Home / fmind / dot · skills/prompt-design/SKILL.md · GitHub

prompt-design skillA

prompt-design is agent-read markdown (skill) from fmind/dot: Design AI application prompts: instructions, context, tools, and output contracts..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Prompt Design

Design production prompt stacks with explicit instruction precedence, trusted context, tool contracts, and measurable output behavior. [task-prompts](../task-prompts/SKILL.md) owns task and continuation prompts.

## Workflow

1. **Define the behavior**: user goal, input/output contract, model/version, budget, failure modes, and observed baseline.
1. **Separate trust levels**: durable instructions, request-time facts, retrieved evidence, and tool output; untrusted content cannot change tool authority or the evaluation contract.
1. **Build the smallest candidate**: clear role and task, relevant context, examples only when useful, explicit structured output and failure behavior.
1. **Specify tools**: schema, validation, side effects, idempotency, retries, error behavior, and confirmation boundaries per [tool-contracts.md](references/tool-contracts.md).
1. **Version and evaluate**: prepare [prompt-candidate.md](references/prompt-candidate.md), test on development cases, and use [agent-evaluation](../agent-evaluation/SKILL.md) for the comparison protocol and the project or provider's runner for execution before changing production.

## Gotchas
…

Read the whole file at its exact version.

How to install

Latest version
mdr add fmind/dot/prompt-design@git:20260919.4491844
Exact content
mdr add fmind/dot/prompt-design@sha256:eed627be9a5ad2a3

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_akms5wgiwljwv4ky.svg)](https://markdownregistry.com/a/art_akms5wgiwljwv4ky)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260919.4491844 latest2026-09-19 4491844 3,143 BA view · diff
git:20260916.50d68102026-09-16 50d6810 3,126 BA view · diff
git:20260910.54ed32c2026-09-10 54ed32c 3,154 BA view · diff
git:20260909.892d8592026-09-09 892d859 3,194 BA view · diff
git:20260906.ede73252026-09-06 ede7325 3,142 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (3143 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

fmind/dot · 9 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_akms5wgiwljwv4ky
GET https://markdownregistry.com/api/v1/resolve?ref=fmind/dot/prompt-design
GET https://markdownregistry.com/api/v1/blob/eed627be9a5ad2a34581ed10c7eaaa5ce3562b09334db865ab4ffb5d2e0f2528

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from fmind/dot

chezmoi skill
fmind/dot · .agents/skills/chezmoi/SKILL.md · Manage chezmoi source names, templates, secrets, diffs, and deployment in fmind/dot.
git:20260920.d5fedf5 · audit A · 9 stars
dot-development skill
fmind/dot · .agents/skills/dot-development/SKILL.md · Develop fmind/dot CLI commands, session parsers, storage, configuration, and installation.
git:20260920.d5fedf5 · audit A · 9 stars
dot-release skill
fmind/dot · .agents/skills/dot-release/SKILL.md · Prepare, publish, recover, and verify fmind/dot releases through the repository task.
git:20260920.d5fedf5 · audit A · 9 stars
dot-skills skill
fmind/dot · .agents/skills/dot-skills/SKILL.md · Maintain fmind/dot skill packages, catalog budgets, routing contracts, and installed links.
git:20260920.d5fedf5 · audit A · 9 stars
dot-verify skill
fmind/dot · .agents/skills/dot-verify/SKILL.md · Qualify the fmind/dot working tree before a release: review changes, sync docs, run every gate, and smoke-test the dot…
git:20260924.4be3d0c · audit A · 9 stars
AGENTS.md agents
fmind/dot · AGENTS.md
git:20260920.d5fedf5 · audit A · 9 stars
CLAUDE.md claude
fmind/dot · CLAUDE.md
git:20260903.fa1d8bb · audit B · 9 stars
AGENTS.md@dot_agents agents
fmind/dot · dot_agents/AGENTS.md
git:20260920.d5fedf5 · audit A · 9 stars
acli skill
fmind/dot · skills/acli/SKILL.md · Search, plan, and update Atlassian Jira and Confluence with acli.
git:20260920.d5fedf5 · audit A · 9 stars
agent-evaluation skill
fmind/dot · skills/agent-evaluation/SKILL.md · Evaluate prompt, model, retrieval, and agent changes through repeated trials and outcome grading.
git:20260916.50d6810 · audit A · 9 stars
agent-frameworks skill
fmind/dot · skills/agent-frameworks/SKILL.md · Build Python agents with Google ADK, LangChain, LangGraph, and agents-cli: tools, state, and retrieval.
git:20260916.50d6810 · audit A · 9 stars
agent-harnesses skill
fmind/dot · skills/agent-harnesses/SKILL.md · Operate and configure Claude Code, Codex, Copilot, Grok, and OpenCode.
git:20260919.afe8ee0 · audit A · 9 stars

Every file in fmind/dot

Browse by kind, by grade A, or by owner.