Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Workhuman Debug Bundle

ASecurity

Assemble a privacy-safe Workhuman support bundle with contract, configuration, timeline, and correlation evidence. Use when escalating a tenant or managed-integration issue. Trigger with "build a Workhuman debug bundle".

2,785 stars
0 votes
0 copies
0 views
Added 9/24/2026
ai-agentssecuritydocumentation

Works with

claude codecli

Security Analysis

A100/100

Scanned 9/24/2026

$npx -y skills add jeremylongshore/claude-code-plugins-plus --skill workhuman-debug-bundle --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Workhuman Debug Bundle?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Workhuman Debug Bundle
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/jeremylongshore-workhuman-debug-bundle-5e58bb3f/badge)](https://www.skillsdirectory.com/skills/jeremylongshore-workhuman-debug-bundle-5e58bb3f)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: workhuman-debug-bundle
description: 'Assemble a privacy-safe Workhuman support bundle with contract, configuration, timeline, and correlation evidence. Use when escalating a tenant or managed-integration issue. Trigger with "build a Workhuman debug bundle".'
argument-hint: "[incident-id] [time-window]"
allowed-tools: Read, Glob, Grep, WebFetch, Write, Edit
version: 1.4.0
author: Jeremy Longshore <jeremy@intentsolutions.io>
license: MIT
tags: [saas, workhuman, diagnostics, privacy, support]
model: inherit
effort: high
compatibility: Designed for Claude Code; collection and disclosure must follow customer privacy, retention, legal, security, and Workhuman support rules
---
# Privacy-Safe Workhuman Support Bundle

## Overview

Create the minimum reproducible evidence package needed by customer teams or Workhuman support without exposing workforce data, messages, awards, balances, or credentials.

## Prerequisites

- Incident identifier, bounded time window, tenant and environment, symptom, severity, and support owner
- Customer classification, retention, disclosure, and legal requirements
- Current contract or connector documentation and an approved sharing channel

## Tool Discipline

Use `Read`, `Glob`, and `Grep` for local evidence discovery, `WebFetch` to verify current vendor context, and `Write` or `Edit` only inside an access-controlled redacted bundle.

## Current Contract

Workhuman processes workforce, recognition, reward, and integration data and publishes privacy and security commitments. Support evidence must follow the customer's agreement and support process; public pages do not authorize unrestricted log or payload sharing.

## Authentication

Do not collect credentials, authorization headers, session cookies, client secrets, signed URLs, or reusable tokens. Hash or truncate identifiers only when the receiving owner confirms that they remain useful.

## Instructions

1. Define the diagnostic question, audience, time window, allowed data classes, retention, and deletion owner.
2. Inventory candidate logs, configuration, contract fingerprints, deployment history, connector runs, reports, and safe correlation fields.
3. Exclude names, recognition messages, employment details, balances, addresses, financial data, secrets, raw payloads, and unrelated tenants.
4. Create a UTC timeline containing expected behavior, actual behavior, last success, first failure, changes, retries, and partial effects.
5. Include secretless topology, environment and version identifiers, schema digests, counts, sanitized statuses, and synthetic reproduction steps.
6. Run pattern and manual redaction review; record excluded classes and the reviewer.
7. Package a manifest with hashes, purpose, audience, expiry, and approved transfer channel.
8. Obtain disclosure approval before sending and record receipt and deletion expectations.

## Approval Boundaries

Do not query extra personal data, widen the incident window, decrypt archives, or send the bundle outside approved channels without privacy and support-owner approval.

## Output

Return the redacted timeline, safe configuration and topology, reproduction, schema and correlation evidence, manifest hashes, redaction proof, approvers, expiry, and transfer receipt.

## Error Handling

| Condition | Response |
|---|---|
| Necessary evidence is personal data | Minimize or tokenize it and obtain explicit disclosure authorization. |
| Bundle cannot reproduce the issue | State the limitation and request one narrowly defined additional artifact. |
| Secret scan finds a credential | Quarantine the bundle, rotate if exposed, redact, and rescan. |

## Example

A redacted completion receipt might look like this:

```text
incident=WH-42; window=15m; records=redacted-counts-only; secrets=0; manifest=sha256:...; approved=privacy+support; expires=7d
```

## Resources

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

## Next Steps

Track the vendor response against the manifest and delete the bundle at the approved expiry.

Attribution

jeremylongshorejeremylongshore
View sourceSee grades on GitHubMore from jeremylongshore →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →