PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/disability-benefit-appeal)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/disability-benefit-appeal"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/disability-benefit-appeal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/disability-benefit-appeal"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/disability-benefit-appeal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00124 | $0.01418 |
| Opus 5 | $0.00062 | $0.00709 |
| Sonnet 5 | $0.00025 | $0.00284 |
| Haiku 4.5 | $0.00012 | $0.00142 |
Grade A, and why
disability-benefit-appeal scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Disability Benefit Appeal Skill
Disability benefits are denied at high rates on first application, and a large share of those denials are overturned on appeal — which means a denial is often the start of the process, not the end. But appeals are lost on avoidable things: missing the short deadline, re-submitting the same application instead of answering the specific reason for refusal, and describing a good day instead of the worst day. This skill decodes why you were denied, builds the case that speaks to the actual eligibility criteria, and gets you organized for the hearing. It does not give legal advice or guarantee outcomes — it structures your evidence and routes you to the free specialist advice that materially raises success rates.
What This Skill Produces
- A decoded denial: what the decision letter actually says you failed to meet, in plain language, separated from boilerplate
- An appeal strategy mapped to the criteria: for each point of refusal, the specific evidence and description that answers it — appeals are won by rebutting the refusal, not restating the claim
- An evidence checklist: the medical records, functional descriptions, and third-party statements that carry weight, and how to request them ([[medical-records-request]])
- A personal statement draft in the framework assessors use (how the condition affects daily function on a bad day, consistently, not at your best) and hearing prep if it goes that far
Required Inputs
Ask for (if not already provided):
- The benefit and country/system (SSDI/SSI in the US, PIP/DLA/ESA/UC in the UK, etc. — criteria and process differ completely), and the denial letter's stated reasons
- The appeal deadline (often short — this is the first thing to pin down)
- The condition(s) and how they actually affect daily function, honestly and at worst
- What evidence exists already and what's missing
Framework
- Deadline first — it's a hard gate. Appeal windows are short and missing them can end the case regardless of merit. Pin the exact deadline from the letter and make the whole plan fit inside it; if it's tight, the request-more-time or interim step comes first.
- Decode the actual refusal. The letter's boilerplate hides a few specific findings ("you can walk 50m," "you scored X points," "your condition isn't 'severe'"). Extract those — the appeal must answer these, not make the original case louder.
- Map evidence to each refusal point. For every finding, name what would rebut it: a consultant's letter on mobility, a functional report, a medication list, statements from people who see your daily reality. Generic "I'm unwell" evidence loses; evidence aimed at the specific criterion wins.
- Describe the bad day, consistently. The single most common self-inflicted loss: describing function on a good day, or "managing." Assessors judge against criteria about repeatability, safety, and reliability — so the statement describes the worst and typical days, what you can't do reliably/safely/repeatedly, with concrete examples. Honest, not exaggerated — but not stoically minimized either.
- Get free specialist help and prep the hearing. Disability-benefit advice services (welfare-rights orgs, legal aid, disability charities — free, and strongly correlated with success) should be engaged; the skill routes there explicitly. For a tribunal/hearing, prepare what to expect, the questions, and bringing a representative or supporter.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 118 lines · 124 tokens per session scan A c9290fb99241
disability-benefit-appeal is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 4d ago), licensed MIT. It adds 124 tokens to every session and 1,418 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other cursor rules, from other repositories
cursor
Always-on my-adhd-caveman. Off with "stop adhd-caveman" or "normal mode".
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.