figure-reference-checker

Use figure reference checker for academic writing workflows that need structured execution, explicit assumptions, and clear output boundaries.

Quality

53%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./scientific-skills/Academic Writing/figure-reference-checker/SKILL.md

Quality

Content

50%

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

The body provides real, executable commands and a genuine script, but it is bloated with generic process boilerplate and its workflow covers request triage rather than the figure-checking task. A file-handling bug in the headline usage example further weakens actionability.

Suggestions

Remove generic template boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria test cases, Lifecycle Status) that does not add figure-checking-specific value.

Replace the request-triage Workflow with the actual technical workflow: run the checker, parse its output, verify figure-label consistency, and report orphans.

Fix the --manuscript usage so main.py reads the file path instead of regex-matching the literal argument string; otherwise `--manuscript paper.docx` does not check the document.

Dimension	Reasoning	Score
Conciseness	Concrete commands and a parameter table earn their place, but the body is heavily padded with generic template boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria test cases like 'Successfully executes main functionality', Lifecycle Status) that Claude does not need.	2 / 3
Actionability	Executable commands are present (py_compile, --help, --manuscript), but the documented `--manuscript paper.docx` example is misleading because main.py treats the argument as literal text rather than reading the file, so the example does not actually check the document.	2 / 3
Workflow Clarity	The 5-step Workflow has sequence and an early-stop/fallback checkpoint, but it describes request triage rather than the actual checking task; the technical flow (run checker, parse output, verify consistency) is missing.	2 / 3
Progressive Disclosure	There is one clearly signaled one-level reference (references/audit-reference.md) and a real script, but the SKILL.md itself is a monolithic ~190-line document with process content that should be split out.	2 / 3
	Total	8 / 12 Passed

Description

57%

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 identifies a clear niche but leans on abstract process language instead of concrete capabilities and natural trigger terms. It answers 'when' only implicitly and 'what' only by tool name.

Suggestions

Rewrite the description to state concrete actions (e.g., 'Detect orphaned figure references and check figure-label consistency in manuscripts') instead of abstract process qualities like 'structured execution'.

Add an explicit 'Use when...' trigger clause naming natural terms users would say (e.g., 'Use when reviewing manuscripts for figure references, citations, or label consistency').

Dimension	Reasoning	Score
Specificity	Names the domain ('figure reference checker', 'academic writing workflows') but describes abstract process qualities ('structured execution, explicit assumptions, and clear output boundaries') rather than concrete actions like detecting orphaned references or checking label consistency.	2 / 3
Completeness	A 'Use ... for' clause gives an implied trigger, but the 'what' is weak (only the tool name, not what it does) and there is no explicit 'Use when...' trigger guidance, capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Contains some relevant natural terms ('figure reference', 'academic writing') but is padded with process jargon ('structured execution', 'clear output boundaries') that users would not naturally say, and misses common variations like 'manuscripts', 'citations', or 'labels'.	2 / 3
Distinctiveness Conflict Risk	The 'figure reference checker' niche for academic writing is clearly scoped and unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 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: aipoch/medical-research-skills
Commit: 7cc5680

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.