company-analysis
Analyze companies and generate comprehensive research reports. Use when user asks to research, analyze, profile, or investigate a company.
67
54%
Does it follow best practices?
Impact
84%
1.21xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./lesson-04-claude-code-config/demo/.claude/skills/company-analysis/SKILL.mdQuality
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.
The description is functional with a clear 'Use when' clause and good trigger terms, making it easy for Claude to know when to select this skill. Its main weakness is the lack of specificity in what concrete actions the skill performs—'comprehensive research reports' is somewhat vague and could benefit from listing specific deliverables or analysis types. The distinctiveness could also be improved by clarifying what differentiates this from general research or financial analysis skills.
Suggestions
Add specific concrete actions to improve specificity, e.g., 'Analyze companies by examining financials, competitive landscape, market position, leadership, and recent news to generate comprehensive research reports.'
Add more trigger term variations like 'due diligence', 'company overview', 'business analysis', or 'competitor analysis' to improve coverage and distinctiveness.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (company analysis) and a general action (generate comprehensive research reports), but doesn't list specific concrete actions like financial analysis, competitor comparison, SWOT analysis, or market positioning. | 2 / 3 |
Completeness | Clearly answers both 'what' (analyze companies and generate comprehensive research reports) and 'when' (explicit 'Use when' clause with trigger terms: research, analyze, profile, or investigate a company). | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'research', 'analyze', 'profile', 'investigate', and 'company'. These cover the most common ways users would phrase such requests. | 3 / 3 |
Distinctiveness Conflict Risk | Reasonably specific to company research, but 'analyze' and 'research' are broad terms that could overlap with skills for market research, financial analysis, or general research tasks. The focus on 'company' helps but doesn't fully eliminate conflict risk. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is well-intentioned and covers company research comprehensively, but it is far too verbose for a skill file—it reads more like a tutorial for a human intern than instructions for Claude. The report template is the strongest element, providing a concrete output format. The content would benefit enormously from being split into referenced files and stripped of explanations Claude doesn't need (basic research methodology, obvious quality criteria, trigger phrase examples).
Suggestions
Cut the content by 60-70%: remove 'When to Use', 'Common Pitfalls', 'Success Criteria', time estimates, and explanations of basic concepts like what B2B means or why to cite sources—Claude already knows these things.
Extract the report template, search patterns, and report variations into separate referenced files (e.g., REPORT_TEMPLATE.md, SEARCH_PATTERNS.md, VARIATIONS.md) to improve progressive disclosure.
Add explicit validation checkpoints within the workflow, such as 'Verify at least 3 independent sources before including a funding figure' or 'If a section has no verifiable data after 3 searches, mark as Not Available and move on.'
Make the subagent delegation section concrete—either provide actual tool invocation syntax or remove the section if those tools don't exist in the environment.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~250+ lines. Explains obvious research methodology (e.g., 'search for company website'), includes time estimates Claude doesn't need, explains what B2B/B2C means implicitly, and has extensive sections like 'Common Pitfalls' and 'Success Criteria' that state things Claude already knows (don't speculate, cite sources, use neutral tone). The 'When to Use' trigger phrases are also unnecessary padding. | 1 / 3 |
Actionability | The report template is concrete and copy-paste ready, and the search patterns provide specific queries. However, the bash code blocks for searches aren't actually executable commands—they're just search strings. The subagent delegation references tools ('web-researcher', 'people-finder') without confirming they exist or providing real invocation syntax. The methodology phases are more descriptive than executable. | 2 / 3 |
Workflow Clarity | The three-phase research methodology provides a clear sequence, and the quality checklist at the end serves as a validation step. However, there are no feedback loops—no guidance on what to do if information is contradictory, sources conflict, or key sections can't be filled. The checklist is post-hoc rather than integrated into the workflow as explicit checkpoints. | 2 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files and no references to external documents. The report template, search patterns, example analysis, report variations, and competitive analysis format could all be separate referenced files. Everything is inlined into one massive document, making it hard to navigate and consuming excessive context window. | 1 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- udacity/cd14715-claude-code-classroom
- Commit
6820a25
- 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.