CtrlK
BlogDocsLog inGet started
Tessl Logo

scite-database

Access Scite.ai Smart Citations to classify how a paper is cited (supporting, contrasting, mentioning) and assess scientific claims; use it when you need to evaluate a paper’s reliability or its acceptance in the literature.

59

Quality

69%

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 ./scientific-skills/Evidence Insight/scite-database/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

46%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 content is actionable thanks to concrete CLI examples, but it is undermined by duplicated sections, templated padding, contradictory dependency info, and a false claim about additional scripts that do not exist. Structure and conciseness need a cleanup pass.

Suggestions

Remove the duplicated sections (When to Use, Key Features, Dependencies, Example Usage, Implementation Details) — keep a single canonical version of each.

Fix the contradictory dependency info (Python 3.10+ vs 3.9+) and correct the '3 additional script(s)' claim, since only scripts/scite_client.py exists.

Trim templated filler ('scope-focused workflow aligned to', 'use this skill when the user expects a concrete deliverable') and add an explicit validate/retry checkpoint in the run plan.

DimensionReasoningScore

Conciseness

Noticeably verbose and padded: the body duplicates entire sections (two 'When to Use', two 'Key Features', two 'Dependencies', two 'Example Usage', two 'Implementation Details') and includes templated filler ('Use this skill when the user expects a concrete deliverable') plus contradictory dependency statements (Python 3.10+ vs 3.9+).

2 / 5

Actionability

Provides executable commands ('python scripts/scite_client.py "10.1038/nature12345"', '--format json') with concrete example output shapes; minor gaps such as not showing how failures surface to the caller.

4 / 5

Workflow Clarity

An 'Example run plan' gives a numbered sequence, but validation checkpoints are implicit (relying on the script's own exit code) and there is no explicit verify/retry loop before returning the artifact.

3 / 5

Progressive Disclosure

Only one bundle file actually exists (scripts/scite_client.py), yet the body claims '3 additional script(s)' that are absent, and content is duplicated inline rather than split into a references/ directory — structure is misleading rather than well-organized.

2 / 5

Total

11

/

20

Passed

Description

92%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 strong: it states concrete capabilities, an explicit use-when trigger, and a distinctive niche tied to Scite.ai Smart Citations. Its only weakness is slightly limited synonym/extension coverage in trigger terms.

DimensionReasoningScore

Specificity

Names the domain (Scite.ai Smart Citations) and multiple concrete actions — 'classify how a paper is cited (supporting, contrasting, mentioning) and assess scientific claims' — giving comprehensive coverage.

5 / 5

Completeness

Explicitly answers both 'what' (classify citations into supporting/contrasting/mentioning, assess claims) and 'when' ('use it when you need to evaluate a paper's reliability or its acceptance in the literature') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Includes natural phrases like 'evaluate a paper's reliability', 'acceptance in the literature', and 'scientific claims', but omits common synonyms/extensions such as '.doi', 'is this paper credible', or 'citation sentiment'.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (Scite.ai Smart Citations) with distinct triggers unlikely to fire for unrelated skills; minimal conflict risk.

5 / 5

Total

19

/

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.