startup-design
Design, validate, and plan a startup from scratch. Covers market research, competitive analysis, business model, brand identity, product definition, financial projections, and validation experiments. Trigger when the user has a startup idea to explore, wants to validate a business concept, needs a business plan or lean canvas, asks for market sizing or competitive landscape, wants brand positioning or go-to-market strategy, or says anything like "I have an idea for..." or "is this idea worth pursuing". Also handles resuming from a previous checkpoint.
93
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%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 well-crafted skill description that excels across all dimensions. It provides comprehensive coverage of capabilities, includes natural trigger terms users would actually say, explicitly states when to use it, and carves out a distinct niche for startup planning and validation. The description uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Design, validate, and plan a startup from scratch. Covers market research, competitive analysis, business model, brand identity, product definition, financial projections, and validation experiments.' | 3 / 3 |
Completeness | Clearly answers both what (design, validate, plan startup with specific domains) AND when with explicit 'Trigger when...' clause listing multiple specific scenarios and user phrases. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'startup idea', 'validate a business concept', 'business plan', 'lean canvas', 'market sizing', 'competitive landscape', 'brand positioning', 'go-to-market strategy', and conversational triggers like 'I have an idea for...' and 'is this idea worth pursuing'. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on startup planning and validation with distinct triggers; unlikely to conflict with general business or document skills due to specific startup-focused terminology and use cases. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
85%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-designed, comprehensive skill for startup validation with excellent workflow clarity and progressive disclosure. The multi-phase structure with explicit checkpoints, resume capability, and verification steps demonstrates sophisticated process design. The main weakness is moderate verbosity—some explanatory content could be trimmed to improve token efficiency without losing clarity.
Suggestions
Trim explanatory preambles in phase descriptions (e.g., 'This is the most resource-intensive phase' adds no actionable value) to improve conciseness
Remove framework definitions from the main skill body since they're already in references/frameworks.md—just reference the file
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is comprehensive but includes some unnecessary explanation (e.g., explaining what a Lean Canvas is, describing what each phase does conceptually before giving instructions). Some sections could be tightened, though the content is generally relevant and not padded with basic concepts Claude would know. | 2 / 3 |
Actionability | Highly actionable with specific questions to ask, exact file paths for outputs, concrete examples of what to include in each deliverable, step-by-step processes for each phase, and clear templates (e.g., the scorecard table, interview questions structure, experiment design format). | 3 / 3 |
Workflow Clarity | Excellent workflow clarity with explicit phase sequencing (Phase 0 → 8), clear checkpoints (Research Gate go/no-go, verification pass), resume capability via PROGRESS.md, and explicit validation steps before proceeding (e.g., 'If Critical issues found: Pause and present issues to the user'). | 3 / 3 |
Progressive Disclosure | Well-structured with clear one-level-deep references to supporting files (research-wave-*.md, frameworks.md, etc.), a reference table showing when to read each file, and appropriate separation of detailed agent templates into reference files while keeping the main skill focused on orchestration. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
skill_md_line_count | SKILL.md is long (563 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- ferdinandobons/startup-skill
- Commit
1dbf392
- 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.