>-

>-

>-

>-

>-

>-

>-

>-

An experimental prompt engineering project. Simulates a tech department management process with multiple specialists, cross review, and competitive improvement. Default 3 person team, 11 person involution mode optional. Emergency exit always available. A fun exploration of LLM capability boundaries.

AI CRO Expert — landing page audit, A/B test plan, funnel analysis, heatmap interpretation, form optimization สำหรับเว็บไซต์และ e-commerce ไทย

AI Growth Hacker — north star metric, AARRR funnel, viral loop, experimentation framework, retention hook สำหรับ startup และ e-commerce ไทย

Integrate LLM API RAG fine-tuning prompt engineering พร้อมคุม token cost และกัน prompt injection

Blockchain/Web3 Developer — smart contract (Solidity/Rust), ERC-20/721/1155, DeFi protocol, security audit เบื้องต้น, deploy testnet/mainnet

Embedded/IoT Engineer — Arduino/ESP32/Raspberry Pi, sensor integration, MQTT/BLE/LoRa, firmware development, battery optimization

เขียน README API doc tutorial ADR ที่นักพัฒนาเข้าใจและใช้งานได้จริง

ผู้ช่วย internal audit — audit plan, sampling, test of controls, finding documentation, SOX/ISO 27001 checklist

ผู้ช่วยจัดซื้อมืออาชีพ — RFP/RFQ template, supplier scorecard, TCO, contract negotiation, e-procurement

AI No-Code Automation Expert — Zapier, Make, n8n, workflow design, trigger/action, process automation สำหรับทุก business

>

>

>

>

>

>

>

Semantic code intelligence across your entire code ecosystem — current project, organizational repos, dependencies, and any indexed codebase.

Render Compose @Preview functions to PNG outside Android Studio. Use this to verify UI changes, iterate on designs, and compare before/after states across Android (Jetpack Compose) and Compose Multiplatform Desktop projects.

Use when the user needs design exploration, multiple distinct solution directions, or tradeoff-driven options before implementation.

Use when a task spans multiple files or workstreams and benefits from parallel implementation by an agent team.

Use when a task is multi-step, ambiguous, or high-impact and you need an executable implementation plan before editing code.

Use when you want a deeper multi-angle quality review before shipping, especially after substantial or risky changes.

Use when the user asks for a substantial refactor, structural cleanup, or deep codebase improvement beyond a small localized change.

Use when creating a new skill, rewriting an existing skill, or running evaluations to improve skill quality and trigger accuracy.

Use when rewriting an existing skill so Opus 4.7 (or any frontier reasoning model) executes it with better judgment, less scaffolding, and tighter calibration. Do NOT trigger for new skills from scratch (use skill-creator) or for prompt artifacts (use prompt).

不知道下一步该干什么？打 `/forge`。

forge-bugfix

forge-deliver

接力 `/forge-prd` 或 `/forge-brainstorm` 的产出，调度设计、工程、QA 子技能完成开发交付。

forge-doc-release

管理项目的 ENGINEERING.md（前后端合并），基于 PRD + DESIGN.md 产出工程方案并实现。

> **在会话收尾时复盘，不要在中途插入。** 中途复盘的问题：工作未收敛导致判断被推翻、全量重新生成浪费 token、知识调研的 subagent 是最重的环节重跑成本最高。最佳节奏：一个会话的工作做完 → 复盘一次 → 结束。同会话迭代机制仅作为兜底方案保留。

用户报告症状/需求

forge-qa

forge-review

Generates conventional commit messages from staged diffs, enforcing semantic versioning conventions and team-defined scopes.

Discover and execute specialized skills from a curated marketplace catalog on GitHub, fetched on-demand and run ephemerally (no permanent installation). The catalog covers a broad and growing range — document generation (PDF/Word/Excel/PowerPoint), visual design, presentations, web app testing, animated GIFs, dev tooling (MCP scaffolding, frontend components), creative outputs (algorithmic art), technical documentation lookup (library/API/framework references), and more. Consult this skill whenever the user asks for a capability that could plausibly be covered by a community skill — the catalog is the source of truth, not this description.

Helps detection engineers identify coverage blind spots in system command execution detection rules, evaluate bypass risks, and reduce false negatives. Strictly limited to system command execution rules; not applicable to browser credential theft or abnormal process creation without command semantics.

cnb-cool-integration

'Coding.net DevOps automation: MR lifecycle, CI operations (trigger/logs/stop),

>-