Name: citation-management
Rating: 43.2 (1 reviews)
Author: administrakt0r

Blog Docs Log in Get started

citation-management

Manage citations systematically throughout the research and writing process.

Quality

45%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/citation-management/SKILL.md

The canonical home for this skill is citation-management in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

37%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 skill has a well-structured Phase 1-5 workflow with explicit validation and feedback loops, but is undermined by severe verbosity (known-concept explanations, redundancy, off-topic schematic padding) and by a complete failure of progressive disclosure: every referenced bundle file and script is absent, making the concrete-looking bash examples non-executable. The body is essentially a 32KB monolith that promises supporting materials it does not deliver.

Suggestions

Actually create the referenced bundle files (references/*.md, scripts/*.py, assets/*) or remove all dangling references and inline only what is essential, so progressive disclosure is real rather than signaled-to-nothing.

Cut the 'Visual Enhancement with Scientific Schematics' section and remove explanations of concepts Claude already knows (MeSH, Google Scholar scope, BibTeX entry types) to roughly halve the body length.

De-duplicate script usage: present each script's full invocation once in 'Tools and Scripts' and reference it from Core Workflow / Example Workflows rather than repeating the same bash blocks 2-3 times.

Dimension	Reasoning	Score
Conciseness	Severely verbose at ~1100 lines: explains known concepts like 'what MeSH is, what Google Scholar covers, what BibTeX entry types are', repeats script usages '2-3 times across Core Workflow, Tools and Scripts, and Example Workflows', and pads with an off-topic 'Visual Enhancement with Scientific Schematics' section promoting another skill and 'Nano Banana Pro' AI generation.	2 / 5
Actionability	Commands are concrete with real flags (e.g. 'python scripts/validate_citations.py --auto-fix --report') and would be copy-paste ready, but every referenced script and asset (search_google_scholar.py, format_bibtex.py, assets/bibtex_template.bib, etc.) does not exist, so nothing actually executes — guidance is specific but non-functional.	2 / 5
Workflow Clarity	Phase 1-5 sequence is clear and numbered with explicit validation checkpoints ('validate_citations.py with --auto-fix and --report') and a feedback loop ('Review validation report and fix any remaining issues'), plus batch deduplication; docked one point because the validation tooling itself is dangling rather than present.	4 / 5
Progressive Disclosure	References are well-signaled and one level deep (references/.md, scripts/.py, assets/*), but the 'references/, scripts/, assets/ directories are absent entirely' — every signaled reference dangles to nothing, forcing all detail inline into a monolithic 1100-line body.	2 / 5
	Total	10 / 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 names a clear niche (citations) but relies on the vague verb 'Manage' and the filler adverb 'systematically' rather than enumerating concrete actions. It lacks an explicit 'Use when...' trigger clause and misses common synonym keywords users might say. Adding concrete actions and trigger phrases would lift all three lowest dimensions.

Suggestions

Replace 'Manage' with concrete actions, e.g., 'Insert, format, verify, and organize citations and bibliographies throughout the research and writing process.'

Add an explicit trigger clause such as 'Use when drafting or editing a document that needs citation tracking, bibliography generation, or source verification.'

Include natural synonym keywords users may say — 'references', 'bibliography', 'sources', 'footnotes', 'cite' — to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('citations') and implies actions 'throughout the research and writing process', but the only action verb 'Manage' is vague and 'systematically' is filler, with no concrete operations like format, insert, verify, or organize listed.	3 / 5
Completeness	The 'what' is clear ('Manage citations') and 'when' is weakly implied ('throughout the research and writing process'), but there is no explicit 'Use when...' trigger clause, capping completeness at 3.	3 / 5
Trigger Term Quality	'citations' is a natural keyword users would say, and 'research' and 'writing' are relevant but generic; common variations like 'references', 'bibliography', 'cite', 'sources', and 'footnotes' are missing.	3 / 5
Distinctiveness Conflict Risk	'Manage citations' carves a clear niche with only minor overlap against general research or writing skills; it is distinguishable from broader document or writing-skill descriptions.	4 / 5
	Total	13 / 20 Passed

Validation

75%

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 — 12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 77 missing	Warning

	Total	12 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills/skills/citation-management/SKILL.md
Commit: 57c135b

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.