Vc Feasibility Test logo

Vc Feasibility Test

CommunityPopular
withkynam
vc-feasibility-test

Use when a SPEC, INNOVATE, or VALIDATE (Layer 2) approach hinges on an unverified runtime/library/external mechanism: run a probe from the 8-family taxonomy and produce a VIABLE/NOT-VIABLE/INCONCLUSIVE VERDICT artifact.

Overview

Publisherwithkynam
Repositoryvibecode-pro-max-kit
Skill namevc-feasibility-test
Stars
1.1K
Forks
234
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by withkynam on GitHub. Read the source before you install it.

Installation

Install the Vc Feasibility Test AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/withkynam/vibecode-pro-max-kit/tree/main/.claude/skills/vc-feasibility-test
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/withkynam/vibecode-pro-max-kit.git /tmp/vibecode-pro-max-kit
mkdir -p .claude/skills
cp -r /tmp/vibecode-pro-max-kit/.claude/skills/vc-feasibility-test .claude/skills/vc-feasibility-test
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vc Feasibility Test in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Vc Feasibility Test on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Vc Feasibility Test is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

vc-feasibility-test

Output style: Follow process/development-protocols/communication-standards.md — answer-first, plain language, no unexplained jargon, TL;DR on long responses.

One-shot empirical probe skill. Used when SPEC or INNOVATE encounters an approach hinging on an unverified external/runtime/library mechanism — the question is "does this mechanism actually work the way the design assumes?", asked before the decision locks.

Boundary vs vc-test-coverage-plan

These two skills are complementary and must not be confused:

  • vc-feasibility-test (this skill) = PRE-decision. "Does the mechanism work at all?" Run before SPEC/INNOVATE locks an approach, when the answer is unknown. Output: a one-shot VERDICT artifact.
  • vc-test-coverage-plan = POST-plan. "How do I cover this blast radius across the 4 test tiers?" Run after a plan exists, when the design is already chosen. Output: a per-area tier table.

If the approach is already decided and you are assigning test tiers → use vc-test-coverage-plan. If you cannot decide because a mechanism is unverified → use this skill first.

When To Invoke

  • When vc-spec-agent, vc-innovate-agent, or a vc-validate-agent Layer 2 dimension agent emits VC-FEASIBILITY-PROBE-NEEDED
  • When a mechanism cannot be verified from source code alone
  • One-shot: not an iterative loop (use vc-autoresearch for iteration)

Skill Executor

Always executed by vc-debugger (via the VC-FEASIBILITY-PROBE-NEEDED signal routing in orchestration.md). SPEC, INNOVATE, and VALIDATE Layer 2 agents do not run probes themselves.

Probe-Method Taxonomy (pick one family)

Every probe belongs to one of these 8 families. Name the chosen family in the VERDICT. Each family has a default cost/safety class (see next section) — the probe inherits it.

#FamilyWhat it probesTypical methodDefault cost class
1Local process / Node scriptpure library/runtime behavior in isolationrun a .mjs/Bun script, regex/parse check, call the lib fn directlycheap-local
2Unit/integration test harnessbehavior under the project's own test runnerpnpm --filter … test (Vitest) or bun test on a scratch casecheap-local
3tRPC / Prisma / DB queryroute shape, query behavior, index/constraint semanticshit a tRPC route or run a Prisma/raw-SQL query against a test DBneeds-container (only if it needs the live app DB) / else cheap-local
4External API shape capturereal response shape/behavior of a 3rd-party APIone live request to OpenRouter / Stripe / Composio / Clerk / Bright Dataneeds-live-provider
5Container exec / internal-port curlin-container service behavior, proxy injection, file-server, supervisorddocker exec … curl http://localhost:{port} on a disposable containerneeds-container
6Browser / CDP captureanti-detect quirks, CDP events, SPA nav, popup behaviorPlaywright/CDP client, page.on(...), snapshotneeds-browser
7WS / SSE handshake & timinggateway WS framing, SSE delivery/reconnect, JSONL shaperaw ws/EventSource client + frame/timing captureneeds-container (if against in-container service) / else cheap-local
8Cloudflare worker runtimeKV staleness, step-replay/idempotency, edge JWT verifywrangler dev + curl, deploy a throwaway workerneeds-cf

If none of the 8 fit, the question is probably not a feasibility probe — reconsider whether vc-research-agent (unknown context) or vc-test-coverage-plan (known design) is the right tool instead.

Probe Cost / Safety Class (MANDATORY GATE)

Every VERDICT declares one cost class. The class governs whether the probe may run unattended or needs explicit opt-in. A probe that cannot be run within its safety gate produces an INCONCLUSIVE verdict — it is never silently skipped or faked.

Cost classSafety gateIf gate not met
cheap-localnone — run freely (local script, test harness, parse check)n/a
needs-containeruse a disposable container only. NEVER docker exec the shared dev container (app-*) or shared Postgres. Disposable live-E2E containers need the disposable-cleanup env gate enabled.verdict INCONCLUSIVE, note "no disposable container available"
needs-live-providerrequires explicit double opt-in from the user before any billed/live 3rd-party call (OpenRouter, Stripe, Composio, Bright Data, Clerk). Default local mode is BYOK Mistral.verdict INCONCLUSIVE, note "live-provider opt-in not granted"
needs-browsera browser/CDP session must be available; never drive a shared user sessionverdict INCONCLUSIVE, note "no browser session available"
needs-cfa wrangler dev/throwaway-worker sandbox; never touch a deployed production workerverdict INCONCLUSIVE, note "no CF sandbox available"

The emitted VC-FEASIBILITY-PROBE-NEEDED signal SHOULD carry the anticipated cost class so the orchestrator can resolve the opt-in gate before dispatching vc-debugger (see orchestration.md §VC-FEASIBILITY-PROBE-NEEDED Signal Routing).

Probe Execution Steps

  1. Read the hypothesis from the VC-FEASIBILITY-PROBE-NEEDED signal
  2. Pick the probe family (1–8) and its cost class
  3. Confirm the safety gate for that cost class is met. If not → write an INCONCLUSIVE verdict with the gate-not-met reason and stop. Do NOT escalate to a higher-cost probe or run against a shared resource.
  4. Design the minimal probe within that family
  5. Run the probe empirically — capture actual output, not expected output
  6. Analyze the evidence: does it confirm or refute the hypothesis?
  7. Assign a verdict: VIABLE | NOT-VIABLE | INCONCLUSIVE
  8. Write the VERDICT artifact to the active task folder

VERDICT Artifact Format

Filename: {slug}_FEASIBILITY_{dd-mm-yy}.md Location: same active task folder as the SPEC/plan that triggered the probe

Required frontmatter fields (MUST be present — validated by validate-feasibility-verdict.mjs):

yaml
---
slug: [task-slug]
date: YYYY-MM-DD
verdict: VIABLE | NOT-VIABLE | INCONCLUSIVE
originating-phase: spec | innovate | pvl
---

The originating-phase: field is REQUIRED. Valid values:

  • spec — probe triggered by vc-spec-agent ([SP3])
  • innovate — probe triggered by vc-innovate-agent ([I2.5])
  • pvl — probe triggered by vc-validate-agent Layer 2 ([V2-PROBE])

Required sections (MUST be present — validated by validate-feasibility-verdict.mjs):

Hypothesis

One-sentence statement of what is being tested.

Mechanism Under Test

The specific external, runtime, or library behavior being probed.

Probe Family

One of the 8 families above (e.g. 5 — Container exec / internal-port curl).

Probe Cost Class

One of: cheap-local | needs-container | needs-live-provider | needs-browser | needs-cf. State whether the safety gate was met.

Probe Method

The exact command(s) or steps run to test the hypothesis.

Evidence Captured

The raw output from the probe (trimmed to relevant lines). For an INCONCLUSIVE gate-not-met verdict, state explicitly that the probe was not run and why.

Verdict

One of: VIABLE | NOT-VIABLE | INCONCLUSIVE

Resulting Design Constraint

The "action consequence" of the probe, split into three explicit parts:

  • What this licenses: what the approach is now allowed to depend on.
  • What this forbids: what the approach must NOT depend on.
  • What remains uncertain (known-gap): what the probe did not settle and must be treated as an open risk (for INCONCLUSIVE, this is the main content).

Completion Signal

After writing the VERDICT artifact, emit:

VC-FEASIBILITY-VERDICT-READY: [verdict keyword] — [full path to VERDICT file]

Example:

VC-FEASIBILITY-VERDICT-READY: NOT-VIABLE — process/features/model-selector/active/model-selector_10-06-26/model-selector_FEASIBILITY_10-06-26.md

Re-spawn Handoff

The orchestrator reads the VERDICT artifact and extracts a Prior Feasibility: summary. Format passed to the re-spawned agent:

Prior Feasibility: [hypothesis] — verdict: [VIABLE|NOT-VIABLE|INCONCLUSIVE] — licenses: [one line] — forbids: [one line] — uncertain: [one line]

Example:

Prior Feasibility: Does the gateway forward params.provider.sort? — verdict: NOT-VIABLE — licenses: nothing new — forbids: any approach depending on params.provider.sort being forwarded (the layer strips it) — uncertain: whether a different forwarding field survives

The re-spawned SPEC, INNOVATE, or VALIDATE agent reads this block and uses the verdict to lock or reject the approach. When originating-phase: pvl, the re-spawned vc-validate-agent resumes from V1 and records resolved probes in a ## Feasibility Probes Resolved subsection of the validate-contract (omitted when no probe ran).

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Vc Feasibility Test AI skill do?

Use when a SPEC, INNOVATE, or VALIDATE (Layer 2) approach hinges on an unverified runtime/library/external mechanism: run a probe from the 8-family taxonomy and produce a VIABLE/NOT-VIABLE/INCONCLUSIVE VERDICT artifact.

Why use Vc Feasibility Test on TypingMind?

Because you install it once and use it with any model. Vc Feasibility Test is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Vc Feasibility Test in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/withkynam/vibecode-pro-max-kit/tree/main/.claude/skills/vc-feasibility-test. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Vc Feasibility Test?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Vc Feasibility Test?

As many as you like. As long as a model supports skills, you can use Vc Feasibility Test with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Vc Feasibility Test AI skill free?

Yes. It is published on GitHub by withkynam under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇