CtrlK
BlogDocsLog inGet started
Tessl Logo

literature-statistics

Generate statistics for publication-year and journal distributions from local references or PDFs; use when you need standardized Year/Journal tables and a summary without any network access.

58

Quality

68%

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/Other/literature-statistics/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

53%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 delivers specific, actionable parsing and normalization guidance with a clear pipeline, but is weighed down by generic template boilerplate, a missing referenced script, and a fabricated validation example. Tightening the lower half and aligning references with actual files would lift it substantially.

Suggestions

Remove or collapse the generic boilerplate sections ('When Not to Use', 'Required Inputs', 'Recommended Workflow', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') into a few skill-specific lines, since most repeat obvious guidance.

Either add the referenced scripts/process_references.py or replace its example with the actual available entry point so the documented commands are all runnable.

Fix the Quick Validation block: replace the fabricated --help output with the real help text, and fold an explicit validate-checkpoint step into the Processing Pipeline for the batch case.

DimensionReasoningScore

Conciseness

The core (parsing rules, normalization, pipeline, output format) is efficient, but roughly half the body is generic template boilerplate ('When Not to Use', 'Required Inputs', 'Recommended Workflow', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling') that restates obvious guidance and pads the token budget.

2 / 5

Actionability

Provides concrete executable commands (process_pdfs.py invocation, pip install) and detailed parsing/normalization rules, but references a non-existent scripts/process_references.py and shows a fabricated --help expected output, leaving minor gaps.

4 / 5

Workflow Clarity

An 8-step Processing Pipeline is clearly sequenced, but as a batch operation it lacks integrated validate-then-fix checkpoints inside the sequence; validation appears only as separate generic sections and the Quick Validation output is fabricated, so it sits at the cap.

3 / 5

Progressive Disclosure

Well-organized sections with a real one-level reference (references/examples.md, scripts/process_pdfs.py, scripts/requirements.txt all exist) and clear navigation, but one referenced file (scripts/process_references.py) is missing and the body leans monolithic.

4 / 5

Total

13

/

20

Passed

Description

82%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 clearly states both what the skill does and when to use it, with a distinct local-only niche. Its only real weakness is second-person voice ('use when you need'), which slightly weakens specificity and naturalness.

DimensionReasoningScore

Specificity

States concrete actions ('Generate statistics for publication-year and journal distributions', 'standardized Year/Journal tables and a summary') but uses second person ('use when you need'), which per rubric reduces specificity by one from a 4.

3 / 5

Completeness

Explicitly answers both what ('Generate statistics for publication-year and journal distributions from local references or PDFs') and when ('use when you need standardized Year/Journal tables and a summary without any network access') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Good natural coverage ('publication-year and journal distributions', 'local references or PDFs', 'Year/Journal tables') but lacks common file-extension synonyms like .bib/.ris and the phrase 'literature review'.

4 / 5

Distinctiveness Conflict Risk

The niche of publication-year/journal distributions from local references or PDFs with no network access is clearly scoped and unlikely to trigger for unrelated skills.

5 / 5

Total

17

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

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.