inno-reference-audit

This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports ml-paper-writing by providing detailed verification principles and common error patterns.

Quality

80%

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 ./skills/inno-reference-audit/SKILL.md

Quality

Content

77%

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

The content is highly actionable with a clear, validated workflow and a concrete worked example, but it is verbose due to heavy duplication and fails to leverage its own bundle files, leaving detailed material inline rather than split into the existing references.

Suggestions

Deduplicate the workflow: keep one authoritative sequenced version and have 'Summary' and 'Best Practices' reference it instead of restating it, removing the repeated Core Principle lines.

Link the existing bundle files from the body (e.g., 'For the full matching algorithm, see references/verification-rules.md; for error patterns, see references/common-errors.md') so detailed material lives in the reference files rather than inline.

Dimension	Reasoning	Score
Conciseness	The body is mostly useful but repeats the same workflow across 'Verification Workflow', the 'Verification Step Example', 'Summary / Key Steps', and 'Best Practices', and restates the Core Principle verbatim in multiple places; tightening the duplication would improve token efficiency without losing information.	2 / 3
Actionability	It gives copy-paste-ready WebSearch queries ('site:scholar.google.com [paper title] [first author]'), a fully worked Transformer-paper example with concrete queries and results, and explicit BibTeX steps, providing concrete executable guidance.	3 / 3
Workflow Clarity	The process is laid out as a flow diagram plus numbered steps with explicit gatekeeping ('Add to bibliography only after verification passes') and a dedicated failure-recovery section with feedback loops (try different queries, mark [CITATION NEEDED], notify the user).	3 / 3
Progressive Disclosure	Bundle files exist (references/common-errors.md, verification-rules.md, api-usage.md and scripts/*.py, each with a README), but the SKILL.md body never links or signals them; instead it inlines detailed verification rules and common-error patterns that overlap with those separate files, matching the anchor where references are present but not clearly signaled and inline content should be split out.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 has clear triggers and answers both 'what' and 'when' well, but its capability list is a cluster of guidance-flavored actions rather than distinct concrete operations, and its tight coupling to ml-paper-writing raises conflict risk.

Suggestions

Replace the guidance-flavored verbs with distinct concrete actions (e.g., 'Verify citations against Google Scholar, fetch BibTeX entries, flag unverifiable references with [CITATION NEEDED]') to lift specificity.

Clarify the boundary with ml-paper-writing: state when this skill should trigger on its own (e.g., standalone citation-verification queries) versus when ml-paper-writing owns the workflow, to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	The description names the domain ('citation verification in academic writing') and a few action variants ('provides reference guidance', 'providing detailed verification principles and common error patterns'), but these are all shades of 'provide guidance' rather than multiple distinct concrete actions as the score-3 anchor requires.	2 / 3
Completeness	It explicitly states both what the skill does ('provides reference guidance for citation verification') and when to use it ('Use when the user asks about...'), with explicit triggers, matching the score-3 anchor.	3 / 3
Trigger Term Quality	It lists natural user phrasings ('citation verification best practices', 'how to verify references', 'preventing fake citations', 'guidance on citation accuracy') that a user would plausibly say, giving good coverage of trigger terms.	3 / 3
Distinctiveness Conflict Risk	Citation verification is a recognizable niche, but the description explicitly ties the skill to ml-paper-writing ('supports ml-paper-writing by providing...'), and the body states verification is integrated into ml-paper-writing, creating real overlap and uncertain trigger boundaries between the two skills.	2 / 3
	Total	10 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: OpenLAIR/dr-claw
Path: skills/inno-reference-audit/SKILL.md
Commit: 6da7f7c

Reviewed: about 7 hours 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.