agent-researcher
Agent skill for researcher - invoke with $agent-researcher
40
7%
Does it follow best practices?
Impact
98%
1.88xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.agents/skills/agent-researcher/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is critically deficient across all dimensions. It provides no concrete actions, no trigger terms, no 'when to use' guidance, and is so generic that it would be indistinguishable from any research-related skill. It essentially tells Claude nothing useful for skill selection.
Suggestions
Describe specific concrete actions the skill performs, e.g., 'Searches academic databases, summarizes papers, compiles literature reviews, and extracts citations.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to research a topic, find sources, summarize articles, or compile references.'
Remove the invocation command from the description (it's not useful for skill selection) and replace with domain-specific keywords that distinguish this from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description provides no concrete actions whatsoever. 'Agent skill for researcher' is entirely vague and abstract, giving no indication of what the skill actually does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no description of capabilities and no explicit trigger guidance or 'Use when...' clause. | 1 / 3 |
Trigger Term Quality | The only potentially relevant keyword is 'researcher', which is overly generic. The invocation command '$agent-researcher' is technical jargon, not a natural user term. No natural keywords a user would say are present. | 1 / 3 |
Distinctiveness Conflict Risk | 'Researcher' is extremely generic and could conflict with any skill involving research, analysis, information gathering, 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 a verbose, loosely structured document that reads more like a general role description than an actionable skill. It explains many concepts Claude already understands (grep usage, what dependency analysis means, generic best practices like 'be thorough') while failing to provide a clear, sequenced workflow with validation steps. The MCP tool examples provide some value but are buried in excessive surrounding content.
Suggestions
Cut the content by 60-70%: remove 'Core Responsibilities' (role description Claude doesn't need), generic 'Best Practices', and 'Collaboration Guidelines' sections. Focus only on the specific MCP tool calls and the expected output format.
Define a clear sequential workflow: e.g., 1) Gather context via search → 2) Store initial findings in memory → 3) Validate findings against code → 4) Store final structured output → with explicit checkpoints at each stage.
Split the research output YAML template and MCP tool reference into separate bundle files, keeping SKILL.md as a concise overview with links.
Make MCP tool examples fully concrete with realistic parameters rather than placeholder values, and specify exactly when each tool should be invoked in the workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose with extensive content Claude already knows (how to grep, what pattern analysis is, what dependencies are). The research methodology, search strategies, and best practices sections are largely generic advice that doesn't add actionable value. The YAML output format template and multiple bash/JS examples bloat the content significantly. | 1 / 3 |
Actionability | Contains some concrete code examples (grep commands, MCP tool calls), but much of the content is descriptive rather than instructive ('Track import statements', 'Identify external package dependencies'). The MCP tool integration examples are somewhat concrete but use pseudocode-like JavaScript syntax rather than clearly executable commands. Many sections describe what to do conceptually without specifying how. | 2 / 3 |
Workflow Clarity | While numbered sections exist (Information Gathering, Pattern Analysis, etc.), there is no clear sequential workflow with validation checkpoints. The 'Research Methodology' is a list of categories rather than a step-by-step process. No feedback loops or error recovery are defined. For a research agent that stores findings in memory, there's no validation that stored data is correct or complete. | 1 / 3 |
Progressive Disclosure | Monolithic wall of text with no references to external files. All content is inline including detailed YAML templates, multiple code blocks, and extensive guidelines. No bundle files exist to support separation, but the content itself (~150+ lines) would benefit greatly from splitting into separate reference files for output formats, MCP integration, and search strategies. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
100%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/ruflo
- Commit
844f68d
- Reviewed
Table of Contents
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.