Accommodation Request logo

Accommodation Request

CommunityPopular
mohitagw15856
accommodation-request

Request a reasonable accommodation at work or in education — frame it around the barrier and the adjustment (not your diagnosis), cite the right process, and navigate the back-and-forth constructively. Use when someone says 'I need a workplace accommodation', 'request reasonable adjustments', 'ADA/Equality Act accommodation', or 'how do I ask for accommodations for my disability/condition'. Produces the request letter, a barriers-and-adjustments map, disclosure guidance, and a plan for the interactive process. Not legal advice — routes to the formal process and to advocacy where needed.

Overview

Publishermohitagw15856
Repositorypm-claude-skills
Skill nameaccommodation-request
Stars
1.4K
Forks
240
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by mohitagw15856 on GitHub. Read the source before you install it.

Installation

Install the Accommodation Request 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.
  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/mohitagw15856/pm-claude-skills.git /tmp/pm-claude-skills
mkdir -p .claude/skills
cp -r /tmp/pm-claude-skills/exports/openclaw/accommodation-request .claude/skills/accommodation-request
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Accommodation Request 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 Accommodation Request 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 Accommodation Request 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.

Accommodation Request Skill

Reasonable accommodations (US: ADA; UK: reasonable adjustments under the Equality Act; similar elsewhere) are a right, but getting them often stalls on how the request is framed: people over-share medical detail, ask for a vague "help," or frame it as a favor rather than an adjustment to a barrier. Employers and institutions respond best to a specific request that names the barrier and the adjustment that removes it — they generally don't need your diagnosis, only the functional limitation and what helps. This skill writes that request, guides how much to disclose, and prepares you for the interactive back-and-forth that follows. It is not legal advice; it routes to the formal process and to advocacy if you hit resistance.

What This Skill Produces

  • A barriers-and-adjustments map: for each thing that's hard, the specific workplace/course barrier and the concrete adjustment that removes it (framed as an adjustment to a barrier, not a personal favor)
  • The request letter/email: to the right person (HR, disability services, manager per the process), citing the process, naming the adjustments, and inviting the interactive dialogue
  • Disclosure guidance: how much to share (usually the functional limitation and what helps, not the diagnosis), what you're not obliged to reveal, and where medical documentation is genuinely needed
  • A process plan: the interactive/good-faith dialogue that's expected, how to handle "that's not possible," alternatives, and escalation to advocacy or the formal complaint route if needed

Required Inputs

Ask for (if not already provided):

  • The setting (workplace or education) and country/system, since the legal framework and process differ
  • The specific difficulties and the tasks/situations where they bite (the barrier), and what adjustments would help
  • What the user is comfortable disclosing and to whom, and whether there's an existing process (HR policy, disability services office)
  • Any history (a prior refusal, a difficult manager) that shapes strategy

Framework

  1. Frame around barrier → adjustment, not diagnosis. The request names the barrier ("open-plan noise makes focused work impossible," "fixed exam timing conflicts with medication effects") and the specific adjustment that removes it (noise-cancelling/ a quiet space, extra time/a separate room). The employer's duty attaches to the barrier and the reasonable fix, not to your medical history.
  2. Disclose the minimum that works. Generally you must share enough functional information to justify the adjustment and may need medical documentation of the limitation — but not your full diagnosis or records. The skill helps calibrate: enough to establish the need, no more, and names what you're not obliged to reveal.
  3. Send it to the right process. Route to whoever owns adjustments (HR, disability/ access services, occupational health) rather than only a manager who can't approve, cite the relevant policy/law framing, and put it in writing so there's a record.
  4. Expect the interactive dialogue — and engage it. These processes are meant to be a good-faith back-and-forth: they may propose alternatives, ask for documentation, or push back on cost/feasibility. The skill preps constructive responses, the "undue-hardship/reasonableness" conversation, and holding firm on the barrier while being flexible on the exact fix.
  5. Know the escalation and get support. If met with refusal, delay, or retaliation: the formal grievance/complaint route, disability advocacy organizations, and (where warranted) legal advice. Retaliation for requesting accommodations is itself usually unlawful — flag it, and route to real help rather than adjudicating it here.

Output Format

## Barriers → adjustments
| The barrier (situation/task) | The adjustment that removes it |

## Your request (send this)
[To the right owner · cites the process · names the adjustments · invites the
interactive dialogue · in writing]

## What to disclose (and what you needn't)
[The functional info to share · documentation if genuinely needed · what you're not
obliged to reveal]

## The back-and-forth
[Expect a good-faith dialogue · handling "not possible"/alternatives · firm on barrier,
flexible on fix]

## If you hit a wall
[Grievance/complaint route · disability advocacy orgs · legal advice · retaliation is
usually unlawful — get help]

⚠ Not legal advice. Frameworks differ by country and situation; route to the formal
process and to an advocate/lawyer if you meet resistance.

Quality Checks

  • Every request is framed as barrier → adjustment, not as a diagnosis disclosure or a favor
  • Disclosure is calibrated to the minimum needed, and what's not required is stated
  • It's routed to the actual owner of the process, in writing
  • The interactive/good-faith dialogue is anticipated with constructive responses
  • An escalation/advocacy path and the not-legal-advice line are present

Anti-Patterns

  • Do not over-disclose medical detail — the barrier and the fix are what matter
  • Do not assert specific legal entitlements or "undue hardship" thresholds as fact — they vary; route to the process and to advocacy
  • Do not frame it as asking a favor — it's a request to remove a barrier, often a legal duty
  • Do not counsel giving up at first refusal — the interactive process and escalation exist for exactly that
  • Do not treat retaliation as normal — flag it and route to real help

Related

[[disability-disclosure-decision]] for the whether/how of telling work at all; [[disability-benefit-appeal]] for the benefits side; [[venue-access-check]] and [[accessible-travel-planner]] for physical access; [[nt-translator]] for the workplace- communication layer.

Frequently asked questions

What does the Accommodation Request AI skill do?

Request a reasonable accommodation at work or in education — frame it around the barrier and the adjustment (not your diagnosis), cite the right process, and navigate the back-and-forth constructively. Use when someone says 'I need a workplace accommodation', 'request reasonable adjustments', 'ADA/Equality Act accommodation', or 'how do I ask for accommodations for my disability/condition'. Produces the request letter, a barriers-and-adjustments map, disclosure guidance, and a plan for the interactive process. Not legal advice — routes to the formal process and to advocacy where needed.

Why use Accommodation Request on TypingMind?

Because you install it once and use it with any model. Accommodation Request 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 Accommodation Request in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/mohitagw15856/pm-claude-skills/tree/main/exports/openclaw/accommodation-request. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Accommodation Request?

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 Accommodation Request?

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

Is the Accommodation Request AI skill free?

Yes. It is published on GitHub by mohitagw15856 under the MIT 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 👇