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.

48

Quality

51%

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/Academic Writing/reference-style-sync/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 with concrete commands and examples but is heavily padded with redundant boilerplate and inlined sections that should be split out. Destructive/batch operations lack validation checkpoints, capping workflow clarity.

Suggestions

Remove the repeated verbatim description and the empty 'See ## X above' stub sections; consolidate the lifecycle/risk/security/evaluation boilerplate into a separate reference file.

Add an explicit validation/dry-run checkpoint before destructive operations (e.g., '--check-only' first, then confirm before overwrite/deduplicate), with a validate->fix->retry loop.

Move the Repair Rules, Risk Assessment, Security Checklist, and Evaluation Criteria sections into references/ files and keep SKILL.md as a concise overview pointing to them.

DimensionReasoningScore

Conciseness

The ~360-line body is noticeably verbose: it restates the description verbatim three times, contains empty 'See ## X above for related details' stubs, and piles on lifecycle/risk/security/evaluation boilerplate, matching anchor 2 rather than the 3 anchor's 'some unnecessary explanation'.

2 / 5

Actionability

Provides copy-paste-ready CLI commands, a Python API example, a parameter table, and before/after repair examples covering common cases, with only minor gaps (e.g., Python version inconsistency 3.10+ vs 3.8+, no requirements.txt shown), fitting anchor 4.

4 / 5

Workflow Clarity

As a batch/destructive skill it has a sequenced workflow and error handling but no explicit validation checkpoint before destructive operations (only a py_compile parse check), so per the rubric's feedback-loop cap it cannot exceed 3.

3 / 5

Progressive Disclosure

Bundle files (references/audit-reference.md, scripts/main.py) are real, one level deep, and signaled, but large content that belongs in separate files (risk, security, evaluation, repair rules) is inlined in a monolithic body, balancing at anchor 3.

3 / 5

Total

12

/

20

Passed

Description

53%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 communicates a clear purpose but relies on marketing language and lacks explicit trigger guidance and named tools/formats. It scores in the mid-range across all dimensions.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger phrases (e.g., Zotero/EndNote exports, .bib/.ris files, citation style conversion).

Replace 'One-click'/'intelligently' with a concrete list of actions (detect and fix metadata, unify citation styles, deduplicate entries, complete missing DOI/page fields).

Include natural terms users say — tool names (Zotero, EndNote) and file extensions (.bib, .ris) — to improve trigger matching and distinctiveness.

DimensionReasoningScore

Specificity

Names the domain and a couple of concrete actions ('synchronization and standardization of reference formats', 'fixing metadata errors'), but marketing phrasing ('One-click', 'intelligently') replaces a comprehensive list of concrete actions, matching anchor 3 rather than 4.

3 / 5

Completeness

Gives a clear 'what' but no explicit 'Use when...' trigger clause, and the rubric caps completeness at 3 when trigger guidance is missing; it is not the 4 anchor because 'when' is absent rather than merely weak.

3 / 5

Trigger Term Quality

Includes relevant keywords ('reference formats', 'literature management tools', 'metadata errors') but omits natural user/tool terms like Zotero, EndNote, BibTeX, RIS, citations, or .bib, fitting anchor 3 ('some relevant keywords but missing common variations or synonyms').

3 / 5

Distinctiveness Conflict Risk

The reference-format/literature-tool niche is mostly distinct with only minor overlap risk against generic citation skills, but the tool-agnostic wording keeps it from fully locking the niche as the 5 anchor would.

4 / 5

Total

13

/

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.