title: Wishes
shell: standard
components:
- type: header
title: Wishes
subtitle: Point kazam at a folder with your real context, let your agent read it, get back a populated YAML. No terminal interviews, no file parsing in kazam.
- type: section
eyebrow: The flow
heading: Scaffold, drop, grant
components:
- type: markdown
body: |
A **wish** is a workspace template plus the prompt that tells your agent
how to turn that workspace into a valid kazam YAML. kazam scaffolds the
workspace and shells out to your agent — it doesn't parse PDFs, chunk
large files, or do anything the agent is already good at.
- type: columns
equal_heights: true
columns:
- - type: callout
variant: info
title: 1. Make the wish
body: "`kazam wish deck` with no `wish-deck/` folder present scaffolds one: `questions.md` for structured prompts, `README.md` for what to drop in, and `reference/` with the schema + a worked example (version-matched to the binary)."
- - type: callout
variant: info
title: 2. Add your context
body: "Fill in any parts of `questions.md` you already know the answer to. Drop your real material into the folder — meeting notes, transcripts, last quarter's deck, PDFs, metrics dumps. Anything the agent can read is fair game."
- - type: callout
variant: info
title: 3. Grant it
body: "`kazam wish deck` a second time. kazam picks the first agent on your `$PATH` (Claude, Gemini, Codex, OpenCode), runs it from inside the workspace, and writes `deck.yaml`. The agent reads the workspace with its own file tools."
- type: section
eyebrow: First wish
heading: "kazam wish deck"
components:
- type: markdown
body: |
A 7-slide QBR / strategy-review deck. The agent writes every slide —
cover, context, wins, challenges, learnings, next, the ask — from
whatever you drop into the workspace. No placeholder copy.
- type: code
language: bash
code: |
kazam wish deck # 1st run: scaffold wish-deck/
# …fill in wish-deck/questions.md, drop your context files…
kazam wish deck # 2nd run: grant it
kazam wish deck --yolo # skip the workspace, agent invents everything
kazam wish deck --yolo "about me" # YOLO with a topic (agent pulls from context)
kazam wish deck --agent claude # force a specific agent
kazam wish deck --dry-run # print the grant prompt
kazam wish deck --stdout # portable wish spec (markdown)
kazam wish deck --out quarterly.yaml # pick the output path
kazam wish list # see every wish
- type: callout
variant: info
title: 🎲 YOLO mode
body: "Skip the workspace entirely with `kazam wish deck --yolo`. The agent invents every slide — no questions, no context files, just vibes. Pass an optional topic (`--yolo \"about me\"`, `--yolo \"history of coffee\"`) or leave it bare for a surprise. Great for demos, warm-ups, or when your agent already knows you well enough to write the deck."
- type: section
eyebrow: Applications
heading: First-class in every agent
components:
- type: markdown
body: |
kazam auto-detects the first agent on your `$PATH` and shells out using
its native non-interactive mode. No skill installer, no per-agent plugin
format. Pass `--agent <name>` to force a specific one.
- type: card_grid
columns: 2
cards:
- title: "Claude Code"
description: "`claude -p` — best for agents that want to use Read tools on your context."
color: default
- title: "Gemini CLI"
description: "`gemini -p` — Google's CLI, same one-shot prompt shape."
color: default
- title: "Codex"
description: "`codex exec` — OpenAI's Codex CLI, subcommand form."
color: default
- title: "OpenCode"
description: "`opencode run` — SST's open-source agent CLI."
color: default
- title: "No CLI agent? No problem."
badge:
label: universal
color: teal
description: "Scaffold the workspace with `kazam wish deck`, fill in questions.md, then `kazam wish deck --dry-run` prints the full grant prompt. Paste it into ChatGPT, Claude.ai, Gemini web, Cursor, Aider, or any other LLM context window — save what comes back as `deck.yaml`."
color: teal
- type: section
eyebrow: The catalog
heading: Every wish
components:
- type: markdown
body: |
`deck` ships today. The rest land one at a time — each one a Friday drop for a
minor release. More wishes get added as patterns emerge in the wild.
- type: card_grid
min_width: 260
cards:
- title: "kazam wish deck"
badge:
label: shipped
color: teal
description: "QBR / strategy-review deck (7 slides). Cover, context, wins, challenges, learnings, next, the ask."
- title: "kazam wish brief"
badge:
label: planned
color: default
description: "Incident brief / meeting agenda. Document shell, print-optimized."
- title: "kazam wish landing"
badge:
label: planned
color: default
description: "Indie-hacker landing page with hero, features, stats, CTA."
- title: "kazam wish api-ref"
badge:
label: planned
color: default
description: "OpenAPI-style endpoint documentation."
- title: "kazam wish dashboard"
badge:
label: planned
color: default
description: "Dashboard + `sync.sh` reference script. You own the fetcher; kazam ships zero connectors."
- title: "kazam wish post-mortem"
badge:
label: planned
color: default
description: "Structured incident post-mortem — timeline, impact, learnings."
- title: "kazam wish resume"
badge:
label: planned
color: default
description: "Personal CV / resume riff."
- title: "kazam wish roadmap"
badge:
label: planned
color: default
description: "Public product roadmap with timeline and status."
- type: section
eyebrow: Next
components:
- type: callout
variant: info
title: Next up → Components
body: Browse the component catalog to see what the rendered output can look like. `kazam agents` prints the full authoring guide — it's also what kazam drops into every wish workspace as `reference/kazam-schema.md`.