SkillMachine
All skills

Reasonable Accommodation Advisor

Report

Turns an employee request into a defensible reasonable-accommodation package

Live output preview

Input Format: Input FormatOutputWatch the Output: Watch the Output

A plan is required to view this content

Choose a plan to access input format, sample outputs, and live previews.

View Plans →

About the skill

What it does

The Reasonable Accommodation Advisor processes an incoming employee accommodation request through the four steps of the EEOC interactive process: (A) it extracts the role's essential functions and separates them from marginal tasks; (B) it resolves the request into a functional limitation (sensory / executive function / attention-focus / social-communication / processing / physical axes) and ties it to the essential function it blocks; (C) it generates 2-4 concrete accommodation options; (D) it selects the most suitable one while respecting the employee's preference. Every option passes an undue hardship test and receives a Low/Medium/High burden label from net-cost × operational-impact. The output is a 0-100 Compliance/Safety Score, a verdict, a ranked accommodation matrix and defensible decision documentation that also records why options were rejected.

The skill makes no clinical diagnosis and gives no binding legal opinion; it produces a functional-need → accommodation mapping and a decision record.

When to use it

When an employee/candidate sends a specific accommodation request ("I need X", "I can't do Y"); when HR wants a defensible response + rationale; when the question "is this reasonable, is it undue hardship, what's the alternative?" arises; when an accommodation package needs validation for legislative (TR/US) and ethical cleanliness. The sibling skill audits a role proactively; this one processes an incoming request.

Method / frameworks

Judgment binds to named canon, not intuition. Six industry-standard frameworks run together: (1) EEOC Interactive Process (4 steps, legal backbone); (2) Essential Functions test (essential↔marginal split — a request removing an essential function isn't reasonable); (3) Undue Hardship cost-benefit test grounded in JAN/ODEP field data (~49-56% of employers report zero cost, one-time median ≈ $300-500); (4) Universal Design / UDL (CAST's 3 principles — build an inclusive environment rather than per-person fixes); (5) Accommodation Taxonomy, 4 clusters (assistive tech · environmental/sensory · managerial/relational · psychosocial/skill); (6) JD-R framework (Bakker & Demerouti — demand-reducing vs resource-increasing; side scales UWES, MBI, Edmondson psychological safety). Options are ranked by a RICE-derived score (Impact × Reach × Confidence ÷ Burden). The legal layer is TR Labor Law Art.30 + KVKK Art.6 + 6701 TİHEK, or US ADA Title I.

How do I use this skill?

You don't "run" a skill — after installing it you just tell the agent your task (e.g. ask for the relevant job), and the skill kicks in by itself when its description matches.

Upload the makul-duzenleme-rehberi.zip you downloaded as-is — no packaging needed, the format is already correct (folder at root).

  1. Open Settings → Customize → Skills
  2. Upload → select the makul-duzenleme-rehberi.zip you downloaded
  3. Claude reads SKILL.md; the name + description appear. Ready ✅

Scripts run in Anthropic's code-execution environment (sandbox) — not on your machine.