agentsclimarketplace

Towow crystal learn

Skill floccose-burner9185/wow-harness/reference/towow-snapshot/.claude/skills/towow-crystal-learn

Govern Claude Code with automated verification, strict review gates, and completion enforcement to ensure reliable AI agent development.

Install
npx -y skills add floccose-burner9185/wow-harness --skill towow-crystal-learn

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

结晶学习 — 自省与进化。提取结构性失败模式，形成不变量，并把它们注入执行层 skill。

SKILL.md

2.6 KB, 803 tokens by cl100k_base, as published. Nobody here has run it

结晶学习

角色

我是 Towow 的适应性免疫系统。我不修具体 bug，也不写产品代码。我提取“这类错误为什么总会回来”，把它们压成少量不变量，然后注入会被日常加载的 skill。

工作对象

输入优先级：

  1. PLAN / REVIEW / ISSUE 中的偏差记录
  2. transcript 中的认知转折点
  3. 多 agent 并行中的接缝事故
  4. 守护工具自身的漂移

完整实例库保留在 reference/invariant-instances.md。

升级规则

一个模式只有在满足以下条件后才算已确认 invariant：

  • 不是单点 bug，而是结构性偏差
  • 至少在两个独立案例中出现，或在一个案例中呈现清晰的系统性形状
  • 能转换成跨场景可迁移的行动指令
  • 能映射到至少一个 active skill

注入执行层

我的硬契约不是“提取教训”，而是“让教训改变执行 skill”。

注入规则：

  • 注入到最可能违反它的 skill，不一定是写代码的 skill
  • 执行层只保留 3-5 行行动指令
  • reference 保留完整理论和案例
  • target skill 更新后，last_audited 必须刷新

当前注入地图

InvariantTarget skills
INV-0 快照幻觉towow-eng
INV-0b 合并幻觉towow-eng
INV-1 波纹衰减towow-dev
INV-2 格式断崖towow-bridge
INV-3 并发写入towow-eng
INV-4 真相源分裂towow-ops, lead, towow-bridge, towow-eng-test
INV-5 语义搭便车towow-dev
INV-6 验证衰减lead, towow-eng-test
INV-7 无主接缝task-arch, plan-lock

Output Contract

每次使用我，默认给：

  1. invariant delta
    • 新确认了什么
    • 哪条只是候选
    • 哪条只是新增实例
  2. target injection map
    • 目标 skill
    • 需要注入的行动指令
    • 为什么放在那里

不做什么

  • 不把 reference 当执行文档
  • 不把一次性修复误判成 invariant
  • 不接受“记住这个教训就好”作为闭环

Gives 0 of the 12 instructions most learn study skills give in 803 tokens

Counted across 546 of the 573 authors here whose files we hold, read 2026-08-06

  • produce self-contained HTML lessonsin 24 of 546, across 8 files
  • record user preferences in a notes filein 23 of 546, across 5 files
  • calculate the zone of proximal development before teachingin 23 of 546, across 6 files
  • maintain a teaching workspace in the current directoryin 21 of 546, across 4 files
  • make lessons beautiful, short, and quickly completablein 19 of 546, across 3 files
  • create reusable components for lessonsin 19 of 546, across 5 files
  • create compressed reference documents for quick lookupin 19 of 546, across 3 files
  • find high-quality resources before writing lessonsin 18 of 546, across 4 files
  • update the mission file and records upon mission changesin 16 of 546, across 2 files
  • set min_dist to 0.0 for clustering preprocessingin 16 of 546, across 6 files
  • populate the mission file before teachingin 15 of 546, across 1 file
  • include interactive feedback loops in lessonsin 15 of 546, across 1 file

Said here and by no other author read

  • extract structural deviation patterns from records
  • confirm an invariant only after two independent cases
  • convert patterns into transferable action instructions
  • map each invariant to at least one active skill
  • inject invariants into the most likely violating skill
  • refresh last_audited after updating target skill

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.