CtrlK
BlogDocsLog inGet started
Tessl Logo

high-value-paper-screener

Quickly judges whether a biomedical paper is worth deep reading by screening for question fit, design quality, sample adequacy, methodological novelty, and reproducibility value.

51

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./awesome-med-research-skills/Evidence Insight/high-value-paper-screener/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

58%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 body is a well-organized, instruction-only triage skill with a clear 7-step workflow, mandatory output structure, and properly signaled one-level-deep references to real bundle files. Its main weaknesses are redundancy across sections and the absence of a concrete worked example or filled output template.

Suggestions

Consolidate the repeated clarification/input-validation guidance into one section (Reference Module Integration, Input Validation, Step 1, and Hard Rules overlap heavily) to improve conciseness.

Add one short worked example (e.g., a title+abstract input with the A-G output filled in) to lift actionability from guidance to copy-paste ready.

Avoid inlining the full Hard Rules list in the body since they already live in references/hard-rules.md; reference them instead to reduce duplication and sharpen progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly efficient and well-structured, but it restates the same guidance multiple times (e.g., clarification/input-validation appears in 'Reference Module Integration', 'Input Validation', 'Step 1', and 'Hard Rules') and reiterates the distinctions and what-not-to-do lists, adding padding that could be trimmed.

3 / 5

Actionability

As an instruction-only skill it gives concrete, specific guidance (named output sections A-G, classification buckets, explicit assessment factors), which is actionable, but it stops short of worked examples or a concrete filled-in output template that would make it copy-paste ready, leaving minor gaps.

3 / 5

Workflow Clarity

The 7-step Execution sequence is clearly ordered with an upfront clarification gate (Step 1) and a mandatory structured output, plus 'What Would Change the Recommendation' as a feedback/checkpoint loop; this is a non-destructive triage skill so the destructive-cap does not apply, with only minor validation gaps keeping it below 5.

4 / 5

Progressive Disclosure

The body is an overview pointing to seven real one-level-deep reference files, each clearly signaled with its purpose under 'Reference Module Integration', and the listed paths match actual files in references/; it stays just short of 5 because several referenced rules are also fully inlined in the body (Hard Rules), creating some duplication between overview and bundle.

4 / 5

Total

14

/

20

Passed

Description

53%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 gives a reasonably specific, well-scoped statement of what the skill does across five screening dimensions, but it lacks an explicit 'Use when...' trigger clause and the natural phrases users would actually say, which caps completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. 'Use when deciding whether a biomedical paper is worth a full read, a skim, or a skip, or when triaging a reading list.'

Surface the concrete output action ('read / skim / skip') in the description so the 'what' is complete.

Include natural user phrasing such as 'triage these papers', 'should I read this paper', or 'skim or skip' to improve trigger-term quality.

DimensionReasoningScore

Specificity

It names the domain (biomedical paper triage) and several concrete actions ('screening for question fit, design quality, sample adequacy, methodological novelty, and reproducibility value'), giving comprehensive screening dimensions, but it omits the actual output action (read/skim/skip) so minor gaps remain.

4 / 5

Completeness

It clearly states 'what' (screens papers across five named criteria), but 'when' is only weakly implied via 'worth deep reading' with no explicit 'Use when...' clause, so per the judging guideline completeness caps at 3.

3 / 5

Trigger Term Quality

Phrases like 'worth deep reading' and 'biomedical paper' are mildly natural, but it lacks the common trigger phrases a user would actually say ('is this paper worth reading', 'triage these papers', 'skim or skip'), giving only minimal natural keyword coverage.

2 / 5

Distinctiveness Conflict Risk

'biomedical paper ... worth deep reading ... reproducibility value' carves a clear niche distinct from general paper or PDF skills, with only minor overlap risk against a broader literature-review skill.

4 / 5

Total

13

/

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.