CtrlK
BlogDocsLog inGet started
Tessl Logo

reference-style-sync

One-click synchronization and standardization of reference formats in literature management tools, intelligently fixing metadata errors.

47

Quality

50%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/reference-style-sync/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers genuinely useful concrete guidance (CLI, parameters, repair rules, output samples) but is undermined by verbosity, broken internal cross-references, an inaccurate Python API example, and a missing output-validation feedback loop for batch operations. It lands at the mid anchor on every dimension.

Suggestions

Remove the repeated verbatim description and fix or delete the broken 'See ## Features/Prerequisites/Usage/Workflow above' cross-references (those sections appear below, not above).

Correct the Python API example to match scripts/main.py, which exposes load/fix_metadata/deduplicate/quality_check/export — there is no convert_style method.

Add an explicit validate-output → fix → retry feedback loop for the batch/destructive processing path so workflow clarity can reach 3.

DimensionReasoningScore

Conciseness

The core content (CLI usage, parameter table, repair rules, output examples) is efficient, but the body is padded with repeated verbatim descriptions, generic boilerplate (risk/security/evaluation/lifecycle tables), and broken 'See ## X above' cross-references that earn no value.

2 / 3

Actionability

CLI examples and the parameter table are concrete and copy-paste ready, but the Python API example calls sync.convert_style(target_style='apa'), a method that does not exist in scripts/main.py, so that example is not executable.

2 / 3

Workflow Clarity

A workflow with scope-validation and fallback steps is present, but for a batch/destructive operation the missing explicit output-validation feedback loop (validate output → fix → retry) caps workflow clarity at 2.

2 / 3

Progressive Disclosure

A real one-level-deep reference (references/audit-reference.md) is clearly signaled, but the SKILL.md body is a 360-line monolith with inline content that could be split and several 'See above' pointers that reference sections actually located below.

2 / 3

Total

8

/

12

Passed

Description

50%

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 states a clear purpose but leans on marketing language ('One-click', 'intelligently') and lacks an explicit 'Use when' trigger clause and the natural tool/format keywords users would say. It sits at the mid anchor across all dimensions.

Suggestions

Add an explicit 'Use when...' clause with natural user phrases, e.g. 'Use when converting references to APA/MLA/AMA/Vancouver, fixing Zotero or EndNote metadata, or cleaning up BibTeX/RIS files'.

Replace 'One-click' and 'intelligently' with concrete actions (detect and fix metadata, deduplicate entries, convert citation styles) and name the specific tools and formats (Zotero, EndNote, BibTeX, RIS).

DimensionReasoningScore

Specificity

Names the domain ('reference formats in literature management tools') and a couple of actions ('standardization of reference formats', 'fixing metadata errors'), but 'One-click' is marketing fluff and it does not list multiple concrete actions like the score-3 anchor (extract, fill, merge).

2 / 3

Completeness

Clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, which per the judging guidelines caps completeness at 2.

2 / 3

Trigger Term Quality

Contains some relevant keywords ('reference formats', 'metadata errors') but omits the natural terms users actually say — Zotero, EndNote, BibTeX, RIS, APA/MLA/Vancouver, 'fix my citations'.

2 / 3

Distinctiveness Conflict Risk

The reference-format niche is somewhat specific, but without tool-specific triggers (Zotero/EndNote/BibTeX) it could overlap with general citation or bibliography skills.

2 / 3

Total

8

/

12

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.