Product Skills for
AI Harness.

Product craft happens too far from the codebase.

Decisions are made in docs, slides, and chat — disconnected from the codebase where the truth is.

• — Products are increasingly more complex in the AI Era — Most of the spec relates to an invisible logic. It's not anymore about UI. It's much more about agents, sub-agents, skills, tools, memory management, etc.
• — Product scoping without access to the codebase becomes less relevant — AI Harness tools such as Claude Code or others allow product people to query the codebase without knowing how to code.
• — Every source of truth should be accessible to AI-harness — With coding, data from Analytics, Database, Competitors website etc. can be gathered in a central source of context for product thinking.

Acumen fixes this by embedding product craft where the building happens — skills that read your codebase and an organised knowledge layer before they write a single line.

19 skills. Each one reads your product's context before it writes a single line.

Each skill is a focused product operation — grounded in your codebase and knowledge layer, not generic prompting.

Context that lives where the code lives.

Acumen closes the distance with persistent context files that live in your repo, versioned alongside code. Every skill reads them before it writes. The more you use Acumen, the sharper the output gets.

.acumen.md

Product context: users, strategy, positioning, constraints, north star metric.

Created by /teach-acumen

.acumen/value-chain.md

End-to-end workflow map per persona — extension points, friction, expansion opportunities.

Created by /teach-acumen · Updated by /workshop

.acumen/personas.md

Behavioral personas grounded in real usage patterns, not demographics.

Maintained by /persona

.acumen/competitors.md

Living competitor map: who they are, what they ship, where they're strong and weak.

Maintained by /scout

.acumen/features.md

Feature inventory: what exists, what's healthy, what's decaying, what's missing.

Maintained by /features

.acumen/value.md

Per-persona value delivery mapped to usage and north star metrics.

Maintained by /value

.acumen/sources.md

Data source config: analytics, database, backlog — how skills pull real data.

Connects to

Created by /teach-acumen

.acumen/reports/

Point-in-time outputs from diagnostic and ideation skills.

Generated by /diagnose, /measure, /workshop

Install in under a minute.

Acumen follows the agents.md spec. Drop the skills into your AI tool and go.

Step 1

Open your codebase

Use any coding agent that supports the agents.md spec. It works with read-only access rights.

Step 2

Install Acumen

# One command, auto-detects your tool
npx skills add VGrss/acumen

Step 3

Teach & go

# One-time product context
/teach-acumen

# Then let the skills guide you
/diagnose
/orientation
/workshop

Each skill suggests the next one. Just follow the flow.

The stack is collapsing. Product «» Design «» Developer: all become Builders with a speciality.

Every profile benefits from reinforcing their Product Acumen.