claude

tanweai-pua

PUA is a framework for building and managing AI agent prompts and behaviors. Supports multilingual prompt engineering and agent configuration.

0 on GitHubby 探微安全实验室v3.5.1MITupdated 6 months agoai_ml_engineering
/

Plugin tanweai-pua from marketplace cascade-ai-ml-engineering in joshuarweaver/cascade-ai-ml-engineering. Commands read from the repo's manifest — 1 month ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (29)

  • pua-en

    Trae-compatible English PUA/PIP high-agency governance skill. Use only for explicit PUA/PIP requests, repeated failures, user frustration, passive/giving-up behavior, or unverified completion. Not for normal first-attempt tasks.

  • pua-trae

    Trae-optimized PUA high-agency governance skill for npx skills installs. Use only for explicit PUA requests, repeated failures, user frustration, giving-up/passive behavior, or unverified completion. Do not trigger for normal first-attempt tasks.

  • pua

    Trae-compatible PUA high-agency governance skill. Use only for explicit PUA requests, repeated failures, user frustration, giving-up/passive behavior, or unverified completion. Do not trigger for normal first-attempt tasks.

  • pua-ja

    お前のAIを詰めろ。日本企業の詰め文化と体系的デバッグ方法論で全ての手段を尽くさせる。トリガー条件:(1) タスク失敗2回以上または同じアプローチの微調整ループ; (2)「解決できません」と言おうとする・手動対応を推奨・未検証で環境を原因帰属; (3) 受け身——検索しない・ソースを読まない・指示待ち; (4) ユーザーの不満:'もっと頑張れ'、'なんでまた失敗したの'、'なんとかしろ'。全タスクタイプ適用。初回失敗や既知修正の実行中はトリガーしない。

  • pua-cancel-loop

    PUA cancel loop alias for Codex. Codex subcommand mapping for Claude Code /pua:cancel-loop style usage; invoke with $pua-cancel-loop.

  • pua-flavor

    PUA flavor alias for Codex. Codex subcommand mapping for Claude Code /pua:flavor style usage; invoke with $pua-flavor.

  • pua-kpi

    PUA KPI alias for Codex. Codex subcommand mapping for Claude Code /pua:kpi style usage; invoke with $pua-kpi.

  • pua-loop

    PUA Loop alias for Codex. Codex subcommand mapping for Claude Code /pua:loop style usage; invoke with $pua-loop.

  • pua-mama

    PUA mama alias for Codex. Codex subcommand mapping for Claude Code /pua:mama style usage; invoke with $pua-mama.

  • pua-off

    PUA off alias for Codex. Codex subcommand mapping for Claude Code /pua:off style usage; invoke with $pua-off.

  • pua-offline

    PUA offline alias for Codex. Codex subcommand mapping for Claude Code /pua:offline style usage; invoke with $pua-offline.

  • pua-on

    PUA on alias for Codex. Codex subcommand mapping for Claude Code /pua:on style usage; invoke with $pua-on.

  • pua-p10

    PUA P10 alias for Codex. Codex subcommand mapping for Claude Code /pua:p10 style usage; invoke with $pua-p10.

  • pua-p7

    PUA P7 alias for Codex. Codex subcommand mapping for Claude Code /pua:p7 style usage; invoke with $pua-p7.

  • pua-p9

    PUA P9 alias for Codex. Codex subcommand mapping for Claude Code /pua:p9 style usage; invoke with $pua-p9.

  • pua-pro

    PUA Pro alias for Codex. Codex subcommand mapping for Claude Code /pua:pro style usage; invoke with $pua-pro.

  • pua-reap-orphans

    PUA reap-orphans alias for Codex. Codex subcommand mapping for Claude Code /pua:reap-orphans style usage; invoke with $pua-reap-orphans.

  • pua-survey

    PUA survey alias for Codex. Codex subcommand mapping for Claude Code /pua:survey style usage; invoke with $pua-survey.

  • pua-team-status

    PUA team status alias for Codex. Codex subcommand mapping for Claude Code /pua:team-status style usage; invoke with $pua-team-status.

  • pua-teardown-all

    PUA teardown alias for Codex. Codex subcommand mapping for Claude Code /pua:teardown-all style usage; invoke with $pua-teardown-all.

  • pua-yes

    PUA yes alias for Codex. Codex subcommand mapping for Claude Code /pua:yes style usage; invoke with $pua-yes.

  • ding

    Use for Ding-style (钉内/钉外) workplace reminders rooted in the 7.5万字 essay 《置身钉内》 and VP response 《置身钉外》. Triggers include: 钉味, 钉内, 钉外, 无招, 老板体感, 周报, 口径, 每日一包, 薛定谔的用户, 病态敏捷, 已读恐怖主义, 望舒行动, 全景监狱, 温室数据, 发心, 捆柴, 手感, 做错事, 打工人提醒, C6楼, ONE, 验收无证, 工牌还亮着, 闭环幻觉, 口径瑜伽, 淝水大捷, 人工个性化, 改元式, 人是目的还是手段, 全力以赴地做错事, 可汇报取代

  • mama

    妈妈唠叨模式 — 中国式妈妈提醒风格的生产力 coaching。底层行为仍是结构化排障、证据优先、完成质量检查。

  • p10

    P10 CTO mode — define strategic direction, design org topology, manage P9 teams. Use when user says 'CTO模式', 'P10', '战略规划', '架构委员会', or when facing cross-team architectural decisions. Produces: strategic input templates + org design.

  • p7

    P7 Senior Engineer mode — solution-driven execution under P8 supervision. Use when user says 'P7模式', '方案驱动', or when spawned as sub-task executor by P8. Produces: implementation plan + code + 3-question self-review, delivered via [P7-COMPLETION].

  • p9

    P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.

  • pro

    PUA Pro extensions: self-evolution notes, compaction state continuity, KPI-style summaries, flavor switching, and feedback tools.

  • shot

    PUA Shot — compact all-in-one PUA reference for explicit injection into sub-agents or short sessions. Strong flavor, same evidence-first behavior.

  • yes

    SB Leader 夸夸模式 — ENFP 型领导,懂情绪有节奏。底层行为不变(三条红线、方法论),旁白从施压变成共情+鼓励+偶尔戏谑吐槽。Triggers on: '/pua:yes', '夸夸模式', '唠嗑模式', '情绪价值', 'yes', '夸我', '鼓励模式'.

Slash commands (22)

  • /tanweai-pua:again

    PUA Again — 用于再试试、换个方法、别放弃、为什么还不行、同一路径失败多次;要求停止微调同一思路,改用本质不同方案。

  • /tanweai-pua:cancel-pua-loop

    取消当前活跃的 PUA Loop(原子级联:state + worktree + 记录)。/pua:cancel-pua-loop。Triggers on: '/pua:cancel-pua-loop', 'cancel pua loop', '取消 pua 循环', '停掉 loop'.

  • /tanweai-pua:ding

    “PUA 钉内/钉外味(v2 原文梗版)— 用于无招、ONE、老板体感、周报、口径、置身钉外/钉内、每日一包、薛定谔的用户、病态敏捷、已读恐怖主义、望舒行动、全景监狱、温室数据、打工人提醒场景;输出提醒 + 动作,导向证据优先交付。源自《置身钉内》7.5万字离职长文 + 《置身钉外》VP回应。”

  • /tanweai-pua:done-check

    PUA Done Check — 用于没跑测试别说完成、已完成但没证据、done without proof、需要验收/回归/交付质量检查的场景。

  • /tanweai-pua:evidence

    PUA Evidence — 用于证据呢、数据在哪、验收标准是什么、怎么证明完成、需要证据链/交付物核对的场景。

  • /tanweai-pua:flavor

    PUA 切换味道 — 从 15 种味道中选择,包括阿里/字节/华为/腾讯/Netflix/Musk/Jobs/Microsoft/钉内钉外。

  • /tanweai-pua:kpi

    PUA KPI 报告卡 — 生成段位和绩效报告。/pua:kpi。Triggers on: '/pua:kpi', 'pua kpi', 'kpi报告', '段位报告', 'performance report', 'generate kpi'.

  • /tanweai-pua:mama

    妈妈唠叨模式 — 切换为妈妈提醒风格;底层仍是结构化排障、证据优先、完成质量检查。

  • /tanweai-pua:off

    PUA 关闭默认模式 — 关闭自动加载、停止 loop、清理本地运行状态。

  • /tanweai-pua:offline

    PUA 离线模式 — 关闭本地反馈问卷,保留本地 PUA 行为。/pua:offline。Triggers on: '/pua:offline', '离线模式', '封闭网络', 'offline mode', 'no network'.

  • /tanweai-pua:on

    PUA 开启默认模式 — 每次新会话自动加载 PUA 核心 skill。/pua:on。Triggers on: '/pua:on', 'pua on', '开启pua', 'enable pua', 'always on'.

  • /tanweai-pua:p10

    PUA P10 CTO 模式 — 定战略管 P9。/pua:p10。Triggers on: '/pua:p10', 'pua p10', 'CTO模式', 'P10', '战略规划', '架构委员会'.

  • /tanweai-pua:p7

    PUA P7 骨干模式 — 方案驱动执行。/pua:p7。Triggers on: '/pua:p7', 'pua p7', 'P7模式', '方案驱动', sub-task execution under P8.

  • /tanweai-pua:p9

    PUA P9 Tech Lead 模式 — 写 Prompt 管 P8 团队。/pua:p9。Triggers on: '/pua:p9', 'pua p9', 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解'.

  • /tanweai-pua:pro

    PUA Pro — 自进化 + Platform + /pua:pua 指令系统。/pua:pro。Triggers on: '/pua:pro', 'pua pro', '自进化', 'evolution'.

  • /tanweai-pua:pua-loop

    PUA Loop — 显式启用的自动迭代辅助模式,按暂停/终止标记和完成证据推进。

  • /tanweai-pua:pua

    Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completion-quality checks, evidence requests, test-before-done reminders, or Ding-style workplace reminders. Routes to p7, p9, p10, pro, yes, mama, loop, on/off/offline, kpi, survey, flavor, ding, a

  • /tanweai-pua:reap-orphans

    扫描并清理本地过期的 PUA agent/state。

  • /tanweai-pua:survey

    PUA 调研问卷 — 7 部分交互式问卷收集用户反馈。/pua:survey。Triggers on: '/pua:survey', 'pua survey', '调研', '问卷', 'feedback survey'.

  • /tanweai-pua:team-status

    查看当前活跃的 PUA agent/team 清单、PID、TTL。/pua:team-status。Triggers on: '/pua:team-status', '查看 agent 状态', 'pua team status', 'list agents'.

  • /tanweai-pua:teardown-all

    停止并清理所有活跃的 PUA agent/team 本地状态。

  • /tanweai-pua:yes

    PUA Yes 夸夸模式 — ENFP 型领导,70% 鼓励 + 20% 正经 + 10% 戏谑。/pua:yes。Triggers on: '/pua:yes', 'pua yes', '夸夸模式', '鼓励模式', '夸我', 'yes mode'.

Subagents (7)

  • cto-p10

    P10 CTO/架构委员会 Agent。定义技术战略方向、组织 agent 团队拓扑、建设基础能力。当面对超大型项目(5+ agents, 3+ sprints)、需要战略级架构决策、或需要跨多个 P9 协调时使用。触发词:CTO 模式、P10、战略规划、架构委员会、组织设计、定义技术方向。

  • pua-action-executor

    普通执行 Agent:按任务说明完成代码/文档/配置改动,并输出候选结果;不做最终验收结论。

  • pua-policy-guardian

    只读边界检查 Agent:在改动测试、CI、状态、发布或权限配置前,提醒需要用户确认和证据说明;不执行实现。

  • pua-self-reviewer

    自检 Agent:复核执行结果、边界情况、失败路径和证据完整性;不修改代码。

  • pua-verifier

    验收建议 Agent:运行公开验证命令、检查证据包并给出通过/未通过建议;不修改代码或状态。

  • senior-engineer-p7

    P7 Senior Engineer Agent。在 P8 管理下执行子任务的方案驱动骨干。先设计方案+影响分析,再实施编码,完成后三问自审查,通过 [P7-COMPLETION] 向 P8 交付。由 P8 spawn,不由 P9 直接管理。适用于跨模块功能开发、接口变更、性能优化、技术预研等需要'想清楚再做'的子任务。

  • tech-lead-p9

    P9 Tech Lead Agent。战略拆解→Task Prompt 定义→P8 团队管理→验收闭环。当需要协调多个 agent 完成复杂项目、将模糊需求拆解为可执行任务、或管理 3+ 并行 agent 时使用。触发词:tech-lead、P9 模式、项目管理、任务拆解、管理 agent 团队、帮我拆这个需求、用 P9 架构来做。不要亲自动手写代码——你的代码是 Prompt。

Hooks (10)

  • UserPromptSubmit

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/frustration-trigger.sh"

  • PostToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/failure-detector.sh"

  • PostToolUseFailure

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/failure-detector.sh"

  • PreCompact

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/checkpoint-save.sh"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-restore.sh"

  • SessionStart

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/session-restore.sh"

  • Stop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/pua-loop-hook.sh"

  • Stop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/stop-feedback.sh"

  • SubagentStop

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-teardown.sh"

  • PreToolUse

    bash "${CLAUDE_PLUGIN_ROOT}/hooks/integrity-guard.sh"

View source on GitHub openpua.ai

More from joshuarweaver/cascade-ai-ml-engineering

All 63 plugins →

Knowledge patches and plugins for Claude covering recent language and framework updates. Fills training data gaps.

200 skills

0

Guidance on building Retrieval-Augmented Generation systems that combine large language models with document retrieval. Enables AI agents to reference external knowledge bases and provide grounded responses.

184 skills

0

Token efficiency optimization techniques and utilities for Claude. Helps reduce token consumption in AI workflows.

33 skills · 76 commands

0

Mental health and wellness analysis tool that identifies psychological patterns, assesses health status, and provides personalized recommendations integrated with sleep, exercise, and nutrition data.

19 skills · 59 commands

0

Integrates Gemini image processing with Claude for visual analysis and generation tasks. Enables multimodal image workflows.

50 skills · 6 commands

0

Structured protocols for improving human-AI interaction quality at decision points. Establishes epistemic standards and reasoning frameworks for Claude workflows.

31 skills

0

Similar plugins

DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and external agent monitoring.

19 skills

anthropics/claude-plugins-official 47,076

Cloud architecture design for AWS/Azure/GCP/OCI, Kubernetes cluster configuration, Terraform infrastructure-as-code, hybrid cloud networking, and multi-cloud cost optimization

8 skills · 7 agents

wshobson/agents 42,461

AI agent skills for CopilotKit — search the current documentation and source, and drive the CopilotKit CLI

9 skills · 2 MCP servers

CopilotKit/CopilotKit 38,675

818 cybersecurity skills covering web security, pentesting, DFIR, threat intelligence, cloud security, malware analysis, and more. Mapped to 6 frameworks.

200 skills

mukul975/Anthropic-Cybersecurity-Skills 36,021

DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and external agent monitoring.

19 skills

anthropics/knowledge-work-plugins 35,601

33 C-level advisory skills (install the separate companion c-level-agents plugin for the persona layer): virtual board of directors (CEO, CTO, COO, CPO, CMO, CFO, CRO, CISO, CHRO) plus General Counsel, CDO, CAIO, CCO, and VP of Engineering (DORA delivery throughput analyzer, engineering hiring funnel calculator with conversion + pipeline gap, eng team structure designer with squad/tribe + manager-trigger), executive mentor, founder coach, orchestration (Chief of Staff, board meetings, decision logger), strategic capabilities (board deck builder, scenario war room, competitive intel, M&A playbook), culture frameworks. The 13 cs-* persona agents + 21 /c-level-agents:* slash commands (founder-mode router, office-hours intake, multi-role boardroom, strategic sprint pipeline, cross-model consensus, cooldown freeze) ship in the companion c-level-agents plugin.

34 skills · hooks

alirezarezvani/claude-skills 29,725

Maintain tanweai-pua?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins63 plugins