Use when structuring work so that planning, candidate generation, and verification remain separate and explicit.
Scanned 9/11/2026
Install to Claude Code
npx -y skills add ponybunny-ai/ponybunny --skill planner-generator-evaluator-pattern --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Planner Generator Evaluator Pattern?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/ponybunny-ai-planner-generator-evaluator-pattern)More formats (shields.io, HTML) on the badges page.
---
name: planner-generator-evaluator-pattern
description: Use when structuring work so that planning, candidate generation, and verification remain separate and explicit.
---
# Planner Generator Evaluator Pattern
## Use this skill when
- a task is large enough to require structured delegation
- implementation quality depends on explicit evaluation
- a migration needs safer control points
- you want to avoid generator self-approval
## Goals
- separate planning from implementation
- separate implementation from verification
- reduce false completion claims
- improve traceability and decision quality
## Responsibilities
- planner: defines phases, constraints, acceptance criteria, and verification points
- generator: produces candidate implementation for approved scope
- evaluator: determines whether the implementation is actually verified
## Process
1. Define the problem.
2. Ask planner to create the phased path.
3. Ask generator to implement only one approved phase.
4. Ask evaluator to assess the result against evidence.
5. Feed failures and weak spots into future planning or harness improvement.
## Output contract
Return:
- recommended delegation
- phase boundaries
- evidence boundaries
- stop/go points
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling