Glean Data Handling

What it does

When your agent uses it

• Legal & Compliance work in your project

Example prompts

• “glean data handling”
• “data-handling”
• “/glean-data-handling”

Requirements

• A credential in GLEAN_INDEXING_TOKEN
• A credential in GLEAN_API_TOKEN
• Compatibility (from SKILL.md): Designed for Claude Code
• Pre-approved tools (allowed-tools): Read, Write, Edit, Bash(npm:*), Bash(curl:*), Grep

Workflow steps

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

1. 1Inventory fields and source ACLs before indexing; default any unknown permission or classification to deny and quarantine the record.
2. 2Run redaction and schema validation on a bounded staging batch, logging only record counts, rule versions, and opaque document identifiers.
3. 3Compare source and proposed index ACLs for both an allowed and denied test principal before approving a production batch.
4. 4Send idempotent, bounded batches to the approved datasource and retain a reversible manifest of submitted opaque IDs and timestamps.
5. 5On a failed validation, stop the batch, delete only the staged artifacts, and escalate to the data owner rather than weakening redaction…

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
  • Bash(npm:*)
  • Bash(curl:*)
  • 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:

  • customer-be.glean.com

  Also links to:

  • developers.glean.com

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

• Credentials

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

  • GLEAN_INDEXING_TOKEN
  • GLEAN_API_TOKEN

  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

Glean Data Handling loads about 1.8k tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 534 words of instructions outside code blocks.

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

~38

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

~1.8k

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). 534 words, ~1,775 tokens.

name

glean-data-handling

description

PII filtering: strip emails, phone numbers, SSNs from document body before indexing. Trigger: "glean data handling", "data-handling".

allowed-tools

Read, Write, Edit, Bash(npm:*), Bash(curl:*), Grep

compatibility

Designed for Claude Code

version

1.8.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, enterprise-search, glean

interface GleanDocument {
  id: string; datasource: string; title: string;
  body: string; permissions: { allowedUsers?: string[]; allowAnonymousAccess?: boolean };
  updatedAt: string; url: string;
}

async function indexDocuments(docs: GleanDocument[], datasource: string) {
  // PII strip before indexing
  const sanitized = docs.map(doc => ({
    ...doc,
    body: stripPII(doc.body),
  }));
  // Batch upload with pagination (max 100 per request)
  for (let i = 0; i < sanitized.length; i += 100) {
    const batch = sanitized.slice(i, i + 100);
    await fetch(`https://customer-be.glean.com/api/index/v1/bulkindexdocuments`, {
      method: 'POST',
      headers: { Authorization: `Bearer ${process.env.GLEAN_INDEXING_TOKEN}`, 'Content-Type': 'application/json' },
      body: JSON.stringify({ datasource, documents: batch }),
    });
  }
}

function stripPII(text: string): string {
  return text
    .replace(/\b[\w.+-]+@[\w-]+\.[\w.]+\b/g, '[EMAIL_REDACTED]')
    .replace(/\b\d{3}[-.]?\d{3}[-.]?\d{4}\b/g, '[PHONE_REDACTED]')
    .replace(/\b\d{3}-\d{2}-\d{4}\b/g, '[SSN_REDACTED]');
}

async function exportSearchAnalytics(startDate: string, endDate: string) {
  const res = await fetch(`https://customer-be.glean.com/api/v1/analytics`, {
    method: 'POST',
    headers: { Authorization: `Bearer ${process.env.GLEAN_API_TOKEN}`, 'Content-Type': 'application/json' },
    body: JSON.stringify({ startDate, endDate, metrics: ['query_count', 'click_through', 'zero_results'] }),
  });
  const data = await res.json();
  // Redact user identifiers from analytics export
  return data.results.map((r: any) => ({ ...r, userId: undefined, query: r.query?.length > 3 ? r.query : '[SHORT_QUERY_REDACTED]' }));
}

function validateDocument(doc: GleanDocument): string[] {
  const errors: string[] = [];
  if (!doc.id || doc.id.length > 512) errors.push('Invalid document ID');
  if (!doc.datasource) errors.push('Missing datasource identifier');
  if (!doc.title || doc.title.length > 1000) errors.push('Title missing or exceeds 1000 chars');
  if (!doc.body || doc.body.length === 0) errors.push('Empty document body');
  if (!doc.permissions) errors.push('Missing permissions — defaults to deny-all');
  if (doc.updatedAt && isNaN(Date.parse(doc.updatedAt))) errors.push('Invalid updatedAt 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

Just SKILL.md in skills/.curated/glean-data-handling of jeremylongshore/tons-of-skills-marketplace.

Open the folder on GitHubat commit cfae287