citation-management

Comprehensive citation management for academic research. Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries. This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing.

1.84x

Quality

71%

Does it follow best practices?

Impact

81%

1.84x

Average score across 3 eval scenarios

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./writing_skills/citation-management/SKILL.md

Quality

Content

60%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 body delivers highly actionable, executable command guidance over a well-sequenced five-phase workflow with real validation checkpoints, backed by a genuine, well-organized bundle. Its main weakness is verbosity: heavy duplication of script usage across three sections, an off-topic schematics section referencing a nonexistent script, and inline content that belongs in the existing reference files.

Suggestions

Eliminate duplication: the 'Tools and Scripts' section and the Example Workflows largely repeat the per-script usage commands already shown in Core Workflow — keep one canonical usage per script (or move it to the script's reference file) and cut the rest.

Remove the 'Visual Enhancement with Scientific Schematics' section: it is off-topic for citation management, references a nonexistent scripts/generate_schematic.py, and adds ~30 lines of padding to the context window.

Move the Google Scholar/PubMed operator tables and Best Practices detail into the corresponding references/ files, leaving the body as a lean overview with clearly signaled one-level-deep pointers.

Dimension	Reasoning	Score
Conciseness	The ~1,100-line body is noticeably verbose: every script's usage examples appear twice (Core Workflow and Tools and Scripts) and again in Example Workflows; the off-topic 'Visual Enhancement with Scientific Schematics' section discusses diagram generation and 'Nano Banana Pro'; and Best Practices/Common Pitfalls restate knowledge Claude already has (e.g., 'Use -- for page ranges (not single dash)'). It is above anchor 1 because there are no elementary concept tutorials and the material is accurate, but well below anchor 3 given whole sections are removable duplication.	2 / 5
Actionability	Guidance is largely copy-paste ready: complete commands with flags, outputs, JSON report schemas, and end-to-end example pipelines. Minor gaps prevent a 5: the body instructs 'python scripts/generate_schematic.py' but that script does not exist in scripts/, and Example 4 says 'Extract the top 10 by citation count' with no command. It is above anchor 3 because nearly all guidance is executable rather than pseudocode.	4 / 5
Workflow Clarity	Five clearly sequenced phases each state a goal, validation is a dedicated phase with --auto-fix/--report flags, and the example workflows include review steps ('Review validation report and fix any remaining issues') forming feedback loops for these batch operations. Not anchor 5: the bundled citation_checklist.md is never woven into the workflow and error-recovery guidance after validation is thin ('fix any remaining issues' with no how).	4 / 5
Progressive Disclosure	All five referenced files in references/ exist, are substantial (700-900 lines each), one level deep, and clearly signaled inline ('see references/google_scholar_search.md'), and all bundled scripts and assets are real. Not anchor 5: substantial content that duplicates the reference files (operator tables, per-script tool documentation) is inlined in the body, and one referenced path (scripts/generate_schematic.py) is broken.	4 / 5
	Total	14 / 20 Passed

Description

83%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, comprehensive capability statements and an explicit, well-phrased 'use when' trigger clause. The only notable deductions are a second-person slip ('when you need to find papers') and a few missing natural synonyms such as 'bibliography'.

Dimension	Reasoning	Score
Specificity	The description lists four concrete actions covering the full workflow ('Search Google Scholar and PubMed for papers, extract accurate metadata, validate citations, and generate properly formatted BibTeX entries'), matching the comprehensive anchor, but the second-person phrasing 'when you need to find papers' incurs the mandated 1-point penalty. It is above anchor 3 because coverage is comprehensive rather than 1-2 actions.	4 / 5
Completeness	It explicitly answers both 'what' (search, extract, validate, generate BibTeX) and 'when' ('This skill should be used when you need to find papers, verify citation information, convert DOIs to BibTeX, or ensure reference accuracy in scientific writing') with concrete trigger phrases. Anchor 4 does not fit because the 'when' clause is already explicit and specific rather than merely present.	5 / 5
Trigger Term Quality	Natural trigger phrases are present ('find papers', 'verify citation information', 'convert DOIs to BibTeX', 'ensure reference accuracy') and would be said by real users. It falls short of anchor 5 because common synonyms like 'bibliography', 'references list', or '.bib' files are missing.	4 / 5
Distinctiveness Conflict Risk	The citation-management niche is well distinguished by tool-specific triggers (Google Scholar, PubMed, DOIs, BibTeX). Minor overlap risk remains with a literature-search/review skill since 'find papers' is a trigger a search-focused skill would also claim. Not anchor 5: that overlap is real, though small.	4 / 5
	Total	17 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (1114 lines); consider splitting into references/ and linking	Warning
metadata_version	'metadata.version' is missing	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	13 / 16 Passed

Repository: fernandezbaptiste/CatMaster
Path: writing_skills/citation-management/SKILL.md
Commit: c87fc76

Reviewed: 2 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.