TypingMindTypingMindThe best frontend for AI
Vibe To Spec logo

Vibe To Spec

Community
FAIRY123456789
vibe-to-spec

Convert messy voice input, imperfect speech recognition, half-formed product ideas, and iterative corrections into an implementation-ready software specification for Codex, Claude Code, Copilot, Cursor, or another coding agent. Use when the user speaks faster than they structure requirements, named entities are misrecognized, context or memory can safely resolve recurring terms, and the final output needs scope, flows, data, constraints, acceptance tests, and explicit unknowns rather than a raw transcript.

Overview

PublisherFAIRY123456789
Repositoryhuman-edge-agent-skills
Skill namevibe-to-spec
Stars
108
Forks
0
Bundled files
2
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • 2 bundled files

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

  • Open source

    Published by FAIRY123456789 on GitHub. Read the source before you install it.

Installation

Install the Vibe To Spec 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/FAIRY123456789/human-edge-agent-skills/tree/main/plugins/voice-to-work/skills/vibe-to-spec
  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/FAIRY123456789/human-edge-agent-skills.git /tmp/human-edge-agent-skills
mkdir -p .claude/skills
cp -r /tmp/human-edge-agent-skills/plugins/voice-to-work/skills/vibe-to-spec .claude/skills/vibe-to-spec
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Vibe To Spec 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 Vibe To Spec 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 Vibe To Spec 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.

Vibe to Spec

Purpose

The user's speech can be fuzzy. The implementation contract cannot be. Recover intent without hiding consequential uncertainty or inventing remembered context.

This skill is not voice-dump-to-todo

Use vibe-to-spec when the destination is a product, feature, code change, system, webpage, API, or technical build.

Use voice-dump-to-todo when the destination is the user's personal execution list: tasks, decisions, waiting items, deadlines, and an interactive to-do.

Instructions

  1. Read the entire voice dump before normalizing anything. Later sentences often correct earlier ASR errors or change scope.
  2. Build an active glossary from:
    • exact terms repeated in the current input;
    • named entities in the active conversation or project context;
    • user-provided glossaries or files;
    • host-provided memory only when the product legitimately exposes it and the user would reasonably expect it to be used.
  3. Resolve suspicious ASR terms with references/asr-context-resolution.md.
  4. Maintain a correction ledger for meaningful corrections. High-confidence corrections can be normalized silently in the spec; medium-confidence corrections must remain visible as assumptions; low-confidence terms remain unresolved.
  5. Recover intent in layers:
    • goal and target user;
    • current problem;
    • in-scope behaviors;
    • explicit out-of-scope items;
    • user flow;
    • screens and components;
    • data and entities;
    • integrations and APIs;
    • constraints and non-negotiables;
    • acceptance tests;
    • open questions that genuinely block implementation.
  6. Convert subjective language into testable behavior. “更好看” needs design direction or reference; “更快” needs a measurable threshold or a marked unknown.
  7. Preserve the user's corrections and vetoes. Later explicit corrections override earlier inferred intent.
  8. Do not ask questions that the context can already answer. Ask only when ambiguity changes architecture, data loss risk, cost, security, or acceptance.
  9. Produce the implementation pack using assets/SPEC_TEMPLATE.md.
  10. End with a Ready for coding agent status: YES, YES_WITH_ASSUMPTIONS, or NO_BLOCKED.

Output

Default deliverable:

  • normalized brief;
  • correction ledger for non-trivial ASR fixes;
  • implementation specification content;
  • acceptance criteria;
  • assumptions and open blockers;
  • suggested implementation order.

Never invent a remembered project name merely because it sounds plausible.

Examples

  • Input: a voice transcript that first says “mobile page,” later corrects it to a responsive web dashboard, and leaves the export format uncertain.
  • Output: the corrected scope, a visible export-format assumption, user flows, data entities, acceptance tests, and YES_WITH_ASSUMPTIONS readiness.

Limitations

Do not resolve names from memory when the host does not legitimately expose that context. Do not mark a specification ready when ambiguity changes architecture, cost, security, or data-loss risk.

Troubleshooting

If corrections conflict, prefer the latest explicit correction and record the conflict. If the requested behavior cannot be tested, rewrite it as an observable outcome or leave it as an open blocker.

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 Vibe To Spec AI skill do?

Convert messy voice input, imperfect speech recognition, half-formed product ideas, and iterative corrections into an implementation-ready software specification for Codex, Claude Code, Copilot, Cursor, or another coding agent. Use when the user speaks faster than they structure requirements, named entities are misrecognized, context or memory can safely resolve recurring terms, and the final output needs scope, flows, data, constraints, acceptance tests, and explicit unknowns rather than a raw transcript.

Why use Vibe To Spec on TypingMind?

Because you install it once and use it with any model. Vibe To Spec 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 Vibe To Spec in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/FAIRY123456789/human-edge-agent-skills/tree/main/plugins/voice-to-work/skills/vibe-to-spec. 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 Vibe To Spec?

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 Vibe To Spec?

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

Is the Vibe To Spec AI skill free?

Yes. It is published on GitHub by FAIRY123456789 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.

Related AI Skills

View all
openclaw logo

Release Openclaw Ci

openclaw
OrganizationPopular

Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

82.2K
391K
3 files
View
openclaw logo

Release Openclaw Mac

openclaw
OrganizationPopular

Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion.

82.2K
391K
Instructions
View
openclaw logo

Release Openclaw Maintainer

openclaw
OrganizationPopular

Prepare, publish, recover, or verify OpenClaw beta, stable, and extended-stable releases, including approved backports.

82.2K
391K
11 files
View
openclaw logo

Release Openclaw Plugin Testing

openclaw
OrganizationPopular

Plan and run pre-release OpenClaw plugin validation across bundled plugins, package artifacts, lifecycle commands, doctor/fix, config round-trip, gateway startup, SDK compatibility, Docker E2E,…

82.2K
391K
1 files
View

Set up your own AI workspace now

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