跳到正文
cccskills
免费在 GitHub 公开

context-engine

Loads and manages company context for all C-suite advisor skills. Reads company-context.md, detects stale context, enriches context during conversations, and enforces privacy/anonymization rules.

中文简介正在准备中。当前显示原文说明。

SebastianLuser/claude-code-arcane星标 3(GitHub 3 + cccskills 0)

实测评分 未实测

查看安装方法

包含的文件(2)

  • SKILL.md1.9 KB
  • references/anonymization-protocol.md5.6 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Company Context Engine

The memory layer for C-suite advisors. Every advisor skill loads this first. Context is what turns generic advice into specific insight.

Load Protocol (Every C-Suite Session)

  1. Check for context file: ~/.claude/company-context.md — missing → prompt /cs:setup
  2. Check staleness: < 90 days → load. >= 90 days → prompt refresh or continue with stale flag.
  3. Parse into working memory: Stage, founder archetype, current #1 challenge, runway, team size, unfair advantage, 12-month target.

Context Quality Signals

ConditionConfidenceAction
< 30 days, full interviewHighUse directly
30-90 daysMediumUse, flag what may have changed
> 90 daysLowFlag stale, prompt refresh
Key fields missingLowAsk in-session
No fileNonePrompt /cs:setup

Context Enrichment

During conversations, capture new information. At session end: confirm before updating. Never silently overwrite.

Privacy Rules

Never send externally: Specific revenue, customer names, employee names, investor names, runway months.

Safe externally (with anonymization): Stage label, team size ranges, industry vertical, challenge category.

Required Context Fields

Required:
  - Last updated, Company Identity, Stage, Founder archetype, Priority #1, 12-month target
High-value optional:
  - Unfair advantage, Kill-shot risk, Avoided decision, Watch list

Resources

  • references/anonymization-protocol.md — rules for stripping sensitive data before external calls

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Plan, design, and implement A/B tests and experiments with statistical rigor. Covers hypothesis frameworks, sample sizing, metrics, and result analysis.

中文简介正在准备中。当前显示原文说明。

SebastianLuser/claude-code-arcane32026年10月27日 更新

Web/mobile accessibility decision guide: WCAG 2.2 AA, ARIA, keyboard nav, focus management, contrast, testing. Use for: a11y, accessibility, wcag, aria, screen reader, keyboard, contrast.

中文简介正在准备中。当前显示原文说明。

SebastianLuser/claude-code-arcane32026年10月27日 更新

Generate, iterate, and scale ad creative for paid advertising across Google, Meta, LinkedIn, and X. Covers platform specs, creative frameworks, and quality validation.

中文简介正在准备中。当前显示原文说明。

SebastianLuser/claude-code-arcane32026年10月27日 更新

Musica interactiva para juegos: layering vertical, re-secuenciacion horizontal, stingers, reglas de transicion con sync points, y mapeo de estados de gameplay a musica. Usar para: musica adaptativa, sistema de musica dinamica, transiciones musicales, combat music.

中文简介正在准备中。当前显示原文说明。

SebastianLuser/claude-code-arcane32026年10月27日 更新

Design multi-agent systems, create agent architectures, define communication patterns, and build autonomous agent workflows with structured evaluation frameworks.

中文简介正在准备中。当前显示原文说明。

SebastianLuser/claude-code-arcane32026年10月27日 更新

Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, response formats, and quality loops.

中文简介正在准备中。当前显示原文说明。

SebastianLuser/claude-code-arcane32026年10月27日 更新

查看 SebastianLuser 的全部技能

报告此技能的问题