tt-a1i

Use before starting any coding task when Superpowers is not present.

Use after completing a round of code generation.

Use before starting any coding task when Superpowers is not present.

Use after completing a round of code generation.

Use at the start of every session and before completing any coding task.

Use before declaring any coding task complete, done, or finished.

Use at the start of every session and before completing any coding task.

Ask which skill or flow fits your situation. A router over the skills in this repo.

Craft verifiable, tight goal prompts for AI coding agents (Claude Code /goal, Codex Automations, Pi), either from a standalone task interview or from an already-approved to-goal handoff. Use when the user says "给我一个 goal 提示词", "帮我写个 goal", "设置一个自动化任务", "我想让 agent 自动做 X", or asks to turn a task into a self-running loop. Ensures every goal has a checkable completion criterion so the agent knows when it's done.

Turn an approved spec, agent-ready ticket, tracker frontier, or partially implemented ticket into a verifiable execution goal without re-interviewing the user. Use after to-tickets or triage, before starting a fresh implementation session; use --all only for an explicitly requested cross-ticket goal.

Use when a user asks Claude Code to recommend, install, update, or inspect specialized coding subagents for Claude Code, Codex, OpenCode, or multiple targets in the current repository.

Use when a user asks Codex to recommend, install, update, or inspect specialized coding subagents for Claude Code, Codex, OpenCode, or multiple targets in the current repository.

Create polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, semantic navigation, optional trace motion, an optional 1200×630 Share Card PNG, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, approval or CI/CD flows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid. Prefer typed JSON IR renderers and deterministic validation; deliver static output by default, enable motion only when requested, and use optional post-commit opening only for an interactive local handoff.

Bridge Codex to web-based AI model products by packaging local task context, scrub-checking it, sending it through an approved browser surface to ChatGPT Pro, Claude, Grok, Gemini, or another web model, waiting for the answer, and returning the model response to the user or Codex. Also guide DevSpace-like MCP Connector Mode when the user wants ChatGPT Pro or another MCP-capable web host to access approved local workspaces without relying on Codex browser automation. Use when the user asks for GPT Pro, ChatGPT Pro, Claude web, Grok, Gemini web, web model bridge, external model consult, ask another model, second opinion, use a web AI model, browserless agent access to GPT Pro, MCP connector, DevSpace-like workflow, or send local repo context to a browser-based model for planning, review, debugging, architecture discussion, or implementation guidance.

Use this skill whenever the user asks to inspect, audit, review, assess, or evaluate a codebase/project for maintainability, extensibility, architecture, reliability, security, testing, engineering quality, or AI-agent/prompt/tooling risks. Also use this when invoked by `/inspect`. It performs a read-only, evidence-backed, multi-agent project inspection with complete file coverage, per-dimension scoring, blunt technical findings, and explicit degraded-mode disclosure.

Turn a Git repository URL or local path into one elegant, self-contained HTML learning page that teaches the project's value, architecture, and operating principles top-down with diagrams. Use when the user wants to understand, learn, onboard, explain, map, or study a repository.

在用户已经完成一次 implementation 工作后，把项目里的 implementation plan + git diff/log 渲染成一份单文件 HTML 实施报告。报告包含 TL;DR、风险概览、架构图（mermaid）、Before/After 数据流、决策记录卡片、风险清单。用于开会前快速对齐团队、向 reviewer 解释设计决策、归档实施叙事。当用户说"生成实施报告"、"impl-explain"、"explain implementation"、"展示这次实施方案"、"做一份 HTML 实施总结"时调用本 skill。

Orchestrate evidence-native demand research through the standalone idea-finder CLI. Use when a user asks Codex or another compatible agent to discover or investigate demand, inspect stored evidence, compare qualitative and quantitative signals, handle incomplete research, calibrate an Opportunity, plan or record validation work, or configure recurring monitoring.