Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Afaro Drop Submit

ASecurity

Scaffold for the single California deletion request through the state DROP platform. Not implemented yet. Use when a California resident asks about the state deletion request.

3 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agents

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add afaro-ai/afaro --skill afaro-drop-submit --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Afaro Drop Submit?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Afaro Drop Submit
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/afaro-ai-afaro-drop-submit/badge)](https://www.skillsdirectory.com/skills/afaro-ai-afaro-drop-submit)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: afaro-drop-submit
description: "Scaffold for the single California deletion request through the state DROP platform. Not implemented yet. Use when a California resident asks about the state deletion request."
---

# Afaro data removal: California DROP request

Files one deletion request with California's state platform, which registered data brokers are required to process, instead of one form per broker.

**Status: scaffold. Nothing in this skill runs yet.** The steps below describe what Phase 1 will do. If a person asks for it today, explain what it is, say it is not built, and offer the per-broker guided run instead.

---

## When to use

- The person's profile has `state_of_residence` set to `CA` and they ask about the state deletion request.
- The person asks why they would still file per-broker opt-outs if California has one request.

## When NOT to use

- The person does not live in California. The platform is a California residents' right, and a request from elsewhere is not one Afaro will file.
- The person wants the per-broker opt-outs. Use `afaro-orchestrator`.
- The person wants to know who lists them. Use `afaro-exposure-scan`.

---

## Required inputs

1. **The profile path**, with `state_of_residence` equal to `CA`.
2. **A capture of the current platform page**, read on the day it is used, under the same provenance rule every manifest follows.
3. **The person, present.** The request is theirs, made in their name, and the state platform verifies them directly.

Stop if `state_of_residence` is anything other than `CA`.

---

## The framework

**One request, many brokers.** The state platform takes a single verified deletion request and makes it available to registered data brokers, which are required to process it. That is the reason the skill exists: one request instead of dozens.

**It does not reach everything.** Public-record data is outside what the platform requires brokers to delete, and brokers that are not registered are outside it too. So the per-broker opt-outs still run. A person who files the state request and stops there will still be listed in places.

**The state verifies the person, not Afaro.** Identity checks in the platform belong to the person. Any step asking for identity is a `human_gate` with reason `id_upload` or `phone_verify`, and no mode passes those.

**Nothing is filed on anyone else's behalf.** One person, present, for themselves.

---

## Workflow

Phase 1. Written here so the shape is settled before it is built.

1. Read the profile. Confirm `state_of_residence` is `CA`. Stop if it is not.
2. Confirm with the person that they want the state request in addition to, not instead of, the per-broker opt-outs. Say plainly what the platform does not reach.
3. Open the California Privacy Protection Agency's platform page in the person's browser. Read it as it is today. Do not work from remembered field names.
4. Walk the platform's own steps, gating exactly as a manifest does: every identity check is the person's to complete.
5. Stop at the submit gate. In guided mode the person confirms before anything is sent.
6. Record the outcome in the redacted log: one line, no profile values, no request identifiers that carry personal data.
7. Hand the remaining brokers to `afaro-orchestrator` for the per-broker pass.

Before this is implemented, the platform's page is captured and read the same way a broker's opt-out page is, and this skill is rewritten from that capture rather than from this description.

---

## Failure patterns

- **Treating the state request as the whole job.** It is one part. Public-record data and unregistered brokers remain, and the per-broker opt-outs follow.
- **Filing for a person who does not live in California.** Stop.
- **Filing for somebody who is not present.** Stop.
- **Working from this file instead of the live page.** These notes describe intent. The page decides the steps.
- **Promising a result.** No guarantee is made about what any broker does with the request.

---

## Output format

Not produced yet. When implemented: one line saying the request was submitted and on what date, the platform's own reference if it shows one and it carries no personal data, and the list of brokers still queued for per-broker opt-outs.

---

## Reference files

- `references/drop-scope.md` - What the state platform covers, what it does not, and what has to be verified against the live page before this skill is built.

Attribution

afaro-aiafaro-ai
View sourceMore from afaro-ai →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →