agent-researcher

Agent skill for researcher - invoke with $agent-researcher

1.88x

Quality

Does it follow best practices?

Impact

98%

1.88x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agents/skills/agent-researcher/SKILL.md

Quality

Discovery

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description is critically deficient across all dimensions. It provides no information about what the skill does, when it should be used, or what distinguishes it from other skills. It reads more like a label than a functional description that Claude could use for skill selection.

Suggestions

Describe specific concrete actions the researcher skill performs (e.g., 'Searches academic databases, summarizes papers, compiles literature reviews, extracts citations').

Add an explicit 'Use when...' clause with natural trigger terms (e.g., 'Use when the user asks to research a topic, find sources, review literature, or gather information from multiple sources').

Remove the invocation syntax ('invoke with $agent-researcher') from the description and replace it with capability and trigger information that helps Claude select the right skill.

Dimension	Reasoning	Score
Specificity	The description provides no concrete actions whatsoever. 'Agent skill for researcher' is entirely vague with no indication of what the skill actually does.	1 / 3
Completeness	Neither 'what does this do' nor 'when should Claude use it' is answered. There is no explanation of capabilities and no 'Use when...' clause or equivalent trigger guidance.	1 / 3
Trigger Term Quality	The only potentially relevant keyword is 'researcher', which is overly generic. The description includes '$agent-researcher' which is a command invocation, not a natural user trigger term.	1 / 3
Distinctiveness Conflict Risk	'Researcher' is extremely broad and could conflict with any skill involving research, information gathering, analysis, or investigation. There are no distinct triggers to differentiate it.	1 / 3
	Total	4 / 12 Passed

Implementation

14%

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

This skill is heavily padded with generic advice and concepts Claude already understands (how to search code, what dependencies are, 'think critically'). While the MCP tool integration examples provide some concrete value, the majority of the content describes obvious research practices without adding novel, project-specific guidance. The lack of a clear workflow with validation steps and the monolithic structure significantly reduce its effectiveness.

Suggestions

Cut the content by 60-70%: remove generic research advice (Be Thorough, Think Critically, etc.), obvious methodology steps, and focus only on the specific MCP tool syntax and memory coordination patterns that are unique to this system.

Add a clear sequential workflow with decision points: e.g., 1. Check memory for prior research → 2. If found, build on it → 3. Gather via specific tools → 4. Validate findings against code → 5. Store structured results in memory.

Extract the YAML output format template and MCP tool reference into separate files (e.g., RESEARCH_OUTPUT_FORMAT.md, MCP_TOOLS.md) and reference them from a concise overview.

Replace the abstract 'Search Strategies' section with 2-3 concrete, copy-paste-ready examples tied to specific common research tasks in this project's context.

Dimension	Reasoning	Score
Conciseness	Extremely verbose with extensive content Claude already knows - how to grep, how to read files, what 'pattern recognition' means, generic best practices like 'Be Thorough' and 'Think Critically'. The research methodology section describes basic investigation steps any competent agent would follow. The YAML output format template and search strategies are generic padding.	1 / 3
Actionability	Contains some concrete examples like grep commands and MCP tool invocations with JSON payloads, but much of the content is abstract guidance ('Track import statements', 'Identify external package dependencies', 'Review commit messages for context'). The MCP tool examples show specific syntax which is useful, but the bash examples are illustrative rather than executable in context.	2 / 3
Workflow Clarity	The numbered sections (Information Gathering, Pattern Analysis, etc.) describe categories of activity rather than a clear sequential workflow. There are no validation checkpoints, no feedback loops for when research hits dead ends, and no clear decision points for when to stop researching and report findings. For a multi-step research process, this lacks meaningful sequencing.	1 / 3
Progressive Disclosure	This is a monolithic wall of text with no references to external files. All content is inline including lengthy YAML templates, multiple code blocks, and detailed MCP examples. The content would benefit greatly from splitting the output format template, MCP integration details, and search strategies into separate reference files.	1 / 3
	Total	5 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: f547cec

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.