cortex-prompt SKILL.md skillA

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

cortex-prompt from tonone-ai/tonone is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add tonone-ai/tonone/cortex-prompt@v0.6.4

Pins v0.6.4 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
tonone-ai/tonone
Path
bundle/engineering-team/skills/cortex-prompt/SKILL.md
Versions recorded
1
Latest version
v0.6.4, committed Sep 26, 2026
Size
9,087 bytes
Repository stars
76
License
MIT

Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval criteria. Use when asked to "prompt engineering", "build a prompt", "write a system prompt", or "improve this prompt".

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

# Build a Production-Ready Prompt

You are Cortex — the ML/AI engineer on the Engineering Team. Given a task description, produce the complete prompt package: system prompt, user template, few-shot examples, output schema, edge case handling, and eval criteria. Write the artifact — don't coach the human to write it.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

## Step 0: Scan for Context

Before asking anything, check what already exists:

```bash
# Existing prompts
find . -type f -name "system.txt" -o -name "system_prompt*" -o -name "*prompt*.txt" -o -name "*prompt*.yaml" 2>/dev/null | head -10
grep -rl "SYSTEM_PROMPT\|system_message\|system.*prompt" --include="*.py" --include="*.ts" --include="*.js" . 2>/dev/null | head -10

# LLM provider and SDK
cat requirements.txt 2>/dev/null | grep -iE "anthropic|openai|google-generativeai|cohere|langchain|llamaindex"
cat pyproject.toml 2>/dev/null | grep -iE "anthropic|openai|google-generativeai|cohere"
cat package.json 2>/dev/null | grep -iE "anthropic|openai|@google"

# Existing eval or test infrastructure
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add tonone-ai/tonone/cortex-prompt@sha256:0cc41f9d9ceb3c88

The line at the top of this page pins the label v0.6.4, 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 badge

[![mdr](https://markdownregistry.com/badge/art_swozjkmsbgniaem5.svg)](https://markdownregistry.com/a/art_swozjkmsbgniaem5)

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

Versions

The registry has recorded 1 version of this file, committed on Sep 26, 2026.

versioncommittedcommitsizeaudit
v0.6.4 latest2026-09-26 fd813e4 9,087 BA 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 (9087 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

tonone-ai/tonone · 76 stars · license MIT · pushed 2026-10-14 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_swozjkmsbgniaem5
GET https://markdownregistry.com/api/v1/resolve?ref=tonone-ai/tonone/cortex-prompt
GET https://markdownregistry.com/api/v1/blob/0cc41f9d9ceb3c88e7310134ab2bfd0a563b81327c1cc850ffb9a5999f0b5a66

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 tonone-ai/tonone

CLAUDE.md@.claude-plugin CLAUDE.md file
tonone-ai/tonone · .claude-plugin/CLAUDE.md
git:20260328.5082b4a · audit A · 76 stars
AGENTS.md AGENTS.md file
tonone-ai/tonone · AGENTS.md
git:20260506.3cee926 · audit A · 76 stars
CLAUDE.md CLAUDE.md file
tonone-ai/tonone · CLAUDE.md
git:20261014.1ceec80 · audit A · 76 stars
apex-plan SKILL.md skill
tonone-ai/tonone · bundle/engineering-team/skills/apex-plan/SKILL.md · Plan and scope a project — discovery, challenge assumptions, present XS-XXL depth options with token and cost…
v0.7.0 · audit A · 76 stars
apex-recon SKILL.md skill
tonone-ai/tonone · bundle/engineering-team/skills/apex-recon/SKILL.md · Engineering lead reconnaissance — inventory the project before planning. Use when asked to "understand this project"…
v0.6.4 · audit A · 76 stars
apex-review SKILL.md skill
tonone-ai/tonone · bundle/engineering-team/skills/apex-review/SKILL.md · Cross-cutting review of recent work — catches gaps between specialists. Use when asked to "review what we built"…
v0.6.4 · audit A · 76 stars
apex-status SKILL.md skill
tonone-ai/tonone · bundle/engineering-team/skills/apex-status/SKILL.md · CTO-level project status from git and codebase state. Use when asked "where are we", "project status", "what's done"…
v0.6.4 · audit A · 76 stars
apex-takeover SKILL.md skill
tonone-ai/tonone · bundle/engineering-team/skills/apex-takeover/SKILL.md · System takeover — take ownership of an existing codebase or inherited system. Use when "we acquired this", "previous…
v0.6.4 · audit A · 76 stars
atlas-adr SKILL.md skill
tonone-ai/tonone · bundle/engineering-team/skills/atlas-adr/SKILL.md · Write an Architecture Decision Record — document what was decided, why, what alternatives were considered, and what…
v0.6.4 · audit A · 76 stars
atlas-changelog SKILL.md skill
tonone-ai/tonone · bundle/engineering-team/skills/atlas-changelog/SKILL.md · Maintain per-repo and cross-repo changelogs — append structured entries after agent work. Use when asked to "log this…
v0.6.4 · audit A · 76 stars
atlas-map SKILL.md skill
tonone-ai/tonone · bundle/engineering-team/skills/atlas-map/SKILL.md · Map the system architecture — read the codebase, identify services and connections, output a C4-level architecture map…
v0.6.4 · audit A · 76 stars
atlas-onboard SKILL.md skill
tonone-ai/tonone · bundle/engineering-team/skills/atlas-onboard/SKILL.md · Generate onboarding documentation — what this project does, how to set up locally, where things live, key decisions…
v0.6.4 · audit A · 76 stars

Every file in tonone-ai/tonone

Other files named cortex-prompt

cortex-prompt SKILL.md skill
jeremylongshore/tons-of-skills-marketplace · plugins/ai-agency/tonone/skills/cortex-prompt/SKILL.md · Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval…
v0.6.4 · audit A · 2,851 stars
cortex-prompt SKILL.md skill
tonone-ai/tonone · bundle/full-team/skills/cortex-prompt/SKILL.md · Build a production-ready prompt package — system prompt, few-shot examples, output format, edge case handling, eval…
v0.6.4 · audit A · 76 stars

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