taiyi-compress

SkillAI & models

TaiyiForge helper, Token compression orchestration: /taiyi:token compress + Superpowers subagent + ECC strategic-compact / handoff. Works with OpenCode / Claude / Codex / Cursor.

Use taiyi-compress in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add taiyi-compress and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the taiyi-compress skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

taiyi-compressStart free

What this skill tells your AI

The instructions your AI receives, as published by dong90/oh-my-taiyiforge in skills/taiyi-compress/SKILL.md and read by Ahel’s review.

目的

在 Token 接近预算或工件过大时,分层压缩上下文:先用引擎零 LLM 截断,再按需加载第三方 Skill 隔离/落盘会话。

何时使用

信号动作
/taiyi:status 出现 Token ⚠ 或压缩建议读本 Skill
工件 scan > compressThreshold(默认 120k)先 /taiyi:token compress
dev / 多 slice 并行Superpowers subagent / parallel
长会话 / 换窗口 / compaction 前/taiyi:handoff 或 ECC strategic-compact

策略(与 Superpowers 双线 harness 同级)

1. 引擎(首选 · 零 LLM Token)

用户说 /taiyi:token compress <slug>;Agent 代跑:

scripts/taiyi-forge.sh token compress <slug>

产出 .taiyi/changes/<slug>/CONTEXT-COMPACT.md。后续阶段优先读此文件,再按需打开单工件。

2. Superpowers(聊天 Skill · optional)

Skill用途
subagent-driven-development大实现拆 subagent,主会话只协调(省主窗 token)
dispatching-parallel-agents多 slice 并行,各 agent 不继承主会话历史

打卡(auto 模式 optional):

scripts/taiyi-forge.sh harness-check <slug> superpowers/subagent-driven-development

3. ECC / handoff(聊天 Skill · optional)

方式用途
ecc/strategic-compact战略级会话压缩
/taiyi:handoff写 HANDOFF.md,新会话续作
scripts/taiyi-forge.sh harness-check <slug> ecc/strategic-compact

推荐顺序

  1. /taiyi:token scan <slug> — 了解工件体量
  2. /taiyi:token compress <slug> — 引擎摘要
  3. 若仍超预算 / 进入 dev:加载 subagent-driven-development
  4. 会话结束前:/taiyi:handoff 或 ecc/strategic-compact
  5. /taiyi:token record <slug> <n> --phase <phase> --label "compress-flow"

配置

反模式

  • 在已超阈值时仍全量读 CHANGE…CHANGELOG 进聊天
  • 跳过 CONTEXT-COMPACT 重复 grep 全库
  • 主会话直接实现多个 TASK slice(应 subagent)
  • completed 变更不 archive、探针 slug 堆在 workspace(污染 /taiyi:list 与对话上下文)
  • 在聊天里跑全量 E2E / npm test / probe(日志灌上下文;应 CI 后台 + TEST.md 摘要)

Signals

GitHub stars
886
Forks
24
Last commit
Sep 2026
Advanced
Item type
skill
Key
taiyi-compress
Source
github.com/dong90/oh-my-taiyiforge