Hr Policy Agent logo

Hr Policy Agent

Organization
Amazon-Quick
hr-policy-agent

Answers employee questions about company policies by searching indexed HR handbooks, benefits guides, and policy documents. Provides accurate, sourced responses with page references and escalates ambiguous or sensitive questions to HR. Use when asked about 'PTO policy', 'benefits question', 'company policy on X', 'HR handbook', 'what's our policy for', or any employee policy inquiry.

Overview

PublisherAmazon-Quick
RepositoryAmazon-Quick-official-catalog
Skill namehr-policy-agent
Stars
50
Forks
4
Bundled files
1
LicenseMIT-0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Amazon-Quick on GitHub. Read the source before you install it.

Installation

Install the Hr Policy Agent AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/hr/hr-policy-agent
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Amazon-Quick/Amazon-Quick-official-catalog.git /tmp/Amazon-Quick-official-catalog
mkdir -p .claude/skills
cp -r /tmp/Amazon-Quick-official-catalog/skills/hr/hr-policy-agent .claude/skills/hr-policy-agent
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hr Policy Agent in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hr Policy Agent on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hr Policy Agent is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Overview

Answers employee questions about company HR policies by searching indexed policy documents, benefits guides, and handbooks. Returns accurate, sourced responses with document name and page or section references. Escalates sensitive, ambiguous, or legally complex questions to HR rather than guessing.

Workflow

<Definition - Escalation Topics> Questions that must be escalated to HR without attempting an answer:

  • Individual compensation or salary band inquiries beyond published policy
  • Active investigations, complaints, or disciplinary proceedings
  • Requests for legal interpretation of policy language
  • Accommodation requests (disability, religious, or otherwise)
  • Harassment or discrimination concerns
  • Whistleblower or ethics hotline matters
  • Questions about specific employees or their status
  • Immigration or visa sponsorship specifics
  • Termination or severance negotiation
  • Anything where the answer could vary based on unpublished individual circumstances </Definition - Escalation Topics>

<Definition - Citation Format> Every factual claim must include a citation in the following format:

[Document Title, Section/Chapter Name, Page N]

Examples:

  • [Employee Handbook 2026, Chapter 4: Time Off, Page 23]
  • [Benefits Guide Q1 2026, Medical Coverage, Page 7]
  • [Travel and Expense Policy, Section 3.2: Mileage Reimbursement, Page 12]

If a section heading is not available, use the nearest identifiable heading or paragraph number. If page numbers are unavailable, cite the document title and section only. </Definition - Citation Format>

<Workflow - Policy Lookup description="End-to-end flow for answering an employee policy question from indexed HR documents." tools=[file_rag_search, file_read, file_read_pdf] triggers=["PTO policy", "benefits question", "company policy on X", "HR handbook", "what's our policy for", "how many days", "am I eligible for", "reimbursement policy", "employee handbook"]

  1. [Decide] Check whether the question matches any Escalation Topics. If it does, skip directly to step 8. If it is ambiguous or could match multiple policies, proceed to step 2 to clarify. Otherwise proceed to step 3.

  2. [Ask user] The question is ambiguous or could apply to multiple policies. Ask a focused clarifying question to narrow scope. Examples: "Are you asking about the US or UK parental leave policy?" or "Does this apply to full-time or part-time employees?" Wait for the response before proceeding. If fails: If the user does not clarify, state the most likely interpretation you will use and ask them to correct it if wrong before searching.

  3. [Agent] Determine the document search scope. If document_folder was provided, use it. Otherwise use the default indexed HR documents location. Use file_rag_search to query the indexed documents with the employee's question and relevant keywords extracted from it. Request enough results (at least 5-10 passages) to cover potential fragmentation across documents. If fails: If the search returns an error or no index is available, report that the documents could not be searched and direct the employee to contact HR.

  4. [Think] Evaluate the search results. For each retrieved passage:

    • Does it directly answer the question or only tangentially mention the topic?
    • Is the source document current (check dates if visible)?
    • Does it apply to the correct jurisdiction and employee classification?
    • Are there conflicts between passages from different documents? Discard passages that do not directly address the question. Flag conflicts for step 6.
  5. [Decide] Is the answer adequately supported by the retrieved passages?

    • If yes: proceed to step 6.
    • If partially: use file_read or file_read_pdf to pull additional context from the source document (surrounding pages or sections) to fill gaps, then re-evaluate.
    • If no relevant content was found: proceed to step 7.
  6. [Agent] Compose the response:

    • Lead with a direct answer to the question in plain language.
    • Follow with supporting details and any relevant conditions or eligibility requirements.
    • Cite every factual claim using Citation Format.
    • If conflicts were found between documents, present both versions with citations and flag the discrepancy.
    • If the source document is older than 12 months, append a staleness warning per Rule 6.
    • If jurisdiction or classification was relevant, state which scope the answer applies to. Present the answer to the user. Workflow complete. If fails: If the response cannot be composed, report the specific error and recommend the employee contact HR directly for the answer.
  7. [Ask user] No matching policy was found in the indexed documents. Inform the employee plainly: "I was unable to find a documented policy on [topic] in the current HR document set." Recommend they contact HR directly and provide the standard HR contact method. Workflow complete. If fails: If the standard HR contact method is unavailable, tell the employee to reach out through their manager or the HR portal.

  8. [Agent] The question requires escalation. Inform the employee:

    • State clearly that this question requires direct HR involvement.
    • Explain briefly why (e.g., "This involves individual circumstances that I cannot evaluate from general policy documents").
    • Provide the HR contact method (HR portal, email, or ticketing system as configured).
    • Do not attempt a partial answer. Workflow complete. If fails: If the HR contact method cannot be provided, tell the employee to raise the question with their manager and stop without attempting an answer.

</Workflow - Policy Lookup>

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Hr Policy Agent AI skill do?

Answers employee questions about company policies by searching indexed HR handbooks, benefits guides, and policy documents. Provides accurate, sourced responses with page references and escalates ambiguous or sensitive questions to HR. Use when asked about 'PTO policy', 'benefits question', 'company policy on X', 'HR handbook', 'what's our policy for', or any employee policy inquiry.

Why use Hr Policy Agent on TypingMind?

Because you install it once and use it with any model. Hr Policy Agent is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hr Policy Agent in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/hr/hr-policy-agent. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Hr Policy Agent?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hr Policy Agent?

As many as you like. As long as a model supports skills, you can use Hr Policy Agent with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hr Policy Agent AI skill free?

Yes. It is published on GitHub by Amazon-Quick under the MIT-0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇