# Send Shaping & Breadboarding to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "shaping",
    "name": "Shaping & Breadboarding",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/Borahm/shaping",
    "canonicalUrl": "https://clawhub.ai/Borahm/shaping",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/shaping",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=shaping",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "references/breadboarding.md",
      "references/shaping.md"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "shaping",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-08T19:14:14.945Z",
      "expiresAt": "2026-05-15T19:14:14.945Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=shaping",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=shaping",
        "contentDisposition": "attachment; filename=\"shaping-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "shaping"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/shaping"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/shaping",
    "downloadUrl": "https://openagent3.xyz/downloads/shaping",
    "agentUrl": "https://openagent3.xyz/skills/shaping/agent",
    "manifestUrl": "https://openagent3.xyz/skills/shaping/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/shaping/agent.md"
  }
}
```
## Documentation

### Shaping & Breadboarding

Structured methodology for defining problems, exploring solutions, and planning implementation. Based on Shape Up adapted for working with an LLM.

Source: rjs/shaping-skills by @rjs (Ryan Singer, author of Shape Up)

### Two Skills in One

Shaping — Iterate on problem (requirements) and solution (shapes) before committing to implementation. Separates what you need from how you might build it, with fit checks to see what's solved and what isn't.

Breadboarding — Map a system into UI affordances, code affordances, and wiring. Shows what users can do and how it works underneath in one view. Good for slicing into vertical scopes.

### When to Use

Exploring a new feature or product direction
Comparing solution approaches before building
Mapping an existing system to understand where changes land
Breaking a selected solution into vertical implementation slices
Any "should we build X or Y?" discussion

### Entry Points

Start from R (Requirements) — Describe the problem, pain points, constraints. Build up requirements and let shapes emerge.
Start from S (Shapes) — Sketch a solution already in mind. Capture it as a shape and extract requirements as you go.

No required order. R and S inform each other throughout.

### Core Notation

LevelNotationMeaningRelationshipRequirementsR0, R1, R2...Problem constraintsMembers of set RShapesA, B, C...Solution optionsPick one from SComponentsC1, C2, C3...Parts of a shapeCombine within shapeAlternativesC3-A, C3-B...Approaches to a componentPick one per component

### Phases

Shaping → Slicing

Shaping: Explore problem/solution space, select and detail a shape
Slicing: Break down for implementation into vertical slices with demo-able UI

### Key Actions

Populate R — Gather requirements as they emerge
Sketch a shape — Propose a high-level approach
Detail — Break shape into components or concrete affordances
Check fit — Build decision matrix (R × S), binary ✅/❌ only
Breadboard — Map to UI/Code affordances with wiring
Spike — Investigate unknowns
Slice — Break breadboarded shape into vertical increments

### Detailed Reference

For the complete methodology, notation rules, examples, and procedures:

Shaping reference: See references/shaping.md — Full shaping methodology including fit checks, parts, spikes, documents, multi-level consistency
Breadboarding reference: See references/breadboarding.md — Complete breadboarding procedure, affordance tables, places, wiring, Mermaid conventions, chunking, slicing

Load the relevant reference when entering that phase of work.

### Quick Reference: Fit Check Format

| Req | Requirement | Status | A | B | C |
|-----|-------------|--------|---|---|---|
| R0 | Full requirement text | Core goal | ✅ | ✅ | ✅ |
| R1 | Full requirement text | Must-have | ✅ | ❌ | ✅ |

Always show full requirement text, never abbreviate
Binary only: ✅ or ❌. No ⚠️ in fit checks
Explanations go in Notes section below the table

### Quick Reference: Affordance Tables

UI Affordances: # | Place | Component | Affordance | Control | Wires Out | Returns To
Code Affordances: Same columns
Controls: click, type, call, observe, write, render
Wires Out (solid →): Control flow — calls, triggers, writes
Returns To (dashed -.->): Data flow — return values, reads

### Quick Reference: Slicing

Every slice must end in demo-able UI
Max 9 slices
Each slice demonstrates a mechanism working
Format: V1: Name — affordances, demo statement
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: Borahm
- Version: 1.0.0
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-08T19:14:14.945Z
- Expires at: 2026-05-15T19:14:14.945Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/shaping)
- [Send to Agent page](https://openagent3.xyz/skills/shaping/agent)
- [JSON manifest](https://openagent3.xyz/skills/shaping/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/shaping/agent.md)
- [Download page](https://openagent3.xyz/downloads/shaping)