Kickoff Doc logo

Kickoff Doc

CommunityPopular
rjs
kickoff-doc

Turn a shaped project kickoff transcript into a reference document for the builder. Use when the user has a transcript (VTT, etc.) from a kickoff call and wants to produce a document that captures what was shaped and agreed.

Overview

Publisherrjs
Repositoryshaping-skills
Skill namekickoff-doc
Stars
1.4K
Forks
90
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Kickoff Doc 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.
  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/rjs/shaping-skills.git /tmp/shaping-skills
mkdir -p .claude/skills
cp -r /tmp/shaping-skills/kickoff-doc .claude/skills/kickoff-doc
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kickoff Doc 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 Kickoff Doc 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 Kickoff Doc 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.

Kickoff Document from Transcript

Turn a kickoff call transcript into a builder-facing reference document for a shaped project.


Before You Start

Ask the user:

  1. Who is the primary audience? (Usually the builder who will implement the work.)
  2. What other inputs are there? (Visuals, screenshots, mockups, breadboards from the session.)

The transcript is your source material. The document is NOT a summary of the call — it's a map of the territory that was shaped.


Organizing Principle: Territory, Not Timeline

A kickoff transcript is sequential — people talk through things in the order they come up, circle back, go on tangents, get sidetracked by browser issues. Your job is to reconstruct the territory they were describing, not replay the conversation.

Organize by the thing being built. Each section should describe one area of the system fully — so the builder can look up "how does the Criteria tab work?" and find everything in one place.

Do NOT organize by build sequence. If the team identified slices (a sequence of vertical slices to build in order), those are managed separately — not in this document.


Structure

The document has two top-level sections: Frame and Shape. Both are ## headings. Their subsections are ###.

1. Frame (## Frame)

The strategic context and boundary conditions. This is NOT fluff — the builder needs this to make judgment calls when they hit ambiguity.

  • ### Problem — Why this project, why now. What's broken or missing.
  • ### Outcome — The specific outcomes expected. What success looks like.

2. Shape (## Shape)

One ### section per area of the system. For each area, describe:

  • What it is and what's on the screen (affordances, components, data displayed)
  • How it relates to other areas
  • Design decisions that belong to THIS area — inline, not in a separate section
  • Edge cases or flags that were called out
  • What's temporary/placeholder vs. what's a real commitment

Do NOT include a Build Sequence section. Slices are tracked separately from this document.


Voice: Use Their Words

The document is a record of shared understanding from the kickoff call.

Do

  • Use the actual words and phrases people used on the call
  • Synthesize scattered discussion into clearer form (taking something said across several turns and stating it cleanly)
  • Capture the reasoning people gave for decisions ("we're doing X because Y")

Don't

  • Put new ideas or conclusions in people's mouths
  • Add motivational framing they didn't express ("each piece is a foundation, not a throwaway")
  • Editorialize about importance or quality beyond what was said

The Test

For every sentence, you should be able to point to a moment in the transcript where someone said it or clearly meant it. If you can't, either cut it or flag it as your own synthesis.

Exception: Editorializing that clarifies or synthesizes what was said IS fine. "The criteria screen is how filtering is expressed in the new world" — nobody said that exact sentence, but it accurately captures a point made across several turns. That's the job: make scattered discussion legible without adding your own conclusions.


Design Decisions: Vertical, Not Horizontal

Do NOT create a grab-bag "Design Decisions" section. Instead, put each decision inline in the section where it matters.

  • "Matches stored in DB not Redis" → goes in the section about matching
  • "Candidates must be materialized before attachment" → goes in the section about attaching
  • "Per-ICP match data as value objects" → goes in the section about match results

If a decision only matters when building one specific area, it belongs in that area's section. The builder shouldn't have to cross-reference a separate decisions list while working on a specific screen.


Process

  1. Read the full transcript. Don't start writing after reading part of it.
  2. Identify the areas of the system that were discussed — these become your ### sections under ## Shape.
  3. Draft the Frame (## Frame with ### Problem and ### Outcome) from the framing/outcomes discussion (usually near the start of the call).
  4. Write each Shape section (### ...), pulling from wherever in the transcript that area was discussed. A single section may draw from moments scattered across the whole call.
  5. Place design decisions inline in the section they belong to.
  6. Review against the transcript — can you point to where each claim was said?

Frequently asked questions

What does the Kickoff Doc AI skill do?

Turn a shaped project kickoff transcript into a reference document for the builder. Use when the user has a transcript (VTT, etc.) from a kickoff call and wants to produce a document that captures what was shaped and agreed.

Why use Kickoff Doc on TypingMind?

Because you install it once and use it with any model. Kickoff Doc 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 Kickoff Doc in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rjs/shaping-skills/tree/main/kickoff-doc. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kickoff Doc?

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 Kickoff Doc?

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

Is the Kickoff Doc AI skill free?

It is published on GitHub by rjs. Check the repository for licensing terms. 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 👇