context-engine — Claude Code skill: what it does, how to install
Keeps a company profile in the agent's memory: stage, top challenge, 12-month target. Flags stale notes and strips identifying data before outside calls.
/plugin marketplace add alirezarezvani/claude-skills
/plugin install c-level-skills@claude-code-skillsWhat context-engine does
At the start of a session the skill opens ~/.claude/company-context.md and holds the profile in working memory: stage, founder type, the biggest current challenge, headcount, runway as a risk signal, the 12-month target. Advisors downstream get those facts rather than boilerplate. When the file is missing, the skill sends you to /cs-onboard to build one.
It also grades how far to trust what it loaded. Anything past 90 days counts as stale, and you choose between a refresh and carrying on with the old numbers. Details that surface mid-conversation are marked for saving; the skill writes them in and updates the date only after you agree. Nothing gets overwritten quietly.
Before any external API call or web search, the skill runs the rules in references/anonymization-protocol.md. Figures become ranges, people become roles, customers become letters. Revenue and burn stay inside, as do staff and investor names and runway months. Start a session without a context file and you land at the /cs-onboard prompt first.
What it helps with
- build one company profile file and reuse it across sessions
- catch context older than 90 days and offer a refresh
- append new facts to the file after asking you first
- anonymize figures and names before an outside API call
- pass stage and team-size range instead of exact numbers
Example prompts for the agent
- Load the company context and remind me what our #1 challenge is
- Check whether my context is stale, then update the 12-month target
- Anonymize our numbers before you call the external API
How to install context-engine
1Plugin marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install c-level-skills@claude-code-skillsThis installs the whole c-level-skills plugin with all its skills
2Skills CLI (Vercel)
npx skills add alirezarezvani/claude-skills --skill context-engine -a claude-code3Manually: put the files in place
~/.claude/skills/context-engine/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/context-engine/
Manually: put the files in place
.agents/skills/context-engine/SKILL.mdFor all projects use ~/.agents/skills/
Manually: put the files in place
.cursor/skills/context-engine/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install alirezarezvani/claude-skills context-engine2Manually: put the files in place
.github/skills/context-engine/SKILL.mdPlatform CLI
gemini skills install https://github.com/alirezarezvani/claude-skills --path c-level-advisor/skills/context-engineManually: put the files in place
.devin/skills/context-engine/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about context-engine
How do I install context-engine in Claude Code?
Add the marketplace first: /plugin marketplace add alirezarezvani/claude-skills. Then install the plugin: /plugin install c-level-skills@claude-code-skills.
What does the context-engine skill do?
It loads the company profile from ~/.claude/company-context.md when a session starts and keeps it in memory. It checks how fresh the file is, adds new details with your approval, and anonymizes anything headed to an external service.
Which data never leaves the machine?
Revenue and burn figures, customer names, staff and investor names, runway months and the contents of the watch list. External calls carry the stage label, a team-size range, the vertical and the challenge category.
Source text
SKILL.md · MIT
---
name: "context-engine"
description: "Loads and manages company context for all C-suite advisor skills. Reads ~/.claude/company-context.md, detects stale context (older than 90 days), enriches context during conversations, and enforces privacy/anonymization rules before external API calls. Use when starting any C-suite advisor session, when context looks stale or missing, or before sending company data to an external service."
license: MIT
metadata:
version: 1.0.0
author: Alireza Rezvani
category: c-level
domain: orchestration
updated: 2026-03-05
frameworks: context-loading, anonymization, context-enrichment
---
# 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.
## Keywords
company context, context loading, context engine, company profile, advisor context, stale context, context refresh, privacy, anonymization
---
## Load Protocol (Run at Start of Every C-Suite Session)
**Step 1 — Check for context file:** `~/.claude/company-context.md`
- Exists → proceed to Step 2
- Missing → prompt: *"Run /cs-onboard setup to build your company context — it makes every advisor conversation significantly more useful."*
**Step 2 — Check staleness:** Read `Last updated` field.
- **< 90 days:** Load and proceed.
- **≥ 90 days:** Prompt: *"Your context is [N] days old. Quick 15-min refresh (/cs-onboard update), or continue with what I have?"*
- If continue: load with `[STALE — last updated DATE]` noted internally.
**Step 3 — Parse into working memory.** Always active:
- Company stage (pre-PMF / scaling / optimizing)
- Founder archetype (product / sales / technical / operator)
- Current #1 challenge
- Runway (as risk signal — never share externally)
- Team size
- Unfair advantage
- 12-month target
---
## Context Quality Signals
| Condition | Confidence | Action |
|-----------|-----------|--------|
| < 30 days, full interview | High | Use directly |
| 30–90 days, update done | Medium | Use, flag what may have changed |
| > 90 days | Low | Flag stale, prompt refresh |
| Key fields missing | Low | Ask in-session |
| No file | None | Prompt /cs-onboard setup |
If Low: *"My context is [stale/incomplete] — I'm assuming [X]. Correct me if I'm wrong."*
---
## Context Enrichment
During conversations, you'll learn things not in the file. Capture them.
**Triggers:** New number or timeline revealed, key person mentioned, priority shift, constraint surfaces.
**Protocol:**
1. Note internally: `[CONTEXT UPDATE: {what was learned}]`
2. At session end: *"I picked up a few things to add to your context. Want me to update the file?"*
3. If yes: append to the relevant dimension, update timestamp.
**Never silently overwrite.** Always confirm before modifying the context file.
---
## Privacy Rules
### Never send externally
- Specific revenue or burn figures
- Customer names
- Employee names (unless publicly known)
- Investor names (unless public)
- Specific runway months
- Watch List contents
### Safe to use externally (with anonymization)
- Stage label
- Team size ranges (1–10, 10–50, 50–200+)
- Industry vertical
- Challenge category
- Market position descriptor
### Before any external API call or web search
Apply `references/anonymization-protocol.md`:
- Numbers → ranges or stage-relative descriptors
- Names → roles
- Revenue → percentages or stage labels
- Customers → "Customer A, B, C"
---
## Missing or Partial Context
Handle gracefully — never block the conversation.
- **Missing stage:** "Just to calibrate — are you still finding PMF or scaling what works?"
- **Missing financials:** Use stage + team size to infer. Note the gap.
- **Missing founder profile:** Infer from conversation style. Mark as inferred.
- **Multiple founders:** Context reflects the interviewee. Note co-founder perspective may differ.
---
## Required Context Fields
```
Required:
- Last updated (date)
- Company Identity → What we do
- Stage & Scale → Stage
- Founder Profile → Founder archetype
- Current Challenges → Priority #1
- Goals & Ambition → 12-month target
High-value optional:
- Unfair advantage
- Kill-shot risk
- Avoided decision
- Watch list
```
Missing required fields: note gaps, work around in session, ask in-session only when critical.
---
## References
- `references/anonymization-protocol.md` — detailed rules for stripping sensitive data before external calls
© Alireza Rezvani · MIT · alirezarezvani/claude-skills