figure-reference-checker

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

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

Quality

Content

42%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 provides a few concrete executable commands and a real script, but is dominated by generic process-governance boilerplate unrelated to figure reference checking. The actual checking workflow and its validation are underspecified relative to the claimed features.

Suggestions

Remove generic governance boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Response Template, Output Contract, User Checkpoints) that is not specific to figure reference checking.

Add executable guidance and expected output for the actual checking tasks (orphaned reference detection, figure-label consistency, missing citations), or narrow the Features list to match what main.py actually does.

Add a concrete validate-fix-retry loop for the figure-checking operation rather than only governance stop/fallback steps.

Dimension	Reasoning	Score
Conciseness	The body is padded with generic governance boilerplate (Risk Assessment, Security Checklist, Evaluation Criteria, Lifecycle Status, Output Requirements, Response Template, Output Contract, Failure Handling, User Checkpoints, Quick Validation) that teaches Claude nothing it does not already know, matching 'Noticeably verbose; several unnecessary explanations or padded sections'. Not a 3 because the padding is extensive rather than a few trimmable instances.	2 / 5
Actionability	Concrete commands exist ('python -m py_compile scripts/main.py', 'python scripts/main.py --manuscript paper.docx') and a real bundled script is present, but guidance covers only invocation; the claimed Features (orphaned detection, label consistency, missing citations) have no executable guidance and main.py only regex-finds references, fitting 'Some concrete guidance but incomplete; missing key details'. Not a 4 because the executable surface does not cover the skill's stated purpose.	3 / 5
Workflow Clarity	The Workflow lists five sequenced steps with a stop-early and a fallback checkpoint, but these are governance steps ('Confirm the user objective', 'Validate that the request matches scope') rather than a concrete technical sequence with validation on the actual figure-checking operation, fitting 'Steps listed but validation gaps; checkpoints missing or implicit'. Not a 4 because there is no validate-fix-retry loop on the checking itself.	3 / 5
Progressive Disclosure	There is one clearly signaled one-level-deep reference (references/audit-reference.md, verified to exist) and a bundled script, but SKILL.md inlines large amounts of generic boilerplate that should be removed or split out, fitting 'Some structure but could be better organized; content that should be separate is inline'. Not a 4 because the SKILL.md is bloated rather than a lean overview.	3 / 5
	Total	11 / 20 Passed

Description

48%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 identifies a clear niche but relies on process-quality language ('structured execution, explicit assumptions, clear output boundaries') instead of concrete checking actions or natural trigger phrases. It answers what and when only weakly.

Suggestions

Replace process-quality language with concrete actions, e.g. 'Detect orphaned figure references, check figure-label consistency, and flag missing figure citations in manuscripts.'

Add natural trigger phrases users would actually say, e.g. 'Use when reviewing manuscripts, papers, or academic writing for figure/fig. reference consistency.'

Make the 'what' explicit rather than implied by the skill name alone.

Dimension	Reasoning	Score
Specificity	The description names the domain ('figure reference checker for academic writing workflows') but 'structured execution, explicit assumptions, and clear output boundaries' are process qualities rather than concrete checking actions, matching the anchor 'Names the domain but actions are minimal or generic'. It does not reach 3 because no concrete actions (e.g. detect orphaned references, check label consistency) are stated.	2 / 5
Completeness	A 'Use ... for ...' trigger clause is present so it is not capped, but the 'what' is only weakly implied by 'figure reference checker' and the 'when' describes process properties rather than concrete trigger phrases, fitting 'Has a clear what but when is missing or only weakly implied'. Not a 4 because neither what nor when is explicit and concrete.	3 / 5
Trigger Term Quality	'figure reference' and 'academic writing' are relevant natural keywords, but common synonyms and variations users would say (manuscripts, figures, citations, figure labels) are missing, fitting 'Some relevant keywords but missing common variations or synonyms'. Not a 4 because coverage is thin rather than just a few terms short.	3 / 5
Distinctiveness Conflict Risk	'Figure reference checker for academic writing' is a clear niche with distinct triggers and only minor overlap risk with closely related citation/manuscript skills, matching 'Mostly distinct; minor overlap risk with closely related skills'. Not a 5 because the trigger phrasing is process-based rather than sharply concrete.	4 / 5
	Total	12 / 20 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
Path: scientific-skills/Academic Writing/figure-reference-checker/SKILL.md
Commit: 63c61d3

Reviewed: 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.