prompt-author

Included with Lifetime

$97 forever

Design a single high-quality prompt — the innermost layer an agent reads. Use when a Smithers <Task>'s prompt (its .mdx body or inline string) is vague, ambiguous, or underperforming and you want to tighten the instruction, role, constraints, examples, and output contract before reaching for harness or workflow changes.

Design

What this skill does


# Prompt Author

This skill is about **one layer only: the prompt** — the literal text a single
agent reads. It is the innermost ring of the layered model (prompt → context →
harness → workflow → backpressure; see `skills/context-engineer/SKILL.md`). When
the *graph* is fine but a step keeps producing weak or off-target output, the fix
is usually here, not in the workflow.

## When to reach for it

- A `<Task>`'s output is vague, wrong-shaped, or inconsistent run to run.
- The agent ignores a constraint, invents a format, or stops short of the goal.
- You're tempted to add a retry/reviewer to paper over a prompt that simply
  never said clearly what "done" looks like. Fix the prompt first.

Skip it when the real problem is missing context, the wrong tools/permissions, or
a missing review gate — those are outer layers (`context-engineer`, the harness in
`agents.ts`, the workflow graph).

## What makes a strong prompt

1. **One clear instruction.** Lead with the single concrete task in plain
   imperative voice. No instruction soup; goal-based beats step-by-step.
2. **Role / framing** when it changes behavior ("You are an independent reviewer
   who can reject the diff"). Skip it when it's decoration.
3. **Explicit constraints.** State the must-nots and the bounds: no dead code, no
   magic numbers, don't touch file X, stay under N changes.
4. **Examples** for anything format- or taste-sensitive — one good + one bad
   example teaches more than a paragraph of rules.
5. **Decomposition** for multi-part work: a short numbered checklist of what to
   verify or produce, so nothing is silently dropped.
6. **Success criteria / finish line.** Define "done" as checkable conditions
   ("existing tests pass; new tests prove per-account limits; reviewer approves"),
   plus a cap and fallback for any "keep going until…".

## The Smithers angle: prompts are `.mdx` a `<Task>` renders

In a seeded pack, prompts live as `.smithers/prompts/*.mdx`, authored as JSX
prompt components and imported into a workflow as a tag:

```tsx
import ReviewPrompt from "../prompts/review.mdx";
<Task id="review" output={outputs.review} agent={reviewer}>
  <ReviewPrompt diff={ctx.output("implement").patch} />
</Task>
```

The `.mdx` body *is* the prompt; props inject context. Keep the file focused on
instruction + constraints + criteria, and let the workflow supply the variable
context.

**Critical: end the prompt before the output schema, not with your own JSON
spec.** When a `<Task>` has an `output={outputs.x}` Zod schema, the runtime
auto-appends a `**REQUIRED OUTPUT**` block describing the JSON shape to the *end*
of the prompt, and the parser reads the **last** JSON object in the response. So:

- **Do** end your `.mdx`/string with the task and criteria — leave the tail clean
  for the injected schema. Hand-writing your own "return JSON like {…}" fights the
  injected block and confuses the last-JSON parser.
- **Do** describe *what* each field means in prose if it's non-obvious; let the
  schema describe the *shape*.
- **Don't** wrap the agent in conflicting format rules ("write a report" + a JSON
  schema) — the schema wins, so phrase the body so its result *is* the JSON.

Agents that support native structured output skip the injected block, so a prompt
that defers to the schema works in both modes.

## Tighten-and-verify loop

Edit the `.mdx`, re-run with `--hot true` so wording changes apply on the next
frame without losing finished tasks, then attach a `schemaAdherence` scorer (or a
small `smithers eval` suite) to confirm the new prompt actually holds the format:

```bash
bunx smithers-orchestrator up workflow.tsx --hot true --input '{"prompt":"…"}'
bunx smithers-orchestrator scores <run-id>     # did schema adherence improve?
```

See `skills/smithers/SKILL.md` for the runtime/CLI surface and `docs/llms-core.txt`
("Good Smithers prompts are goal-based") for the canonical prompt examples.

Files: 1

Size: 4.2 KB

Complexity: 9/100

Category: Design

Source: https://github.com/codeplaneapp/smithers/tree/main/skills/prompt-author

Related in Design

contribute

Included

Local-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".

Designscripts

architectural-analysis

Included

User-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).

Designscripts

mcp

Included

Model Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.

Designscripts

react-native-skia

Included

Design, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.

Designscripts

plaid

Included

Product Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".

Designscripts

nextjs-framer-motion-animations

Included

Adds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.

Designscripts