Use when formatting references for journal submission, converting between citation styles (APA, MLA, Vancouver, Chicago), generating bibliographies for manuscripts, or ensuring consistent reference formatting. Automatically formats citations and bibliographies in 1000+ academic styles. Ensures reference accuracy, completeness, and compliance with journal requirements. Supports batch conversion and integration with reference managers.
73
Quality
67%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./scientific-skills/Academic Writing/citation-formatter/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It opens with explicit trigger guidance ('Use when...'), lists specific citation styles by name, describes concrete capabilities, and clearly targets the academic citation management niche. The description uses proper third-person voice throughout and provides comprehensive trigger terms that academics would naturally use.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: 'formats citations and bibliographies', 'converting between citation styles', 'generating bibliographies', 'batch conversion', 'integration with reference managers'. Specific style names (APA, MLA, Vancouver, Chicago) add further concreteness. | 3 / 3 |
Completeness | Explicitly answers both what ('formats citations and bibliographies in 1000+ academic styles', 'ensures reference accuracy') AND when ('Use when formatting references for journal submission, converting between citation styles...'). The 'Use when' clause is present and detailed. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'references', 'journal submission', 'citation styles', 'APA', 'MLA', 'Vancouver', 'Chicago', 'bibliographies', 'manuscripts', 'reference formatting', 'reference managers'. These are terms academics naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on academic citation/bibliography formatting with specific style names and academic context (journal submission, manuscripts). Unlikely to conflict with general document or writing skills due to the specialized academic focus. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill suffers from severe verbosity and redundancy, with the description repeated multiple times and generic boilerplate sections that don't add value. While it contains some useful concrete code examples for citation formatting, much of the content is placeholder code or abstract workflow descriptions. The skill would benefit greatly from aggressive trimming and focusing on the specific, actionable guidance for citation formatting.
Suggestions
Remove all redundant content: the description appears 3+ times, 'See ## Workflow above' references non-existent content, and generic sections (Quality Checklist, Response Template, Output Requirements) should be deleted
Replace placeholder code in Core Capabilities (`result = tool.execute(data)`) with actual executable examples showing specific citation formatting operations
Add concrete validation steps specific to citation formatting: checking DOI validity, detecting missing required fields, verifying author name formats
Consolidate the Quick Start section with the scattered code examples into one clear, executable workflow with specific input/output examples
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with massive redundancy - the description is repeated multiple times verbatim, sections reference each other circularly ('See ## Workflow above'), and includes extensive boilerplate that adds no value (generic quality checklists, response templates). Many sections explain obvious concepts Claude already knows. | 1 / 3 |
Actionability | Contains some concrete Python code examples in Quick Start section that show actual API usage, but Core Capabilities sections have placeholder code (`result = tool.execute(data)`) that is not executable. The command line example is concrete but the script's actual functionality is unclear. | 2 / 3 |
Workflow Clarity | Has numbered workflow steps but they are generic and abstract ('Confirm the user objective', 'Validate that the request matches'). No validation checkpoints specific to citation formatting. Missing feedback loops for handling malformed references or style conversion errors. | 2 / 3 |
Progressive Disclosure | References external files (references/guide.md, references/examples/) but the main document is bloated with content that should be in those files. Multiple redundant sections cover similar ground. The structure exists but content is poorly distributed. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
4a48721
Table of Contents
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.