---
name: workhuman-install-auth
description: 'Select and document the supported Workhuman access path for a customer tenant, including SSO, managed integrations, or customer-issued API credentials. Use when onboarding or repairing an integration. Trigger with "configure Workhuman access".'
argument-hint: "[tenant] [integration-purpose]"
allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit
version: 1.4.0
author: Jeremy Longshore <jeremy@intentsolutions.io>
license: MIT
tags: [ saas, workhuman, authentication, sso, integration ]
model: inherit
effort: medium
compatibility: Designed for Claude Code; tenant access, identity changes, managed integrations, and credential issuance require customer and Workhuman authorization
title: workhuman-install-auth
canonical_url: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/workhuman-install-auth
last_updated: 2026-10-07T06:06:28.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> If the user asked to install this Skill, run `npx skilld install jeremylongshore/tons-of-skills-marketplace/workhuman-install-auth`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/workhuman-install-auth`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/jeremylongshore/tons-of-skills-marketplace/workhuman-install-auth) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/workhuman-install-auth`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/workhuman-install-auth --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/workhuman-install-auth --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Workhuman Tenant Access and Integration Onboarding

## Overview

Choose the supported access model, establish ownership, and prove the smallest safe capability without guessing a host, route, grant, or credential format.

## Prerequisites

- The customer tenant, subscribed products, program owner, and integration purpose
- Identity, security, data, and support owners for the affected workforce records
- Current customer-authorized Workhuman documentation or an assigned Workhuman implementation contact

## Tool Discipline

Use `Read`, `Glob`, and `Grep` to inspect local configuration, `WebFetch` to re-check first-party public and authorized tenant contracts, and `Write` or `Edit` only for secretless configuration and redacted evidence.

## Current Contract

Workhuman publicly documents SSO, controlled privileges, an open API, and managed integrations such as Microsoft Teams and Workday. Its public pages do not define one universal API host, OAuth flow, scope set, or verification route; obtain those details from the customer's current contract.

## Authentication

Separate interactive SSO, managed-connector authorization, and API credentials. Do not reuse browser sessions, infer `client_credentials`, copy administrator cookies, or put secrets in files, commands, prompts, logs, or receipts.

## Instructions

1. Record tenant, products, data classes, intended reads and writes, environments, and accountable owners.
2. Classify the path as interactive SSO, a Workhuman-managed integration, or a customer-issued API contract.
3. Re-fetch the applicable first-party product page and the customer's current implementation documentation.
4. Build an access matrix covering principal, roles or scopes, expiry, rotation, revocation, and break-glass ownership.
5. Search the repository for guessed hosts, undocumented routes, hard-coded secrets, and mixed-tenant configuration.
6. Present every tenant setting, connector enablement, consent, and credential request for explicit approval.
7. After authorized provisioning, run the smallest documented read-only check and retain only redacted status and correlation evidence.

## Approval Boundaries

Do not change SSO, assign privileges, enable an integration, issue credentials, or test production writes without the relevant customer and vendor owners.

## Output

Return the selected access path, contract evidence, access matrix, secretless configuration, verification receipt, rotation and revocation owners, and unresolved vendor questions.

## Error Handling

| Condition | Response |
|---|---|
| Customer API documentation is unavailable | Stop at the decision record and request it from the program owner or Workhuman. |
| SSO succeeds but an integration fails | Diagnose the connector or API principal independently; do not reuse the browser session. |
| Capability is not subscribed | Record the entitlement gap and route it to the commercial or program owner. |

## Example

A redacted completion receipt might look like this:

```text
tenant=customer-specific; path=managed-workday; principal=vendor-managed; contract=current; smoke=read-only-pass; secrets=redacted
```

## Resources

- [Workhuman integrations](https://www.workhuman.com/capabilities/integrations/)
- [Workhuman security and privacy](https://www.workhuman.com/why-workhuman/security-and-privacy/)

## Next Steps

Test reauthorization or credential rotation in a non-production context and assign a contract review date.
