Systematic approach to building complex software by delegating prompt engineering to Claude itself. Separates analysis from execution -- generates specification-grade prompts that run in fresh sub-agent contexts.
Scanned 6/6/2026
Install via CLI
Skills Directoryopenskills install paperclipai/companies---
name: meta-prompting
description: >
Systematic approach to building complex software by delegating prompt engineering to
Claude itself. Separates analysis from execution -- generates specification-grade
prompts that run in fresh sub-agent contexts.
metadata:
sources:
- kind: github-file
repo: glittercowboy/taches-cc-resources
path: commands/create-prompt.md
commit: 0d915b80b95f9889673e1dc6a9059ed239764cde
attribution: "TÂCHES"
license: MIT
usage: referenced
- kind: github-file
repo: glittercowboy/taches-cc-resources
path: commands/run-prompt.md
commit: 0d915b80b95f9889673e1dc6a9059ed239764cde
attribution: "TÂCHES"
license: MIT
usage: referenced
- kind: github-file
repo: glittercowboy/taches-cc-resources
path: docs/meta-prompting.md
commit: 0d915b80b95f9889673e1dc6a9059ed239764cde
attribution: "TÂCHES"
license: MIT
usage: referenced
---
No comments yet. Be the first to comment!
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', ...
