Skip to main content
skill CX Codex

windsurf-data-handling — Claude Code skill: use and install

The windsurf-data-handling skill maps data flows, sets context exclusions, and gathers evidence for privacy and compliance reviews around Devin Desktop, formerly Windsurf.

MIT 1 installs ★ 2,935 updated 2026-11-01

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-data-handling -a claude-code
Open on GitHub

What windsurf-data-handling does

The skill builds a data map for Devin Desktop, formerly Windsurf. It covers Cascade, autocomplete, indexing, remote indexing, MCP, Hooks, diagnostics, and App Deploys. Each flow records its inputs, destination, purpose, identity, retention evidence, owner, and applicable policy, including metadata and logs.

It uses .gitignore and repository .codeiumignore to limit local context, while shared handling rules can live in AGENTS.md or .devin/rules/*.md. The workflow reviews MCP servers, Hooks, deployment targets, and analytics exports for ownership, authentication, scope, logging, revocation, and incident contacts. Context exclusions do not revoke filesystem access or prove a regulatory requirement.

Prepare a data-classification policy, an approved repository inventory, contract or security evidence, and named security, privacy, and legal owners. Synthetic canaries are used to test exclusions. Approval is required before enabling regulated workloads, remote indexing, or external MCP access.

What it helps with

  • map data flows across Devin Desktop features
  • exclude secrets and customer exports from context
  • turn data-handling requirements into repository rules
  • review owners and permissions for integrations
  • record retention and residency evidence

Example prompts for the agent

  • Map the data flows for a “windsurf data privacy” review and create a data-boundary record.
  • Exclude PII with .codeiumignore and add the approved handling rules to AGENTS.md.
  • Review every MCP server and prepare the approvals needed for a regulated workload.

How to install windsurf-data-handling

1Skills CLI (Vercel)

npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-data-handling -a claude-code

2Manually: put the files in place

~/.claude/skills/windsurf-data-handling/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/windsurf-data-handling/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about windsurf-data-handling

How do I install windsurf-data-handling in Claude Code?

Run npx skills add jeremylongshore/tons-of-skills-marketplace --skill windsurf-data-handling -a claude-code, then check ~/.claude/skills/windsurf-data-handling/SKILL.md.

What does windsurf-data-handling do?

It maps data flows, context exclusions, integrations, and supporting evidence for privacy and compliance reviews. It also produces a data-boundary record with validation results.

What do I need before using this skill?

Prepare a data-classification policy, an approved repository inventory, contract or security evidence, and named security, privacy, and legal owners. Use synthetic canaries when testing exclusions.

Source text

SKILL.md · MIT
---
name: windsurf-data-handling
description: 'Govern data processed through Devin Desktop (formerly Windsurf).
  Use when mapping sensitive data, configuring context exclusions, reviewing vendor
  controls, or preparing regulated-workload evidence. Trigger with "windsurf data
  privacy", "windsurf PII", "GDPR", "data residency", or "AI data boundary".'
allowed-tools: Read, Write, Edit
argument-hint: "[scope or requirements]"
version: 1.12.0
license: MIT
author: Jeremy Longshore <[email protected]>
tags:
- saas
- windsurf
- privacy
- compliance
- data-handling
compatibility: Designed for Claude Code
---

# Devin Desktop Data Handling

## Overview

Build an evidence-backed data map for Devin Desktop. Do not infer retention, residency, training use, certification coverage, or zero-data-retention from plan names; verify mutable vendor claims against the current contract and security documentation.

## Prerequisites

- Data-classification policy and approved repository inventory
- Contract, DPA, or security evidence available to the authorized reviewer
- Named security, privacy, and legal decision owners

## Tool Use

- Use `Read` to inspect only the repository files and configuration needed for the request.
- Use `Write` only for a new artifact the user requested; never write credentials or unreviewed production configuration.
- Use `Edit` for bounded, reviewable changes and preserve unrelated user work.

## Instructions

### Step 1: Inventory data flows

For Cascade, autocomplete, indexing, remote indexing, MCP, Hooks, diagnostics, and App Deploys, record inputs, destination, purpose, identity, retention evidence, administrator, and applicable policy. Include metadata and logs, not only source files.

### Step 2: Minimize local context

Use `.gitignore` and repository `.codeiumignore` to exclude secrets, generated output, customer datasets, private keys, production exports, and irrelevant large files. Enterprise administrators may apply a global `.codeiumignore` under `~/.codeium/`.

Ignored paths are context controls. They do not revoke filesystem access, rotate secrets, satisfy least privilege, or prove a regulatory requirement.

### Step 3: Choose durable instructions

Put shared data-handling requirements in `AGENTS.md` or `.devin/rules/*.md`, for example:

```markdown
# Regulated data boundary
- Never paste customer records, access tokens, or production exports into prompts.
- Use synthetic fixtures in tests and examples.
- Require security review for changes under `src/payments/`.
- Stop and escalate if a requested artifact contains regulated data.
```

### Step 4: Review integrations

For every MCP server, Hook, deployment target, and analytics export, confirm an owner, authentication method, approved scopes, destination, log policy, revocation path, and incident contact. Disable integrations that lack an accountable owner.

### Step 5: Reconcile vendor evidence

Capture the URL or contract section, observation date, product/plan scope, and reviewer for each claim. Where public documentation and negotiated terms differ, label the applicable authority rather than blending them.

### Step 6: Test and approve

Use synthetic canaries to verify exclusions and policy behavior. Obtain the required security/privacy/legal approval before enabling regulated workloads, remote indexing, or external MCP access.

## Output

Produce a data-boundary record identifying data classes, indexed and excluded paths, integrations, organization controls, telemetry and logging decisions, retention or residency evidence, open questions, approvals, and validation results. Never reproduce sensitive values.

## Error Handling

| Issue | Response |
|---|---|
| Vendor claim lacks current evidence | Mark unverified and request contract/security review |
| Sensitive data entered Cascade | Stop, contain sharing, rotate affected secrets, and follow incident policy |
| Ignore test fails | Correct syntax or scope, refresh indexing through current controls, and retest |
| Integration owner is unknown | Disable or quarantine the integration until ownership is established |

## Examples

**Evidence row:** "Customer export; excluded by `.codeiumignore`; no MCP access; repository owner: Data Platform; retention claim pending DPA confirmation; synthetic canary passed during the recorded review run."

## Resources

- [Focused first-party references](references/official-docs.md)
- [Windsurf Ignore](https://docs.devin.ai/desktop/context-awareness/windsurf-ignore)
- [Windsurf security](https://windsurf.com/security)
- [Enterprise administration](https://docs.devin.ai/desktop/guide-for-admins)

## Related Skill

Continue with `windsurf-policy-guardrails` to turn approved data controls into enforceable repository, terminal, MCP, deployment, and organization policy.

© Jeremy Longshore · MIT · jeremylongshore/tons-of-skills-marketplace

Similar skills

All skills for Security →

From the same set139

The whole set →
firecrawl-webhooks-events firecrawl-webhooks-events sets up Firecrawl webhook ingestion with raw HMAC-SHA256 signature verification, deduplication, and polling fallback. CX Codex +1 1installs coderabbit-webhooks-events coderabbit-webhooks-events is a Claude Code skill for designing Git-provider event automation around CodeRabbit reviews. It checks signatures and tests replay handling. CX Codex +1 1installs posthog-webhooks-events posthog-webhooks-events registers PostHog webhook destinations through the API, handles the incoming payloads, and runs bounded event queries with HogQL or the private API. CX Codex +1 1installs instantly-webhooks-events instantly-webhooks-events guides the setup and operation of Instantly API v2 webhooks with schema checks, deduplication, and privacy safeguards. CX Codex +1 1installs windsurf-flows-automation windsurf-flows-automation — a skill for building and managing Windsurf Flows, the automation scripts for repetitive dev work. Turn routine tasks into one-command flows. CX Codex +1 1installs lindy-core-workflow-b lindy-core-workflow-b is a Claude Code skill for configuring Lindy triggers, Cron schedules, and multi-agent delegation. CX Codex +1 1installs deepgram-core-workflow-b The deepgram-core-workflow-b skill outlines real-time transcription with Deepgram over WebSocket. Use it when adding live captions, voice controls, or speech features to an app. CX Codex +1 1installs code-documentation-analyzer Auto-activating skill for auditing code documentation: API references, user guides, architecture docs. Triggers on phrases like "code documentation analyzer" or "code analyzer". CX Codex +1 1installs

Project sponsors

Companies that keep this analytics open