academic-verify

Verify a research claim or academic citation by tracing it through publication → methodology → raw data → independent replication. Routes through perplexity-research for the actual web lookup, then formats results as a citation-checked brain page. Use when a book/article/conversation cites a study and you want to confirm the claim is real, replicated, and accurately characterized.

Quality

72%

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/academic-verify/SKILL.md

Quality

Content

61%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 is well-structured and actionable with a concrete 5-step workflow, output template, and reference table. Its main weaknesses are some redundancy across verdict definitions and the absence of an explicit validation checkpoint for a skill that mutates the brain, which caps workflow clarity.

Suggestions

Add an explicit validation/verification checkpoint in the workflow (e.g. 'Confirm the DOI/URL resolves and the brain page renders before writing the verdict') so the mutating write step has a feedback loop.

De-duplicate the verdict categories: define the five verdicts once (in the Standards section or template) and reference them from Step 4 instead of restating them in three places.

Consider moving the database URL-pattern table into a references/ file referenced from the body, tightening the inline content while keeping the lookup resources one level deep.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and free of basic-concept padding, but the verdict categories are restated three times (Step 4, the brain-page template, and the 'Standards' section), and the anti-patterns partially restate earlier guidance, so it could be tightened.	3 / 5
Actionability	Provides concrete, specific guidance — a literal gbrain query, a bulleted perplexity prompt, a full brain-page template with frontmatter, and a database table with URL patterns — with only minor gaps (the perplexity/gbrain invocations are workflow-framed rather than literal copy-paste commands).	4 / 5
Workflow Clarity	A clear 5-step sequence (scope → brain-first → invoke → format → cross-link) is present, but for a mutating skill that writes pages there is no explicit validation checkpoint or feedback loop (e.g. verify the DOI resolves or the brain page renders before committing), which caps workflow clarity at 3 per the rubric.	3 / 5
Progressive Disclosure	Well-organized with clear section headers and no nested references; the database table and output template are reasonably inline, though a 200-line single-file skill with no references has minor organization gaps versus an ideal split.	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: it states the concrete verification workflow, names the routing dependency, and gives an explicit 'Use when...' trigger with natural phrasing. It is held back only by minor gaps in action coverage and a few missing trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('tracing it through publication → methodology → raw data → independent replication', 'Routes through perplexity-research', 'formats results as a citation-checked brain page'); minor gaps keep it just below comprehensive anchor 5.	4 / 5
Completeness	Explicitly answers both what (trace claim → publication → data → replication, format brain page) and when ('Use when a book/article/conversation cites a study and you want to confirm the claim is real, replicated, and accurately characterized') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Strong natural phrasing ('book/article/conversation cites a study', 'confirm the claim is real, replicated, and accurately characterized') a user would actually say; a few synonyms (e.g. 'validate this paper') are missing, so not anchor 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (academic citation verification routed through perplexity-research) with explicit differentiation from perplexity-research and citation-fixer; minor overlap risk with those related skills keeps it just below anchor 5.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
relative_links	Relative link issues: 2 missing, 3 suspicious	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/academic-verify/SKILL.md
Commit: 8c70f62

Reviewed: 4 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.