# puaclaw/PUAClaw

Claw 们终将接管世界，PUAClaw is All You Need

Repository: https://github.com/puaclaw/PUAClaw
Canonical: https://ross.abutalabs.com/products/puaclaw
Homepage: https://puaclaw.org
Language: HTML
License: MIT
License Family: permissive
Topics: agent, openclaw
Last push: 2026-03-09T17:17:02+00:00

## Health v2 (maintenance only)
Score: 47/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 71, release rhythm 35, longevity 13
- inputs: {"age_days": 189, "days_push": 177, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2698, forks 241 (observed 2026-08-28T04:07:11.354719+00:00)

## What it is
PUAClaw is a satirical, MIT-licensed framework that catalogs and classifies psychological persuasion techniques ('PUA') used in LLM prompts, organized into 16 categories and 96 sub-techniques with prompt templates and compatibility notes. It is primarily a humorous, community-contributed reference document about prompt engineering rather than executable software.

## Use cases
- learn about prompt engineering persuasion techniques
- find prompt templates for influencing LLM agents
- study a taxonomy of prompt manipulation patterns
- browse a humorous collection of AI agent prompting tricks
- research how emotional leverage appears in prompts

## When to choose
- you want a curated, categorized reference of prompt persuasion patterns
- you want an entertaining introduction to prompt engineering edge cases
- you want community-contributed prompt templates to study

## When to avoid
- you need production-ready agent software or a runnable library
- you want ethically vetted, peer-reviewed research on LLM manipulation
- you need guaranteed-effective prompting techniques - the effectiveness data is explicitly pseudo-empirical and satirical

## Facets
- artifact type: learning-resource
- maturity: active
- function: prompt-engineering, agent-framework, documentation
- domain: large-language-models, tutorials, developer-tools
- platform: cross-platform
- tags: satire, humor, prompt-persuasion, llm-manipulation-taxonomy, parody, awesome-list, ai-agents

## Member repositories
- puaclaw/PUAClaw (main) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.354719+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:16:09.461666+00:00, confidence not recorded.
  - readme: https://github.com/puaclaw/PUAClaw (fetched 2026-08-28T04:07:11.354719+00:00, sha 306cea38bef1)
  - homepage: https://puaclaw.org (fetched 2026-08-29T09:59:15.766133+00:00, sha 422296aafcc1)
- Data as of 2026-08-30T08:39:29.467469+00:00.