context-engine

$npx mdskill add alirezarezvani/claude-skills/context-engine

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

SKILL.md

.github/skills/context-engineView on GitHub ↗
---
name: "context-engine"
description: "Use when starting a C-suite advisor session, when company context is missing or older than 90 days, or before company data goes to an external service. Loads and enriches ~/.claude/company-context.md and applies anonymization rules."
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

More from alirezarezvani/claude-skills

SkillDescription
a11y-auditUse for any accessibility audit or a11y fix (WCAG 2.2 A/AA, color contrast, compliance report, CI check) in React, Next.js, Vue, Angular, Svelte or HTML. Scans with a11y_scanner.py and checks contrast with contrast_checker.py, then fixes and re-verifies.
ab-test-setupUse before planning or launching any A/B, split or multivariate test, or when asked if a result is significant. Sizes the test with sample_size_calculator.py and writes the hypothesis, metric and stop rule first, so it is not called early on noise.
access-lifecycleUse when preparing or running a user access review, checking that leavers lost their access, finding orphaned or ownerless service accounts, answering an auditor's access-control request for SOC 2, ISO 27001, PCI DSS, HIPAA or NIST 800-53, or checking whether a finished review campaign will hold up. Diffs the HR roster against account exports, tests the campaign for coverage, self-review, unremoved revokes and rubber-stamping, and maps every exception to the controls it breaks.
ad-creativeUse for any ad copy request (RSA headlines, Meta, LinkedIn or TikTok ads, bulk variations), before writing. Checks every line against platform character limits and policy with ad_copy_validator.py. Campaign strategy and budgets: paid-ads.
adversarial-reviewerTough, critical review of a diff or PR before merge, through hostile reviewer personas that catch shared blind spots. Use whenever the user wants a change torn apart, a harsh second opinion, or a self-review felt too agreeable.
aeoUse when content should be cited by ChatGPT, Perplexity, Claude or Gemini (answer engine optimization), before rewriting it. Scores E-E-A-T and structure with aeo_audit.py, rewrites with aeo_optimizer.py and logs citations with citation_tracker.py.
agent-decision-receiptsUse when an autonomous agent takes a side-effecting action (deploy, delete, pay, grant access) that may need proving later, or for EU AI Act Art. 12 record-keeping. Builds a tamper-evident signed receipt with build_action_manifest.py and verifies it.
agent-designerDesign multi-agent systems (supervisor, swarm, pipeline) and tool schemas; find bottlenecks in run logs. Use whenever agents split work or a run is slow or costly. Not for Claude Code workflow files (workflow-builder).
agent-harnessUse when an agent should drive a goal in one of this repo's domains to a verified close, before starting the work. Compiles the goal into a task plan with goal_compiler.py and runs it through loop_controller.py, which verifies each task, caps retries and escalates.
agent-launcher-orchestratorUse when someone wants to build, launch, grade or schedule a Claude Managed Agent in their own Anthropic account ('build me an agent', 'run this nightly'). Reads the session goal, routes with goal_router.py and compiles the loop with loop_compiler.py.