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.

referencesofficial-docs.md

≈820 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Cohere Official Documentation Snapshot

Verified against Cohere primary documentation, the official SDK repositories, and package registries on 2026-09-11. Recheck the live model catalog, deprecation schedule, pricing, and rate-limit page before changing a production workload because those surfaces are intentionally dynamic.

SDK and authentication

Models and inference

Lifecycle and operations

Pinned interpretation

  • New integrations use API v2 clients: CohereClientV2 in TypeScript and cohere.ClientV2 in Python. On 2026-09-11, the registry releases were cohere-ai@8.1.0 and cohere==7.1.1; pin a compatible range and retain the resolved lockfile version.
  • Resolve deployable models from the live catalog or Models API. command-a-plus-05-2026, embed-v4.0, rerank-v4.0-pro, and rerank-v4.0-fast were live reference candidates on the review date, not permanent aliases.
  • API v2 requires model for Chat, Embed, Rerank, and Classify; Embed also requires embedding_types. Chat history lives in messages, and tools use JSON Schema.
  • Managed /v1/connectors, connectors on Chat v1, Generate, Summarize, Classify, and legacy fine-tuning were listed as deprecated. In v2, implement retrieval or web search as application-owned tools.
  • Evaluation and production limits differ by endpoint and model. Some newer Chat models require a sales-approved production arrangement. Treat the live limits page and response behavior as authoritative.
  • Cohere Teams expose Owner and User roles, but application authorization, per-tenant budgets, and least-privilege runtime keys remain the customer's responsibility.
  • The public privacy policy says enterprise customer-data commitments are contract-specific. Do not infer retention, residency, or training terms from generic marketing copy; bind production controls to the signed agreement.

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