capx-ai/casa/casa-validate

Claude Code and agent skill by capx-ai/casa

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

The validation gate. Turns a business idea into a validation kit and a GO or KILL verdict by running the validation playbooks. Use when validating an idea before committing to build a company.

Install

npx vskill@latest install capx-ai/casa/casa-validate

SKILL.md

casa-validate

The wedge. Prove there is real demand before anyone builds anything. This is the validation gate every new idea passes through, and its verdict personalizes everything after it.

If company-brain/profile.json does not exist, tell the founder to run /casa-start first and stop. (casa-start invokes this gate itself for an idea-stage company.)

What it runs (the validation playbooks)

In dependency order (see each playbook's frontmatter under playbooks/level-0/):

  1. opportunity-scan (001): mine communities, reviews, search, trends for evidence

of demand. Parallel-safe with 003, 004.

  1. problem-validation-interviews (002): Mom-Test discovery; problem evidence memo.
  2. competitive-teardown (003): map competitors, pricing, gaps.
  3. market-sizing-tam-sam-som (004): top-down and bottom-up; kill if the reachable

market is below threshold.

  1. jobs-to-be-done-extraction (005): functional, emotional, social jobs.
  2. red-team-thesis (006): steelman why this fails; set explicit kill criteria.
  3. why-now-memo (007): the timing thesis.
  4. mvp-scoping (018): the thin slice to build, with explicit non-goals.

On a GO verdict, beachhead-selection (008, the first play of the next level) picks the narrowest wedge with the most compounding.

Output

  • A validation kit written to company-brain/ (evidence, sizing, beachhead, MVP

scope).

  • A GO or KILL verdict against the red-team kill criteria.
  • On GO, a confirmed business profile (type, traits, ICP, monetization) for the

router.

Rules

  • Evidence required. An opportunity is not valid until at least three independent

signals from at least two channels support it. State confidence on every claim.

  • No fabrication. If a required input (an API, a real interview) is missing, say

so and ask the founder rather than inventing data.

  • The landing-page demand test and live waitlist are part of this wedge but

involve a real deploy and possibly paid actions; route those through explicit founder approval. For now, produce the kit and the verdict.

  • No em-dashes, no emojis.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
74
Repository forks
3
7-day trend score
22

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/capx-ai/casa/casa-validate/badge)](https://verified-skill.com/skills/capx-ai/casa/casa-validate)

Something wrong with this skill or its page? Tell us.