citation-formatter

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.

Quality

60%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/Academic Writing/citation-formatter/SKILL.md

Quality

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 clearly communicates its purpose, lists concrete actions, includes an explicit 'Use when' clause with natural trigger terms, and occupies a distinct niche. The description uses proper third-person voice throughout and provides both breadth (1000+ styles) and specificity (named citation formats). Minor note: the claim of '1000+ academic styles' could be seen as slightly promotional, but it does convey scope effectively.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: formatting references, converting between citation styles (with named examples APA, MLA, Vancouver, Chicago), generating bibliographies, ensuring consistent formatting, batch conversion, and integration with reference managers.	3 / 3
Completeness	Clearly answers both 'what' (formats citations and bibliographies in 1000+ styles, ensures accuracy and compliance, supports batch conversion) and 'when' (explicit 'Use when' clause covering formatting references for journal submission, converting between citation styles, generating bibliographies, ensuring consistent formatting).	3 / 3
Trigger Term Quality	Excellent coverage of natural terms users would say: 'references', 'citation styles', 'APA', 'MLA', 'Vancouver', 'Chicago', 'bibliographies', 'manuscripts', 'journal submission', 'reference formatting', 'reference managers'. These are all terms a user would naturally use when needing this skill.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive niche focused specifically on academic citation and bibliography formatting. The specific citation style names (APA, MLA, Vancouver, Chicago), 'journal submission', and 'reference managers' create clear, unique triggers unlikely to conflict with other skills.	3 / 3
	Total	12 / 12 Passed

Implementation

20%

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

This skill is heavily padded with generic boilerplate that is not specific to citation formatting, including repeated copy-pasted descriptions and placeholder code blocks. The Quick Start section shows promising API examples but they reference unverified modules, and the Core Capabilities sections are empty stubs. The audit-ready command includes a medical clinical note as sample input, suggesting template-generated content that wasn't properly customized for this skill's domain.

Suggestions

Remove all duplicate content: the description appears verbatim in at least 3 sections (When to Use, Key Features, When to Use This Skill). Consolidate into one concise purpose statement.

Replace the placeholder Core Capabilities code blocks (`result = tool.execute(data)`) with actual executable examples showing real citation formatting, style conversion, and validation.

Remove generic boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling) that don't contain citation-specific guidance—these waste tokens on things Claude already knows how to do.

Fix the audit-ready command that uses a medical clinical note as input (`--input 'Audit validation sample with explicit symptoms, history, assessment...'`) to use an actual citation/reference as the sample input.

Dimension	Reasoning	Score
Conciseness	Extremely verbose and repetitive. The description is copy-pasted verbatim into 'When to Use', 'Key Features', and 'When to Use This Skill' sections. Generic boilerplate sections (Output Requirements, Response Template, Input Validation, Error Handling) pad the content significantly without adding citation-specific value. Many sections explain things Claude already knows.	1 / 3
Actionability	The Quick Start code references modules (scripts.main, scripts.citation_formatter) that may not exist and are not verified. Core Capabilities sections 1-4 contain only placeholder pseudocode (`result = tool.execute(data)`). No actual executable code for citation formatting is provided—just API calls to an unverified library with unverified method signatures.	1 / 3
Workflow Clarity	There is a numbered workflow and an 'Example run plan' with steps, but they are generic and not specific to citation formatting. No validation checkpoints specific to citation correctness (e.g., verifying DOI resolution, checking formatted output against style rules). The audit-ready commands include a bizarre medical-sounding input string unrelated to citation formatting.	2 / 3
Progressive Disclosure	References to `references/guide.md`, `references/examples/`, and `references/api-docs/` are present and one-level deep, which is good structure. However, no bundle files are provided to verify these exist, and the main SKILL.md itself is monolithic with excessive inline content that should be split out. The document is poorly organized with redundant sections.	2 / 3
	Total	6 / 12 Passed

Validation

90%

Warnings & errors only

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

Repository: aipoch/medical-research-skills
Commit: d3c2c0f

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.