Free — Rikki Skill

Set up Rikki in your Claude Project

Two files. Five minutes. Declare your stack, paste a transcript, and get governed build specs — one per feature, validated before you build. No infrastructure, no code, no credit card.

1

Download the two skill files

The Rikki Skill is two markdown files — the instructions that make Claude behave as Rikki, and the governance references it draws from.

Both files are plain text — you can open them in any editor to review before uploading.
2

Create a Claude Project

Go to claude.aiProjectsNew project. Name it something like "Rikki — Rikki Skill" so you can find it easily.

Need a Claude account? The free Claude.ai plan works. A Pro plan gives you a larger context window, which helps with longer transcripts.
3

Paste the skill instructions

Inside your project, click "Set project instructions". Open OG-SKILL-INSTRUCTIONS.md, copy the entire contents, and paste it into the instructions field. Save.

This is what makes Claude behave as Rikki — do not skip this step.
4

Upload the governance references

In the Project Knowledge section, click "Add content" and upload GOVERNANCE-REFERENCES.md. This gives Rikki the framework citations it applies to your artifacts.

5

Declare your stack, then test with a real transcript

Start a new conversation inside the project. First, tell Rikki your tech stack — this becomes the baseline for every spec it generates. Then paste a transcript and Rikki will interpret the intent, generate governed specs (one per feature), score confidence, and surface gaps.

Start by declaring your stack:
"Our stack is: Next.js, Supabase, Vercel, Clerk for auth, Stripe for payments."

Then generate specs:
"Here's a transcript from our product planning meeting. Generate the appropriate artifacts."

"We had this conversation about a new feature. What specs would you produce from this?"

Validate before you build:
"Validate this spec before we hand it to the engineering team."

Track changes over time:
"The payment flow spec changed after today's meeting. Generate a change log entry."
Longer transcripts produce better specs. A 30-minute meeting gives Rikki more to work with than a 2-minute Slack thread.

Common questions

Does this work with ChatGPT or Gemini?

The Claude Project version is optimized for Claude. A universal prompt version that works across ChatGPT, Gemini, and other LLMs is coming soon — join the waitlist on the main site to be notified.

Who owns the artifacts Rikki generates?

You do. Rikki generates the artifacts from your conversations — they belong to your organization. The skill files are yours to use, modify, and share.

Is my transcript data private?

Your conversations are governed by Anthropic's privacy policy for Claude.ai. Rikki is designed to treat all conversation content as confidential and does not carry context between sessions.

What governance frameworks does Rikki apply?

OWASP Top 10, OWASP LLM Top 10, NIST AI RMF, ISO 42001, ISO 27001, NIST CSF, WCAG 2.2, EU AI Act, STRIDE, and MITRE ATLAS — but only what's genuinely relevant to the feature scope. A static page won't get STRIDE analysis. A payment flow will.

Can Rikki validate a spec before we build?

Yes. Paste any spec (one Rikki generated, or your own) and say "validate this before we build." Rikki will review it as an adversarial reviewer — surfacing blockers, risks, ambiguous requirements, missing acceptance criteria, and governance gaps. It outputs a Validation Report with a clear verdict: clear to build, build with caution, or do not build yet.

How does the tech stack declaration work?

At the start of a conversation, tell Rikki your stack: "Our stack is React, Node.js, PostgreSQL, AWS." From that point, Rikki treats your stack as confirmed constraints (🟢) across every spec it generates. It will flag any requirement that conflicts with your stack, and tailor governance recommendations to your specific technologies.

What's the difference between the free skill and Rikki Platform?

The free Rikki Skill works in Claude Projects with no infrastructure. Rikki Platform (coming soon) adds persistent organizational memory, enterprise data connectors (Jira, GitHub, Slack, Linear), cross-session change tracking, and spec-to-code alignment. Join the waitlist to be first to know.