research
Comprehensive research grounded in web data with explicit citations. Use when you need multi-source synthesis—comparisons, current events, market analysis, detailed reports.
89
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 100%
↑ 6.25xAgent success when using this skill
Validation for skill structure
Discovery
82%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 is a solid description that clearly communicates both purpose and trigger conditions. The 'Use when...' clause with specific use cases (comparisons, current events, market analysis) is effective. However, the description could be more specific about concrete actions performed and could better distinguish itself from other research or analysis skills.
Suggestions
Add more concrete actions like 'searches multiple web sources', 'synthesizes findings', 'formats citations' to improve specificity
Include distinguishing details like output formats or unique capabilities (e.g., 'real-time web search', 'academic citation formats') to reduce potential conflicts with other analytical skills
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (research, web data) and mentions some actions (multi-source synthesis, comparisons, reports), but lacks concrete specific actions like 'searches websites', 'extracts data', or 'generates citations in APA format'. | 2 / 3 |
Completeness | Clearly answers both what ('Comprehensive research grounded in web data with explicit citations') and when ('Use when you need multi-source synthesis—comparisons, current events, market analysis, detailed reports'). | 3 / 3 |
Trigger Term Quality | Good coverage of natural terms users would say: 'research', 'comparisons', 'current events', 'market analysis', 'reports', 'citations'. These are terms users naturally use when requesting research tasks. | 3 / 3 |
Distinctiveness Conflict Risk | While 'web data' and 'citations' help distinguish it, terms like 'research', 'reports', and 'analysis' could overlap with other analytical or document-generation skills. Could benefit from more specific file types or output formats. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
87%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-crafted skill with excellent conciseness and actionability. The executable examples and parameter tables make it immediately usable. The main weakness is the lack of error handling guidance or validation steps for when research operations fail or produce unexpected results.
Suggestions
Add a brief troubleshooting section covering common failure modes (timeout, authentication errors, empty results) and how to handle them
Include guidance on validating research output quality or what to do if citations are insufficient
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, avoiding explanations of concepts Claude already knows. Every section serves a purpose with no padding or unnecessary context about what research is or how APIs work. | 3 / 3 |
Actionability | Provides fully executable bash commands with concrete JSON parameters. Examples are copy-paste ready with clear variations for different use cases (basic, pro model, save to file). | 3 / 3 |
Workflow Clarity | The authentication flow has clear steps, but the main research workflow lacks validation checkpoints. No guidance on what to do if research fails, times out, or returns poor results. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections (Authentication, Quick Start, Parameters, Model Selection, Examples). Content is appropriately sized for a single file with no need for external references. | 3 / 3 |
Total | 11 / 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.
- 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.