ai-product SKILL.md skillB

ai-product from ghosteken/agent-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add ghosteken/agent-harness/ai-product@git:20260721.efafd9c

Pins git:20260721.efafd9c in mdr.lock. Pin the fingerprint instead.

Audit grade
B, 16 of 17 checks passed
Kind
SKILL.md skill
Repository
ghosteken/agent-harness
Path
archive/skills-community/ai-product/SKILL.md
Versions recorded
1
Latest version
git:20260721.efafd9c, committed Jul 21, 2026
Size
19,783 bytes
Repository stars
4
License
MIT

Every product will be AI-powered. The question is whether you'll.

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

# AI Product Development

Every product will be AI-powered. The question is whether you'll build it
right or ship a demo that falls apart in production.

This skill covers LLM integration patterns, RAG architecture, prompt
engineering that scales, AI UX that users trust, and cost optimization
that doesn't bankrupt you.

## Principles

- LLMs are probabilistic, not deterministic | Description: The same input can give different outputs. Design for variance.
Add validation layers. Never trust output blindly. Build for the
edge cases that will definitely happen. | Examples: Good: Validate LLM output against schema, fallback to human review | Bad: Parse LLM response and use directly in database
- Prompt engineering is product engineering | Description: Prompts are code. Version them. Test them. A/B test them. Document them.
One word change can flip behavior. Treat them with the same rigor as code. | Examples: Good: Prompts in version control, regression tests, A/B testing | Bad: Prompts inline in code, changed ad-hoc, no testing
- RAG over fine-tuning for most use cases | Description: Fine-tuning is expensive, slow, and hard to update. RAG lets you add
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add ghosteken/agent-harness/ai-product@sha256:16a4aafed03f0907

The line at the top of this page pins the label git:20260721.efafd9c, 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_v3ttkjl3573cbpgj.svg)](https://markdownregistry.com/a/art_v3ttkjl3573cbpgj)

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

Versions

The registry has recorded 1 version of this file, committed on Jul 21, 2026.

versioncommittedcommitsizeaudit
git:20260721.efafd9c latest2026-07-21 efafd9c 19,783 BB view

Audit of the latest version

B  16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • fail: No prompt-injection phrasing (matched: Ignore all previous instructions)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (19783 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 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

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

ghosteken/agent-harness · 4 stars · license MIT · pushed 2026-10-13 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_v3ttkjl3573cbpgj
GET https://markdownregistry.com/api/v1/resolve?ref=ghosteken/agent-harness/ai-product
GET https://markdownregistry.com/api/v1/blob/16a4aafed03f090753fbe8151a03bc5e623682867c16a1760b503e659cbb6582

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 ghosteken/agent-harness

AGENTS.md AGENTS.md file
ghosteken/agent-harness · AGENTS.md
git:20261008.1dbcd11 · audit A · 4 stars
CLAUDE.md CLAUDE.md file
ghosteken/agent-harness · CLAUDE.md
git:20261008.1dbcd11 · audit A · 4 stars
2slides-ppt-generator SKILL.md skill
ghosteken/agent-harness · archive/skills-community/2slides-ppt-generator/SKILL.md · AI-powered presentation generation via the 2slides API — create slides from text, match a reference image style…
git:20260721.efafd9c · audit A · 4 stars
3d-web-experience SKILL.md skill
ghosteken/agent-harness · archive/skills-community/3d-web-experience/SKILL.md · Expert in building 3D experiences for the web - Three.js, React
git:20260721.efafd9c · audit A · 4 stars
ab-test-setup SKILL.md skill
ghosteken/agent-harness · archive/skills-community/ab-test-setup/SKILL.md · Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.
git:20260721.efafd9c · audit A · 4 stars
acceptance-orchestrator SKILL.md skill
ghosteken/agent-harness · archive/skills-community/acceptance-orchestrator/SKILL.md · Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and…
git:20260721.efafd9c · audit A · 4 stars
accesslint-audit SKILL.md skill
ghosteken/agent-harness · archive/skills-community/accesslint-audit/SKILL.md · Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written…
git:20260721.efafd9c · audit A · 4 stars
accesslint-diff SKILL.md skill
ghosteken/agent-harness · archive/skills-community/accesslint-diff/SKILL.md · Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based)…
git:20260721.efafd9c · audit A · 4 stars
accesslint-scan SKILL.md skill
ghosteken/agent-harness · archive/skills-community/accesslint-scan/SKILL.md · Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix…
git:20260721.efafd9c · audit A · 4 stars
accint-solve SKILL.md skill
ghosteken/agent-harness · archive/skills-community/accint-solve/SKILL.md · Route agent work through AccInt's MCP memory loop: retrieve prior outcomes, resolve frames, and close commitments with…
git:20260721.efafd9c · audit A · 4 stars
active-directory-attacks SKILL.md skill
ghosteken/agent-harness · archive/skills-community/active-directory-attacks/SKILL.md · Provide comprehensive techniques for attacking Microsoft Active Directory environments. Covers reconnaissance…
git:20260721.efafd9c · audit A · 4 stars
activecampaign-automation SKILL.md skill
ghosteken/agent-harness · archive/skills-community/activecampaign-automation/SKILL.md · Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation…
git:20260721.efafd9c · audit A · 4 stars

Every file in ghosteken/agent-harness

Other files named ai-product

ai-product SKILL.md skill
sickn33/agentic-awesome-skills · plugins/agentic-awesome-skills-claude/skills/ai-product/SKILL.md · Every product will be AI-powered. The question is whether you'll
git:20260905.f2e5074 · audit A · 48,329 stars
ai-product SKILL.md skill
coco-research/coco · skills/ai-product/SKILL.md · Use when building AI features into a product: LLM integration, RAG pipelines, guardrails, streaming, AI UX, prompt…
v0.1.0 · audit A · 827 stars
ai-product SKILL.md skill
francostino/opencode-skills-collection · bundled-skills/ai-product/SKILL.md · Every product will be AI-powered. The question is whether you'll
git:20260906.7d37dc9 · audit A · 87 stars
ai-product SKILL.md skill
aicodedecode/awesome-muse-skills · skills-imported/ai-product/SKILL.md · Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in…
git:20260927.806f3e1 · audit A · 25 stars
ai-product SKILL.md skill
hybridlabor-api/aos · skills/global_config/ai-product/SKILL.md · Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in…
git:20261007.97ebebf · audit B · 6 stars
ai-product SKILL.md skill
hybridlabor-api/bdb-dev-optimized-agent-skills · skills/global_config/ai-product/SKILL.md · Every product will be AI-powered. The question is whether you'll build it right or ship a demo that falls apart in…
git:20261007.97ebebf · audit B · 6 stars

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