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

Hr Accommodation Process

ASecurity

Runs the interactive accommodation process as a Reasonable Accommodation Record, with the options explored and the reason for the choice, a response letter, and adviser questions before any refusal. Use for "run hr-accommodation-process", "reasonable accommodation", "reasonable adjustments", "interactive process", "leave extension as an accommodation", "remote work request for a health reason", "can we say no to this accommodation", part of the AI for HR Pack by Polar Bear.

2 stars
0 votes
0 copies
1 views
Added 10/4/2026
ai-agentsgo

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add polar-bear-org/claude-skills --skill hr-accommodation-process --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Hr Accommodation Process?

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

Security grade badge for Hr Accommodation Process
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-hr-accommodation-process/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-hr-accommodation-process)

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: hr-accommodation-process
description: Runs the interactive accommodation process as a Reasonable Accommodation Record, with the options explored and the reason for the choice, a response letter, and adviser questions before any refusal. Use for "run hr-accommodation-process", "reasonable accommodation", "reasonable adjustments", "interactive process", "leave extension as an accommodation", "remote work request for a health reason", "can we say no to this accommodation", part of the AI for HR Pack by Polar Bear.
---

# Reasonable Accommodation Process

## When To Use
A leave extension or remote work request comes in and someone senior wants to say no without the conversation. This answers: have we recognised the request, looked at real options with the employee, and recorded why we chose what we chose?

## When Not To Use
If the question is the leave itself (dates, notices, return), run Leave of Absence Plan. If it is attendance rules for everyone, run Absence Management.

## Inputs
- Where the person works (country, and state or province), the request in the employee's words, and the job's main duties
- Any options already discussed and who has raised concerns
If you have none of this, I start from the request and the job title, and mark the output as a first draft.

## Approach
The record follows the Job Accommodation Network's six-step accommodation process (askjan.org/topics/interactive.cfm) and Acas guidance on reasonable adjustments (acas.org.uk/reasonable-adjustments). The judgment is that a request needs no legal words to count, and that the conversation is the process. The failure it prevents: a VP refused extra leave without talking to the worker, who came back early and got hurt.

## Workflow
1. Ask where the person works (country, and state or province), what was asked for and when, and who has the authority to decide.
2. Recognise the request: log the date it was made and how, even if the employee never said "accommodation" or "adjustment". The process starts from that date.
3. Begin the process: name who runs it and set the first meeting with the employee. Leaders who want to refuse come to that meeting with their concerns, not a verdict.
4. Request information only when the need is not obvious, and only what the decision needs: the functional limit and what would help. No diagnosis is recorded. Claude never judges whether a condition is genuine or what it means medically.
5. Explore options with the employee in a table: option, what disadvantage it reduces, cost, practicality, who pays (Acas says the employer pays for reasonable adjustments; confirm with a qualified adviser for the country it concerns), decision and reason. Include the employee's own proposal and at least one alternative.
6. A named person chooses. If the choice is a refusal of every option, stop: list the adviser questions and draft nothing until an adviser has answered them.
7. Implement and monitor: draft the response letter from the recorded choice, set a review date with the employee, and name who checks the adjustment works.

## Output Format
```markdown
# Reasonable Accommodation Record
Employee: [name] · Place: [country, state] · Request received: [date, how] · Runs the process: [name]
## Request
[The request in the employee's words] · Functional need: [what the employee cannot do or finds hard, no diagnosis]
## Meetings
| Date | Who | What was discussed | Agreed actions |
|---|---|---|---|
| [date] | [names] | [summary] | [action, owner] |
## Options explored
| Option | Disadvantage it reduces | Cost | Practicality | Who pays | Decision and reason |
|---|---|---|---|---|---|
| [option] | [effect] | [cost supplied] | [note] | [payer] | [decided by, reason] |
## Adviser questions
- [Question to answer before any refusal]
## Response letter
[Draft, naming who approved the choice]
## Decision
[Named person] chooses the adjustment by [date]; review with the employee on [date].
```

## Done When
- The request date is logged even if no legal word was used
- At least two options are in the table, each with a reason
- A refusal has adviser questions answered before any letter exists
- The record holds the functional need, never a diagnosis

## Quality Bar
- The employee is in the conversation; the record shows each meeting
- Only information the decision needs is requested, and health details stay in a restricted file
- No judgement on whether the condition is real or serious enough
- Cost is a fact the user supplies, never an estimate Claude invents
- Claude writes the process, never the verdict: it never screens, ranks, scores or reads people, a named person decides and signs every decision about someone, and every legal point goes to a qualified adviser for the country it concerns.

## Next
Run hr-absence-management (Absence Management) to align absence rules with the adjustment.

## About the makers

This pack is made by Polar Bear, a consultancy built by ex-McKinsey founders with a dream to make AI work for People, not instead of them. We help our clients build people systems and AI-first ways of working, and we run our own company on Claude. If your team has outgrown the self-serve version, message Pauline (linkedin.com/in/paulinebertry).

Attribution

polar-bear-orgpolar-bear-org
View sourceSee grades on GitHubMore from polar-bear-org →
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', ...

698431 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 →