Home / nahid-sparktales / agent-dispatcher · GitHub

prompt-engineering SKILL.md skillA

prompt-engineering from nahid-sparktales/agent-dispatcher is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add nahid-sparktales/agent-dispatcher/prompt-engineering@git:20260919.a0d4f55

Pins git:20260919.a0d4f55 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: nahid-sparktales/agent-dispatcher
Path: skills/ai/prompt-engineering/SKILL.md
Versions recorded: 1
Latest version: git:20260919.a0d4f55, committed Sep 19, 2026
Size: 6,048 bytes
Repository stars: 58
License: MIT

Write or revise a prompt so it holds up — output contract, instruction placement, examples that earn their place, an escape hatch for bad input — and measure the change against a saved set of cases instead of one good-looking run. Use when a prompt is being authored or patched, when output is inconsistent or the wrong shape, when a model or version changes, or when someone reports a prompt as fixed. Not for scoping an agent's job and tools, not for deciding what material to load into the…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Prompt engineering

A prompt that worked once is an anecdote. Almost every "fixed" prompt was judged on the input that
motivated the edit, on a single run, against no recorded baseline.

## When this fires

Authoring or editing any prompt whose output something depends on, and any time a prompt is
declared improved. It does not fire for a one-off question you ask and read yourself.

## Procedure

1. **Collect cases before editing.** At least five real inputs, including the two that fail now and
   two that currently pass and must keep passing. No cases means no measurement is possible — say
   that plainly instead of shipping an eyeballed change.
2. **Run the baseline and record it.** Every case, actual output saved, pass or fail marked. This
   is the only thing a later claim of improvement can be checked against.
3. **Write the output contract first.** Exact shape, field names, ordering, units, and what the
   output looks like when the model cannot comply. Unspecified format is the single most common
   defect, and it is invisible until something downstream parses it.
4. **Separate durable instruction from variable data.** Keep the standing rules in one place and
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add nahid-sparktales/agent-dispatcher/prompt-engineering@sha256:f61d86afdb407491

The line at the top of this page pins the label git:20260919.a0d4f55, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_iqwqo3fkjn7m6lfp.svg)](https://markdownregistry.com/a/art_iqwqo3fkjn7m6lfp)

8 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 19, 2026.

version	committed	commit	size	audit
git:20260919.a0d4f55 latest	2026-09-19	a0d4f55	6,048 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the 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 (6048 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

nahid-sparktales/agent-dispatcher · 58 stars · license MIT · pushed 2026-10-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_iqwqo3fkjn7m6lfp
GET https://markdownregistry.com/api/v1/resolve?ref=nahid-sparktales/agent-dispatcher/prompt-engineering
GET https://markdownregistry.com/api/v1/blob/f61d86afdb407491aa6a253395a0ff10f7b0ddaa5246a9cb77ac5d4a86e5b05e

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from nahid-sparktales/agent-dispatcher

agent-dispatcher SKILL.md skill

nahid-sparktales/agent-dispatcher · skills/agent-dispatcher/SKILL.md · Handle requested Agent Dispatcher work with direct execution or prepared specialist guidance. Includes named roles…

git:20260926.d1b76c1 · audit A · 58 stars

agent-design SKILL.md skill

nahid-sparktales/agent-dispatcher · skills/ai/agent-design/SKILL.md · Scope an agent or subagent before it is built — the one job it owns, the smallest tool set that closes that job, what…