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

Quality

Content

50%

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

The content is a well-organized research methodology with concrete search commands and a structured output template, but it is diluted by generic best-practice padding, non-executable MCP pseudo-calls, and lacks validation checkpoints or progressive file separation.

Suggestions

Trim the generic Best Practices and Core Responsibilities sections to remove advice Claude already knows and reduce token overhead.

Rewrite the MCP tool examples as actual executable invocations (or reference a bundled script) rather than pseudo-syntax blocks.

Add explicit validation/checkpoint steps to the Research Methodology (e.g. confirm findings before synthesizing) and move the output-format schema and MCP integration detail into referenced bundle files.

Dimension	Reasoning	Score
Conciseness	The body includes concrete grep/glob commands and a YAML output template, but also generic advice Claude already knows (e.g. "Be Thorough", "Stay Organized", "Think Critically" in Best Practices) that pads the content.	2 / 3
Actionability	It provides real, usable search commands and a structured output template, but the MCP tool examples use pseudo-syntax (e.g. mcp__claude-flow__memory_usage { ... }) that is not directly executable as written.	2 / 3
Workflow Clarity	The Research Methodology is sequenced into numbered stages, but there are no explicit validation checkpoints or feedback loops between stages; the sequence is present but checkpoints are implicit.	2 / 3
Progressive Disclosure	The skill is a single ~190-line file with no bundle files or external references, and content that could be split (MCP integration, output format) is kept inline; sections are organized but the structure is monolithic.	2 / 3
	Total	8 / 12 Passed

Description

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 largely meta-boilerplate identifying the skill and how to invoke it, rather than stating what it concretely does or when to use it. It fails to provide actionable capability detail or natural trigger guidance.

Suggestions

Replace the boilerplate with concrete actions the skill performs, e.g. "Analyzes codebases, maps dependencies, and synthesizes research findings into structured reports."

Add an explicit "Use when..." clause listing natural trigger terms users would say, such as "Use when investigating an unfamiliar codebase, mapping dependencies, or compiling a research summary."

Tighten the niche so it is distinguishable from general research skills, e.g. by tying it to the agent-swarm coordination context.

Dimension	Reasoning	Score
Specificity	The description "Agent skill for researcher - invoke with $agent-researcher" names only the broad domain "researcher" and an invocation hint, with no concrete actions; it does not reach the anchor that names specific actions.	1 / 3
Completeness	Neither a clear "what does this do" (only a vague domain label) nor any "when should Claude use it" trigger is present; both are missing or very weak.	1 / 3
Trigger Term Quality	"researcher" is a generic term and "invoke with $agent-researcher" is a CLI invocation hint rather than natural keywords a user would say when they need the skill.	1 / 3
Distinctiveness Conflict Risk	It specifies a "researcher" niche, which is somewhat specific, but the term is broad enough to overlap with general research and analysis skills.	2 / 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: ruvnet/claude-flow
Commit: 8ae8752

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.