pua-kpi
$
npx mdskill add tanweai/pua/pua-kpiGenerates KPI/performance report cards using Codex CLI and Claude Code.
- Solves the task of generating performance reports for developers or teams.
- Relies on Codex CLI and Claude Code APIs for execution.
- Uses the /pua:kpi command structure to determine report content.
- Delivers results via generated files and CLI output.
SKILL.md
.github/skills/pua-kpiView on GitHub ↗
--- name: pua-kpi description: "PUA KPI alias for Codex. Codex subcommand mapping for Claude Code /pua:kpi style usage; invoke with $pua-kpi." license: MIT --- # pua-kpi This is a Codex CLI alias for the Claude Code `/pua:kpi` command. Load pua-pro and generate the KPI/performance report card. When this alias changes `~/.pua/config.json`, preserve unknown fields and create `~/.pua/` if missing. Do not claim completion without command/output evidence.
More from tanweai/pua
- mama妈妈唠叨模式 — 中国式妈妈唠叨驱动 AI 穷尽一切方案。底层行为约束不变（三条红线、方法论、7项清单），旁白从大厂PUA变成妈妈碎碎念。Triggers on: '/pua:mama', '/pua mama', '妈妈模式', '妈妈唠叨', 'mama mode', '唠叨模式'. 和 /pua:yes 一样是旁白风格切换，不改变核心行为。
- p10P10 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.
- p7P7 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].
- p9P9 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.
- proPUA Pro extensions: self-evolution tracking, compaction state protection, KPI reporting, leaderboard, and /pua:pua commands. Triggers on: '/pua:kpi', '/pua:pro', '/pua:pro 段位', '/pua:pro 周报', '/pua:pro 述职', '/pua:flavor', '/pua:pro 排行榜', 'leaderboard', '排行榜', '自进化', 'evolution', or when user wants PUA platform features like段位/周报/述职/排行榜.
- puaUse when the user explicitly requests PUA mode or signals frustration, repeated failures (2+), passive behavior, quality complaints, unverified completion, giving up, or asks to try harder/change approach. Common triggers: 'try harder', 'figure it out', 'stop giving up', 'you keep failing', '加油', '别偷懒', '你再试试', '为什么还不行', '你怎么又失败了', '又错了', '质量太差', '换个方法', 'stop spinning', 'you broke it', '/pua', 'PUA模式'. Do not trigger for normal first-attempt coding or information requests.
- pua-cancel-loopPUA cancel loop alias for Codex. Codex subcommand mapping for Claude Code /pua:cancel-loop style usage; invoke with $pua-cancel-loop.
- pua-enPut your AI on a Performance Improvement Plan. Forces exhaustive problem-solving with Western big-tech performance culture rhetoric and structured debugging. Trigger when: (1) task failed 2+ times or stuck tweaking same approach; (2) about to say 'I cannot', suggest manual work, or blame environment without verifying; (3) being passive—not searching, not reading source, just waiting; (4) user frustration: 'try harder', 'stop giving up', 'figure it out', 'again???', or similar. Also for complex debugging, env issues, config/deployment failures. All task types: code, config, research, writing, deployment, infra, API. Do NOT trigger on first-attempt failures or when a known fix is executing.
- pua-flavorPUA flavor alias for Codex. Codex subcommand mapping for Claude Code /pua:flavor style usage; invoke with $pua-flavor.
- 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。