Juicebox Data Handling

What it does

When your agent uses it

• Tasks that involve Privacy and GDPR

Example prompts

• “juicebox data privacy”
• “juicebox gdpr”
• “/juicebox-data-handling”

Requirements

• A credential in JUICEBOX_API_KEY
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Grep

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Inventory fields, source terms, and intended destination before ingestion; quarantine unknown authority, classification, or suppression…
2. 2Run schema, minimization, and suppression validation on bounded synthetic batches, logging only opaque IDs and aggregate counts.
3. 3Compare intended source/destination scope with policy before any enrichment or export, defaulting uncertainty to deny.
4. 4Submit idempotent staged work only to approved destinations, retain a redacted manifest, and verify deletion at the stated retention…
5. 5Stop and escalate rather than weakening suppression, authority, or data-minimization rules.

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit
  • Grep

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are typescript).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Hosts in commands or code, which the agent is likely to contact:

  • api.juicebox.ai

  Also links to:

  • gdpr.eu

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • JUICEBOX_API_KEY

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

• Compatibility

  Designed for Claude Code

  From compatibility in the SKILL.md frontmatter.

Context cost

Juicebox Data Handling loads about 1.6k tokens when it runs, and up to ~3.7k if it reads all its reference files. Until then it costs about 26 tokens; SKILL.md has 462 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~26

When it runs · the whole SKILL.md, loaded when a task matches

~1.6k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.7k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 462 words, ~1,608 tokens.

name

juicebox-data-handling

description

Juicebox data privacy and GDPR. Trigger: "juicebox data privacy", "juicebox gdpr".

allowed-tools

Read, Write, Edit, Grep

compatibility

Designed for Claude Code

version

1.16.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, recruiting, juicebox

interface JuiceboxProfile {
  id: string; name: string; email?: string; phone?: string;
  company: string; title: string; skills: string[];
  source: string; enrichedAt: string;
}

async function importPeopleDataset(query: string, maxResults = 100): Promise<JuiceboxProfile[]> {
  const profiles: JuiceboxProfile[] = [];
  let offset = 0;
  do {
    const res = await fetch(`https://api.juicebox.ai/v1/search`, {
      method: 'POST',
      headers: { Authorization: `Bearer ${process.env.JUICEBOX_API_KEY}`, 'Content-Type': 'application/json' },
      body: JSON.stringify({ query, limit: 50, offset }),
    });
    const data = await res.json();
    if (!data.results?.length) break;
    for (const p of data.results) {
      if (!p.id || !p.name) throw new Error(`Invalid profile: missing required fields`);
      profiles.push(p);
    }
    offset += 50;
  } while (profiles.length < maxResults);
  return profiles;
}

async function exportAnalysisResults(profiles: JuiceboxProfile[], format: 'csv' | 'json') {
  // Strip direct contact info from exports unless explicitly authorized
  const sanitized = profiles.map(({ email, phone, ...rest }) => ({
    ...rest,
    email: email ? '[CONSENT_REQUIRED]' : undefined,
    phone: phone ? '[CONSENT_REQUIRED]' : undefined,
  }));
  if (format === 'csv') {
    const header = Object.keys(sanitized[0]).join(',');
    const rows = sanitized.map(r => Object.values(r).join(','));
    return [header, ...rows].join('\n');
  }
  return JSON.stringify(sanitized, null, 2);
}

function validateProfile(p: JuiceboxProfile): string[] {
  const errors: string[] = [];
  if (!p.id) errors.push('Missing profile ID');
  if (!p.name || p.name.length > 200) errors.push('Invalid or missing name');
  if (p.email && !/^[\w.+-]+@[\w-]+\.[\w.]+$/.test(p.email)) errors.push('Invalid email format');
  if (p.phone && !/^\+?[\d\s()-]{7,20}$/.test(p.phone)) errors.push('Invalid phone format');
  if (!p.source) errors.push('Missing data source attribution');
  if (p.enrichedAt && isNaN(Date.parse(p.enrichedAt))) errors.push('Invalid enrichment timestamp');
  return errors;
}

© jeremylongshore, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/.curated/juicebox-data-handling of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/implementation-guide.md

Open the folder on GitHubat commit cfae287