Is the Vibe Research skill free?

Yes. The skill itself is free from KhazP/vibe-coding-prompt-template. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Vibe Research SkillProof Score?

8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Vibe Research?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Vibe Research with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Vibe Research

Structured idea-validation interview that outputs a research doc with a workflow handoff block

by KhazP · KhazP/vibe-coding-prompt-template

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 20, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · aad8016

Fetched the repo tree (6 sibling vibe-* skills) and picked the vibe-research SKILL.md by slug match; read it fully plus part1-deepresearch.md and README. Frontmatter clean (name+description, allowed-tools), no base64/curl/exfil/secrets. Referenced part1-deepresearch.md exists in repo root but is NOT bundled in the skill folder, so a skill-only copy is missing its question bank (skill degrades by asking user to paste). Trigger phrasings tested — SHOULD fire: "research my idea for a meal-planning app", "help me validate my SaaS idea before I build", "help me start a new project and research the market"; should NOT fire: "research the best React state library for my existing app", "validate this JSON schema against my API" — 5/5 correct. Measured baseline vs skill: skill clearly wins on structure (7 fixed headings, interview discipline, freshness/grounding rules, downstream Handoff Context block), though raw research content quality is WebSearch-bound and equal in both.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Vibe Research does

A prompt-workflow skill that runs a structured idea-validation interview (one question at a time, verification echo) then produces a market-research doc under 7 fixed headings plus a machine-readable Handoff Context block. Triggers when a user says "research my idea", "validate my app", or "help me start a new project".

How to install Vibe Research

Part of the KhazP/vibe-coding-prompt-template repo. Intended install is to use the whole template: copy the repo's `.claude/skills/` into your project AND keep `part1-deepresearch.md` (and part2/3/4) in the project root, since the skill reads part1 as its question-bank source of truth. Copying only `.claude/skills/vibe-research/` leaves that sibling file missing (skill then asks you to paste it). No CLI/MCP/build step; uses standard Claude Code tools (Read, Write, WebSearch, WebFetch, AskUserQuestion).

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Vibe Research

/vibe-research Structured idea-validation interview that outputs a research doc with a workflow handoff block

It also activates on plain-language prompts like these:

Research my app idea before I start building
Validate whether there's demand for this product
Help me start a new project with market research

Frequently asked questions

Is the Vibe Research skill free?: Yes. The skill itself is free from KhazP/vibe-coding-prompt-template. SkillProof publishes the install command and an independent test verdict at no cost.
Does Vibe Research work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 20, 2026. Verdict: Tested · Works. Fetched the repo tree (6 sibling vibe-* skills) and picked the vibe-research SKILL.md by slug match; read it fully plus part1-deepresearch.md and README. Frontmatter clean (name+description, allowed-tools), no base64/curl/exfil/secrets. Referenced part1-deepresearch.md exists in repo root but is NOT bundled in the skill folder, so a skill-only copy is missing its question bank (skill degrades by asking user to paste). Trigger phrasings tested — SHOULD fire: "research my idea for a meal-planning app", "help me validate my SaaS idea before I build", "help me start a new project and research the market"; should NOT fire: "research the best React state library for my existing app", "validate this JSON schema against my API" — 5/5 correct. Measured baseline vs skill: skill clearly wins on structure (7 fixed headings, interview discipline, freshness/grounding rules, downstream Handoff Context block), though raw research content quality is WebSearch-bound and equal in both.
What is the Vibe Research SkillProof Score?: 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Vibe Research?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Vibe Research with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.