confidence gaps into study-ready research opportunities", and "Never fabricate references, metadata, or findings"—giving comprehensive coverage of capabilities.

5 / 5

Completeness

Clearly and comprehensively answers "what" the skill does, but offers no "Use when..." clause; the "when" is only weakly implied from the topic. Per guideline, a missing explicit trigger clause caps completeness at 3, and it is not a 2 because the "what" is unambiguous.

3 / 5

Trigger Term Quality

Includes the natural core term "research gaps in medical research" but leans jargony ("evidence-audited", "pseudo-gaps", "study-ready research opportunities") and omits common synonyms or variations a user would naturally say. Not a 4 because natural keyword coverage is incomplete, and not a 2 since the primary natural term is present.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche—evidence-audited medical research gap analysis with pseudo-gap rejection—whose triggers are distinct and unlikely to fire for unrelated skills. Not below 5 because the domain and methodology are highly specific with minimal overlap risk.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
aipoch/medical-research-skills
Reviewed

Table of Contents

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.