CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quality-assessment

Automates critical appraisal and quality assessment for research papers by analyzing text against established methodological standards (such as risk of bias tools, quality checklists, or reporting guidelines) and synthesizing a structured evaluation report. Use when you need to assess the methodological quality, internal validity, or reporting completeness of any type of study—including RCTs, observational studies, systematic reviews, qualitative research, or diagnostic accuracy studies.

Quality

65%

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 ./scientific-skills/Data Analysis/quality-assessment/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

31%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 has a sound skeleton — a real 3-step appraisal workflow, an existing tool-mapping reference file, and a working PDF extraction script — but it is buried under ~15 sections of generic template filler that duplicate the description and add no skill-specific guidance. The core instructional content (how to actually perform and format the assessment) is missing, and the reference navigation is broken.

Suggestions

Delete the generic template sections (When to Use, Key Features, Dependencies, Implementation Details, Recommended Workflow, Deterministic Output Rules, Output Contract, Validation and Safety Rules, Failure Handling, Completion Checklist, Quick Validation, Scope Reminder) — they restate what Claude already knows and duplicate the description twice; keep only the workflow, study-design list, and helper-script usage.

Fix the reference navigation: replace the empty "## Tools (See references-quality assessment tool)" section with a proper link to the actual file, e.g. "**Tool selection**: See [quality assessment tool.md](references/quality%20assessment%20tool.md) for the study-design → tool mapping", and verify the filename matches.

Make the assessment step concrete: show an example of applying one tool (e.g., a mini ROBINS-I or Downs & Black table) and define the output structure for quality_assessment_result.md, so the deliverable format is executable rather than implied. Also correct the helper command to `python scripts/extract_pdf.py <input.pdf>` to match the script's required argument.

DimensionReasoningScore

Conciseness

Roughly 120 of 177 lines are generic template boilerplate Claude already knows ("Validate the request against the skill boundary", "Do not fabricate measurements", "Confirm all required inputs were present and valid"), and the frontmatter description is duplicated verbatim twice ("Key Features" and "Scope Reminder" sections). This is heavily padded with near-zero skill-specific value.

1 / 5

Actionability

There is some concrete guidance (the 3-step workflow, `python -m py_compile scripts/extract_pdf.py`, `--help` commands), but the core deliverable is never made concrete — no example of applying a checklist or structuring the assessment output — and the shown command `python extract_pdf.py` omits the required PDF argument while the path flip-flops between `extract_pdf.py` and `scripts/extract_pdf.py`.

3 / 5

Workflow Clarity

The core sequence is present ("Identify Study Design" → "Recommend Quality Assessment Tool" → "Complete Quality Assessment") but has no task-specific validation checkpoints or error-recovery loops (e.g., what to do when the study design is ambiguous or the extracted PDF text is empty), and the inconsistent script paths create confusion.

3 / 5

Progressive Disclosure

The one real reference (references/quality assessment tool.md) is signaled only through an empty garbled section header — "## Tools (See references-quality assessment tool)" — whose name does not match the actual filename, making the reference effectively buried; the rest of the body inlines generic boilerplate instead of pointing outward.

2 / 5

Total

9

/

20

Passed

Description

83%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 strong description: third-person, explicit what-and-when with concrete trigger scenarios and good domain keyword coverage. It is slightly long and abstract at the action level, and shares some trigger vocabulary with adjacent research skills.

DimensionReasoningScore

Specificity

"Automates critical appraisal and quality assessment... analyzing text against established methodological standards (such as risk of bias tools, quality checklists, or reporting guidelines) and synthesizing a structured evaluation report" lists several specific actions with concrete tool examples; it stays slightly abstract (no mention of producing item-by-item tool scoring or a report format), so it does not reach fully comprehensive coverage.

4 / 5

Completeness

It explicitly answers both what ("Automates critical appraisal and quality assessment for research papers by analyzing text against... standards... and synthesizing a structured evaluation report") and when ("Use when you need to assess the methodological quality, internal validity, or reporting completeness of any type of study—including RCTs, observational studies, systematic reviews...") with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Natural terms are well covered — "critical appraisal", "quality assessment", "risk of bias", "methodological quality", "internal validity", "reporting completeness", "RCT", "systematic reviews", "diagnostic accuracy" — but a few common user phrasings are missing (e.g., "appraise this paper", "grade the evidence", tool names like CASP or GRADE).

4 / 5

Distinctiveness Conflict Risk

The critical-appraisal niche is clear and distinct from extraction or search skills, but trigger terms like "systematic reviews" and "observational studies" create minor overlap risk with sibling literature-review/screening skills in the same medical-research collection.

4 / 5

Total

17

/

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.

Validation — 15 / 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

Path

scientific-skills/Data Analysis/quality-assessment/SKILL.md

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.