zotero-obsidian-bridge

Use this skill when Zotero is the literature source of truth and the project KB should receive source notes under Sources/Papers plus project-linked synthesis in Knowledge and Writing.

Quality

63%

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/zotero-obsidian-bridge/SKILL.md

Quality

Content

53%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 a lean, well-structured overview with a useful Evidence Record template and a meaningful claim-quality gate, but it functions as an island: the bundle's detailed workflow, note schemas, fallback runbook, and verification script are never surfaced, so both actionability and navigation suffer. The batch-ingestion workflow also lacks any in-body validation step.

Suggestions

Add a well-signaled references section linking the bundle files, e.g. "**Full workflow**: See references/WORKFLOW.md", "**Paper note schema**: See references/PAPER-NOTE-SCHEMA.md", "**MCP fallback runbook**: See references/LOCAL-ZOTERO-FALLBACK.md", so the detailed material is discoverable.

Surface the verification step in the body, e.g. "After batch ingestion, run scripts/verify_paper_notes.py ... before closing", to give the batch workflow a validation checkpoint.

Delete the redundant opening line that restates the frontmatter description, and replace it with the concrete ingestion sequence (read from Zotero -> canonical note -> synthesis -> canvas -> verify).

Dimension	Reasoning	Score
Conciseness	The body is lean with no explanation of concepts Claude already knows, and the Evidence Record template is domain-specific and load-bearing. It misses anchor 5 because the opening line "Use this skill when papers live in Zotero and the project KB should receive project-local notes" restates the frontmatter description almost verbatim, and the contract pointer duplicates guidance that lives in the bundle files.	4 / 5
Actionability	Exact destinations (Sources/Papers/, Knowledge/, Writing/, Maps/literature.canvas), a fill-in Evidence Record template, and explicit gate conditions give some concrete guidance, but the how is missing: no Zotero read steps, no note-naming convention, and no verification command. Key operational details exist only in the bundle files the body never links, so it fits anchor 3 (incomplete, missing key details) rather than anchor 4.	3 / 5
Workflow Clarity	The "Default flow" diagram gives a coarse sequence and the Claim Promotion Gate is one content-level checkpoint, but ingestion is a batch operation and the body has no file-level validation step — the verify script and the section-8 verification workflow exist only in the unreferenced WORKFLOW.md. Per the rubric cap, a batch workflow without validation cannot score above 3.	3 / 5
Progressive Disclosure	Scored against the actual bundle: none of the five bundle files (WORKFLOW.md, PAPER-NOTE-SCHEMA.md, COLLECTION-INVENTORY-SCHEMA.md, LOCAL-ZOTERO-FALLBACK.md, scripts/verify_paper_notes.py) are referenced anywhere in the body, making them undiscoverable from SKILL.md. The only cited path is the cross-skill ../research-ideation/references/research-contract.md, which does not resolve inside this bundle — matching anchor 2 (references buried) rather than 3, since the bundle references are absent, not merely unclear.	2 / 5
	Total	12 / 20 Passed

Description

73%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 distinctive, well-triggered description with a clear explicit when-clause, anchored on the strong natural term "Zotero". Its main weakness is that capabilities are stated as passive deliverables rather than concrete actions, and key natural terms like "Obsidian" and "papers" are absent.

Suggestions

State capabilities as active third-person actions, e.g. "Imports papers from Zotero into canonical notes under Sources/Papers, synthesizes literature into Knowledge notes, and maintains Maps/literature.canvas."

Add the missing natural trigger terms — "Obsidian", "papers", "literature notes", "PDF" — so users phrasing the request in terms of the destination KB also match.

Split the description into a what statement plus the Use-when clause so the capability list is explicit rather than folded into the conditional.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete deliverables ("source notes under Sources/Papers" and "project-linked synthesis in Knowledge and Writing") but phrases them passively ("should receive") rather than as concrete actions, and misses other outputs like the literature canvas and registry updates. It matches anchor 3 (1-2 concrete actions, not comprehensive) rather than 4, which requires a list of several specific actions.	3 / 5
Completeness	An explicit when-clause is present ("Use this skill when Zotero is the literature source of truth..."), and a what is embedded as the deliverables in that clause, so it clears the cap-3 rule. It is not anchor 5 because the what is never stated as its own clear action statement — it is folded into the conditional as what the KB "should receive".	4 / 5
Trigger Term Quality	"Zotero", "literature source of truth", "source notes", "synthesis", "Knowledge", and "Writing" give good natural keyword coverage anchored on the decisive term "Zotero". It falls short of anchor 5 because obvious synonyms are missing — notably "Obsidian" (despite being in the skill name), plus "papers", "notes", and "import".	4 / 5
Distinctiveness Conflict Risk	"Zotero is the literature source of truth" carves a clear niche with a highly distinctive trigger term that no generic or sibling skill would naturally fire on, matching anchor 5. Even the related research-ideation skill targets a different phase (ideation vs. ingestion), so conflict risk is minimal.	5 / 5
	Total	16 / 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: Galaxy-Dawn/claude-scholar
Path: skills/zotero-obsidian-bridge/SKILL.md
Commit: 9037873

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.