CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

75

Quality

92%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

85%Weight 40%Scale 1-3

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

The body is a well-structured, highly actionable multi-phase skill with excellent workflow sequencing, validation gates, and one-level-deep progressive disclosure. The only weakness is mild verbosity from motivational framing that could be trimmed without losing clarity.

Suggestions

Trim reflective/motivational prose (e.g. 'Research tells you what the market looks like from the outside...', 'The quality of everything downstream depends on how much context you extract now') to reduce tokens without losing guidance.

Shorten the extended framing around the Research Gate and synthesis sections to imperative instructions; the reasoning guidance can be condensed to a few bullets.

Consider moving the long reference-files table to a single concise list or merging it with the inline '> Reference:' callouts to avoid restating when-to-read information twice.

DimensionReasoningScore

Conciseness

Mostly efficient and actionable, but padded with motivational framing Claude doesn't need — e.g. 'Research tells you what the market looks like from the outside. Customer interviews tell you what the problem feels like from the inside', 'The quality of everything downstream depends on how much context you extract now', and extended reflective prose around synthesis and the research gate. It is tighter than anchor 1's concept-explaining verbosity but not the lean every-token-earns-its-place of anchor 3.

2 / 3

Actionability

Provides concrete file paths, per-phase output specs, exact search templates ('"{problem domain} software"', 'site:producthunt.com'), explicit matrix columns, and copy-paste-ready gate criteria (4+ of 5 interviewees, ±30% sensitivity, Stage A/B labels). Matches anchor 3's fully executable, specific guidance.

3 / 3

Workflow Clarity

Clear sequenced 8-phase flow with explicit validation checkpoints and feedback loops: Phase 3.5a verification with critical-vs-warning branching, Research Gate go/no-go, Interview Gate proceed/reassess criteria, PROGRESS.md checkpointing, and resume logic. Matches anchor 3's clear sequence with explicit validation and error-recovery loops.

3 / 3

Progressive Disclosure

Body is an overview pointing to 15 reference files confirmed to exist; references are one level deep, each clearly signaled with '> **Reference:** Read ...' callouts and a navigation table (File / When to Read / ~Lines / Purpose). Heavy agent templates and specs are appropriately split out, matching anchor 3.

3 / 3

Total

11

/

12

Passed

Description

100%Weight 40%Scale 1-3

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 strong: specific capabilities, natural trigger terms, explicit when-guidance, and a distinct niche. It cleanly meets the top anchor on every dimension.

DimensionReasoningScore

Specificity

Lists multiple concrete actions/areas — 'Design, validate, and plan a startup' plus an explicit coverage list ('market research, competitive analysis, business model, brand identity, product definition, financial projections, and validation experiments'). It exceeds anchor 2 (which names only some actions) by enumerating many specific capabilities.

3 / 3

Completeness

Explicitly answers both what ('Design, validate, and plan a startup from scratch' with coverage list) and when via an explicit 'Trigger when the user has...' clause, satisfying anchor 3's requirement for clear what-and-when with explicit triggers.

3 / 3

Trigger Term Quality

Strong natural-language triggers users would say: 'startup idea to explore', 'validate a business concept', 'business plan or lean canvas', 'market sizing or competitive landscape', 'brand positioning or go-to-market strategy', and verbatim phrasings 'I have an idea for...' / 'is this idea worth pursuing'. This matches anchor 3's good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (end-to-end startup design) with distinct, specific triggers unlikely to fire for unrelated skills; matches anchor 3. Uses third-person/imperative voice ('Design, validate, and plan') with no first/second person, so no specificity penalty applies.

3 / 3

Total

12

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
ferdinandobons/startup-skill
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.