Predict — AI skill for Claude Code
Initiate the Predict stage of PRIMM-AI+ on a file or code snippet.
How to install Predict
Installs to ~/.claude/commands/panaversity-primm-ai-starter-kit-predict.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/panaversity/primm-ai-starter-kit/HEAD/.claude/commands/predict.md -o ~/.claude/commands/panaversity-primm-ai-starter-kit-predict.md Restart Claude Code, or start a new session, for it to be picked up.
What Predict does
name: predict description: Initiate the Predict stage of PRIMM-AI+ on a file or code snippet
Predict Stage Activated
The student is at the **Predict stage** of PRIMM-AI+. Your role is strict.
Your behavior
**Do not reveal the output.** Even if asked directly. Even if it seems obvious. The whole point of this stage is for the student to commit to a prediction before seeing the answer.
**Ask the student to predict** what the code will print. Be specific: "What exac
Alternatives in AI
- Claudomat Mini — Battle-tested operating system for shipping product with LLM coding agents 74 ★
- Codexlens Search — Lightweight semantic code search engine — 2-stage vector + FTS + RRF fusion + MCP server for Claude Code 45 ★
- Fable Prep — Stage your hardest work now 8 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Modify
Initiate the Modify stage of PRIMM-AI+ on a file
Primm
Run a complete five-stage PRIMM-AI+ cycle on any topic
Decision Content Builder
Builds decision-stage content that people and AI engines trust at the moment of choosing. Honest comparison pa
AI Fluency Assessment Skill
A Claude Code skill for quarterly AI fluency assessment using Anthropic's 4D Framework and Yegge's 8-Stage Dev
Design Image Studio
Design-as-a-loop AI image studio Five-stage workflow combining Claude Design philosophy with engineering disci
Dd Brain
Open the Personal Second Brain and Knowledge OS department (reflect stage) and route the request to one of its
Related Agents
Qe Regression Risk Analyzer
Analyzes code changes to predict regression risk and intelligently select minimal test suites
Outcome Predictor
Independent reviewer for reform analyses. Mode 1 (predict) reads ONLY the reform provisions and predicts expec
Alfresco Debugger Agent
Given an Alfresco stack trace or log snippet, searches documentation and known issues to diagnose the root cau