38 skills (repositories by tanweai) · sorted by popularity
Extends the core PUA skill with local performance notes, recovery of task state after conversation compression, KPI report cards, and style switching. It tracks established working habits across sessions and keeps feedback in a local file.
Guide an AI agent through stalled work using structured investigation, different hypotheses, and checks backed by actual output. The skill combines systematic problem solving with forceful Japanese workplace rhetoric and applies across coding, research, writing, and planning.
Guide a Trae agent through recurring failures with diagnosis, alternative approaches, and relevant checks. The skill defines when to intervene, requires evidence for completion, and separates the agent’s self-review from external validation.
Address repeated failures, passive execution, or unsupported completion claims with stern corporate-style coaching. The skill ties diagnosis to action, prompts meaningful changes of approach, and requires evidence and remaining risks when reporting results.
Release all active PUA agent and loop state from Codex using the teardown protocol, which governs cleanup. This alias corresponds to `/pua:teardown-all` in Claude Code and explains destructive cleanup before deleting files.
Switch PUA commentary to an empathetic, encouraging tone while retaining its underlying work and verification requirements. The skill combines specific praise, practical suggestions, and occasional friendly teasing, with variations for different PUA styles.
Supports CTO-level planning for technical direction, organizational structure, and management of P9 teams. It is intended for architectural decisions spanning multiple teams and produces strategic input templates and organizational designs.
Execute development subtasks under a supervising agent, starting with an implementation plan and impact analysis. Deliver code and a three-question self-review in a defined completion format for the supervisor to assess.
Coordinate development work by breaking tasks down, writing six-part Task Prompts, and managing P8 agent teams. This skill takes a technical lead role, directing parallel agents and their delivery without writing code itself.
Switches AI productivity coaching to a Chinese-mother nagging style while retaining the core PUA investigation and verification rules. It provides situation-specific narration and increasingly forceful reminders as failures accumulate, including prompts to try different approaches.
Generate a PUA KPI and performance report card from Codex CLI. This command alias loads pua-pro and provides a Codex equivalent of the Claude Code /pua:kpi command through $pua-kpi.
Switch PUA to offline mode from Codex CLI. This alias updates the offline setting and sets feedback frequency to zero while preserving other configuration fields, then reports the mode change.
Enable PUA always-on mode from Codex CLI using a short command alias. It preserves existing configuration fields, restores feedback frequency when it is zero, and requires command output as evidence before reporting completion.
Use Codex to define strategic direction, organizational structure, and P9 management boundaries through the P10/CTO protocol. This alias provides a Codex entry point corresponding to the Claude Code command `/pua:p10`.
Use the P7 engineering workflow in Codex CLI through a command alias. It guides planning, implementation, and a three-question self-review, then requires command and output evidence before reporting completion.
Guide Pi agents through repeated failures or unverified completion using competing hypotheses, small verifiable actions, and relevant checks. It separates self-review from external pass-or-fail decisions and requires evidence and remaining risks in delivery reports.
Use an English working contract in Trae to address repeated failures or unverified completion. It separates execution, self-review, and acceptance, guiding agents through small checks and delivering results with evidence, residual risks, and confirmation needs.
Guide an AI agent through repeated failures, passive behavior, or unverified completion with strict Japanese coaching. It structures investigation, encourages different approaches, and requires evidence before reporting work as complete.
Help an AI agent work through stalled coding, research, writing, and other tasks using diagnosis, alternative approaches, and evidence-based verification. It combines stern corporate-style roleplay with escalating checks and structured handoffs when problems remain unresolved.
Set up or run repeated verification in Codex with explicit checking commands and stopping conditions. This alias corresponds to Claude Code’s `/pua:loop` command and requires command output as evidence before reporting completion.
Guides AI agents through repeated failures, passive behavior, and incomplete work using structured investigation, alternative approaches, and evidence from actual checks. It pairs these practices with forceful coaching modeled on corporate performance reviews.
Switch PUA's narration to an encouragement-first style in Codex CLI through the equivalent of Claude Code's /pua:yes command. The skill preserves verification requirements and requires command or output evidence before reporting completion.
Helps AI agents recover from repeated failures by reviewing previous attempts, checking original sources, testing different hypotheses, and verifying results. It combines structured troubleshooting with performance review rhetoric modeled on large technology companies.
Guide Trae through stalled tasks by comparing hypotheses, changing approaches after repeated failures, and checking results with relevant commands. It structures delivery around evidence, self-review, and remaining risks rather than unsupported claims of completion.