CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

journal-latest-issue

Retrieve the latest journal issue's table of contents and abstracts from URL/DOI/PMID/RSS/TOC sources, then generate Chinese key points locally (no external translation APIs) when a new issue needs quick review and archiving.

Quality

72%

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/journal-latest-issue/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

56%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 core usage guidance is genuinely actionable — concrete CLI examples, flags, input formats, and outputs are all well documented — but the body is padded with ~90 lines of generic validation/output-contract boilerplate and duplicated sections, and it references a script that is missing from the bundle. Trimming the filler and shipping the referenced script would lift the weakest dimensions.

Suggestions

Delete the duplicated 'Quick Validation' section (it repeats the 'Validation Shortcut' --help command) and cut the generic boilerplate sections ('Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Deterministic Output Rules', 'Completion Checklist') down to the few lines that carry skill-specific information.

Ship scripts/journal_digest.py in the bundle (or remove/adjust the references to it) so the documented commands are executable as delivered rather than pointing at a missing file.

Merge the overlapping procedural sections ('Recommended Workflow', 'Input Validation', 'Validation and Safety Rules') into one concise, concrete workflow that sequences the actual steps: run the --help check, run the digest command, verify output.md/output.csv were produced.

DimensionReasoningScore

Conciseness

Roughly half of the 176-line body is generic template boilerplate ('Required Inputs', 'Output Contract', 'Validation and Safety Rules', 'Failure Handling', 'Deterministic Output Rules', 'Completion Checklist') that states only platitudes like 'Return a structured deliverable that is directly usable without reformatting', and the same --help validation command is duplicated in 'Validation Shortcut' and 'Quick Validation'. Several padded sections add no skill-specific value, matching the 'noticeably verbose' anchor.

2 / 5

Actionability

Provides concrete, complete CLI invocations ('python scripts/journal_digest.py --journal "Nature" --rss "..."', '--json input.json', flags with defaults like '--max-items 20'), but the referenced scripts/journal_digest.py is absent from the bundle, so the commands cannot be executed or verified as shipped — a minor gap that keeps it below fully executable.

4 / 5

Workflow Clarity

An explicit validation checkpoint exists ('Run this minimal command first to verify the supported execution path'), and batch mode is covered, so the batch-operation cap at 3 does not apply; however, the 'Recommended Workflow' steps are abstract ('Select the documented execution path and prefer the simplest supported command') and checkpoints are diffused across duplicated sections rather than integrated into a coherent sequence.

4 / 5

Progressive Disclosure

Section headers give the body structure, but no bundle files exist at all while the body references scripts/journal_digest.py, and large boilerplate sections that should be trimmed or split remain inlined. Structure is present but organization and reference signaling fall short of the 'good structure' anchor.

3 / 5

Total

13

/

20

Passed

Description

78%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 with concrete actions, explicit source types, both what- and when-clauses, and a distinctive niche. Its main weaknesses are a when-clause that could use more natural trigger phrasing and slightly incomplete coverage of the skill's output capabilities.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Retrieve the latest journal issue's table of contents and abstracts', 'generate Chinese key points locally') and names multiple source types ('URL/DOI/PMID/RSS/TOC'), but omits the export side (Markdown/CSV) mentioned in the body, so coverage has minor gaps rather than being comprehensive.

4 / 5

Completeness

Both 'what' (retrieve TOC and abstracts, generate Chinese key points locally) and an explicit 'when' ('when a new issue needs quick review and archiving') are present; the when-clause is explicit but could be more specific with concrete user trigger phrases, so it is not a 5.

4 / 5

Trigger Term Quality

Natural phrases like 'latest journal issue', 'table of contents', 'abstracts', 'RSS', and 'Chinese key points' are present and would plausibly be said by a user, but common variations such as 'journal digest', 'new articles', or 'scan a journal' are missing, keeping it below comprehensive coverage.

4 / 5

Distinctiveness Conflict Risk

The combination of latest-issue TOC retrieval with locally generated Chinese key points (and an explicit no-external-translation-APIs constraint) is a clear niche with distinct triggers and minimal overlap risk with other 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.

Validation — 14 / 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: 5 missing

Warning

Total

14

/

16

Passed

Repository

aipoch/medical-research-skills

Path

scientific-skills/Evidence Insight/journal-latest-issue/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.