Index of every page on this site: llms.txt
All skills
jeremylongshore avatar

/cohere-data-handling

@820dfc8
Run it yourself

Govern data sent to Cohere with classification, minimization, tenant controls, redaction, retention mapping, and contractual evidence. Use when processing sensitive or regulated data. Trigger with "Cohere privacy", "Cohere PII", or "Cohere data retention".

Use this Skill: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/cohere-data-handling

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈70 tokens for metadata: the name and description. ≈954 when used: this file. ≈820 more on demand in 1 file.

Description uses 3.5% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈279 characters, or 3.5%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

Cohere Data Handling and Privacy

Overview

Decide what may cross the provider boundary from the signed agreement and application purpose, then enforce that decision before each request.

Prerequisites

  • The target repository, runtime, environment, and accountable owner
  • An approved Cohere team and key for any live verification
  • Current quality, security, privacy, capacity, and change-control requirements

Tool Discipline

Use Read, Glob, and Grep to inspect code, configuration, and evidence. Use WebFetch only for current Cohere primary documentation. Use Write or Edit only when the user requested implementation and the exact target files are known; never write credentials or customer content.

Current Contract

  • Cohere's public privacy policy distinguishes enterprise Customer Data from general personal information and points to enterprise commitments.
  • Do not infer retention, residency, training use, deletion, or subprocessors from a generic policy when a contract governs the workload.
  • Embeddings and logs can encode sensitive information even when raw text is absent.
  • Data minimization and tenant authorization must happen before Chat, Embed, Rerank, or tool calls.

Authentication

Use an environment-specific key injected from an approved secret manager. Never print, persist, commit, or place CO_API_KEY in an example. Confirm access with the least costly bounded operation appropriate to the task, and treat key creation, rotation, revocation, role changes, and production-capacity requests as owner-approved actions.

Instructions

  1. Classify inputs, retrieved documents, outputs, embeddings, logs, and tool data by tenant and jurisdiction.
  2. Map each data class to the signed terms, approved region, retention, deletion, access, and incident requirements.
  3. Block disallowed classes and minimize, tokenize, or redact approved inputs before the provider call.
  4. Apply tenant filters before retrieval and keep document identifiers safe for citation auditing.
  5. Configure logs and caches with allowlisted fields, encryption, access control, and deletion tests.
  6. Produce a data-flow record and obtain privacy or legal approval for unresolved contractual claims.

Approval Boundaries

Do not expose or rotate keys, change Cohere Team roles, accept commercial terms, enable sensitive production data, increase spend or capacity, switch production models, send a support bundle, or execute model-proposed side effects without the accountable owner's approval. Keep diagnosis read-only unless implementation was requested.

Output

Return the resolved API and model contract, files or settings inspected, evidence collected, validation result, remaining risk, owner, and rollback or next action. Redact keys, authorization headers, prompts, retrieved documents, embeddings, customer identifiers, and unrestricted environment output.

Error Handling

Condition Response
Terms unavailable Block sensitive production use until the governing agreement is identified.
PII detected Apply the approved transformation or reject the request.
Cross-tenant data Stop processing and invoke the data incident procedure.
Deletion unverified Do not claim compliance; test each controlled storage layer.

Examples

Use this compact handoff shape to keep the selected scope, validation evidence, and operational result reviewable.

Input:

data=customer-support; class=confidential; jurisdiction=EU; contract=enterprise

Expected handoff:

purpose=approved; fields=minimized; retention=mapped; review=recorded

Resources

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts2mo3 checks · Risk SAFE
  • Gen Agent Trust Hub2mo

    The skill provides code and guidance for PII redaction and privacy compliance when using Cohere APIs. It establishes best practices for data handling, auditing, and content filtering to mitigate exposure of sensitive information.

  • Socket2mo

    No alerts

  • Snyk2mo

    Risk: LOW · No issues

Signed by skilld at 820dfc8. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
What it can do
Reads files Network Edits files
Modelinherit
argument-hint
[data-class] [jurisdiction] [environment]
version
1.6.0
author
Jeremy Longshore <jeremy@intentsolutions.io>
All 6 allowed tools
ReadGlobGrepWebFetchWriteEdit
Other metadata
tags
[
  "saas",
  "cohere",
  "privacy"
]
model
inherit
effort
high
compatibility
Designed for Claude Code; live verification requires network access and an approved Cohere API key

README badge

README badge for jeremylongshore/tons-of-skills-marketplace/cohere-data-handling