research-assistant

Conduct thorough research on topics by searching the vault and synthesizing findings. Use when the user asks to research a topic, dig into something across notes, or wants a synthesis of what the vault knows about a subject.

Quality

87%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

85%

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

The body is concise and cleanly organized into a sequenced process, a reusable output template, and brief tips. The main weakness is actionability: the process steps stay abstract rather than giving concrete, executable search or synthesis guidance.

Suggestions

Add concrete guidance for the search step, e.g. specific vault search syntax or tool calls to run, instead of "Search the entire vault for the topic."

Specify how to identify and weight relevant notes (e.g. tag/keyword filters, recency, or link density) so the Deep Dive step is executable rather than descriptive.

Give a brief worked example of the synthesis step showing how to turn extracted quotes into the Key Themes section of the output template.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout: terse process bullets, a compact output template, and four one-line tips, with no padding or explanation of concepts Claude already knows, so every token earns its place.	3 / 3
Actionability	The output template is concrete and copy-paste ready, but the process steps ("Search the entire vault," "Read all relevant notes thoroughly," "Extract key insights") describe rather than instruct, with no concrete search syntax, tool calls, or specific commands, matching the some-guidance-but-incomplete anchor.	2 / 3
Workflow Clarity	A clearly numbered three-step sequence (Initial Search -> Deep Dive -> Synthesis) is presented; since the task is read-only synthesis, the destructive/batch validation cap does not apply, and the simple-skill guidance permits a 3 for a clear, well-sequenced process.	3 / 3
Progressive Disclosure	The skill is self-contained in SKILL.md with no bundle files and is organized into clear sections (Process, Output Structure, Tips); the under-50-lines-no-references guidance applies closely enough to warrant full marks for well-organized structure.	3 / 3
	Total	11 / 12 Passed

Description

90%

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 is well-structured: it states the skill's purpose, uses third-person voice, and includes explicit natural-language triggers covering what and when. Its only gap is that the capability list is somewhat high-level rather than enumerating several concrete actions.

Dimension	Reasoning	Score
Specificity	Names two concrete actions ("searching the vault" and "synthesizing findings") but does not enumerate multiple specific actions like the score-3 anchor; it stays at the domain-plus-some-actions level rather than a comprehensive list.	2 / 3
Completeness	It answers both what ("Conduct thorough research... by searching the vault and synthesizing findings") and when ("Use when the user asks to research a topic, dig into something across notes, or wants a synthesis..."), matching the explicit-trigger anchor.	3 / 3
Trigger Term Quality	Phrases like "research a topic," "dig into something across notes," and "synthesis of what the vault knows" are natural terms a user would actually say, giving good coverage of likely triggers.	3 / 3
Distinctiveness Conflict Risk	The vault/note-research framing ("across notes," "what the vault knows") carves a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	11 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: heyitsnoah/claudesidian
Path: .agents/skills/research-assistant/SKILL.md
Commit: 6c56f35

Reviewed: about 16 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.