The Invent Nothing Rule

SkillDocs & knowledge

The "invent nothing" rule and the Marketing Claim Matrix format for OpenRisk. Load before writing, reviewing or approving any README, ROADMAP, documentation, marketing copy or release note.

Use The Invent Nothing Rule in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add The Invent Nothing Rule and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the The Invent Nothing Rule skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

The Invent Nothing RuleStart free

What this skill tells your AI

The instructions your AI receives, as published by opendefender/openrisk in .claude/skills/openrisk-claim-matrix/SKILL.md and read by Ahel’s review.

No statement describing what OpenRisk does may ship unless the implementing code exists and a user can reach it.

The matrix — docs/MARKETING_CLAIM_MATRIX.md

IDClaim (EN)Claim (FR)StatusEvidence (file:line + test)SurfaceVerified on

Status: VERIFIED · PARTIAL · MOCKED · ABSENT · PLANNED

Rules

  • PLANNED claims are future tense and visually marked on the surface where they appear. "Will support X in Q1" is honest. "Supports X" is not.
  • MOCKED and ABSENT claims never appear on a public surface. No exception.
  • Evidence is a file path plus a passing test. A design file, a screenshot, or a green build is not evidence that a feature works.
  • A UI whose endpoint 500s because its table is excluded from AutoMigrate is MOCKED, not PARTIAL.
  • A widget with a graceful fallback for a nonexistent endpoint is MOCKED.
  • Re-verify the whole matrix before every release, site deploy and milestone close.
  • Anyone may add a claim; only product-verifier may set VERIFIED.

Signals

GitHub stars
35
Forks
3
Last commit
Oct 2026
Advanced
Item type
skill
Key
openrisk-claim-matrix
Source
github.com/opendefender/openrisk