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/elected-rep-letter)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/elected-rep-letter"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/elected-rep-letter/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/elected-rep-letter"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/elected-rep-letter.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 | $0.00115 | $0.01318 |
| Opus 5 | $0.00057 | $0.00659 |
| Sonnet 5 | $0.00023 | $0.00264 |
| Haiku 4.5 | $0.00012 | $0.00132 |
Grade A, and why
elected-rep-letter 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Elected Rep Letter Skill
Representatives' offices triage hundreds of messages by a simple filter: is this a constituent, with a specific ask, that affects the representative's standing? Most letters fail all three — they go to the wrong level of government, rage in generalities, and ask for nothing actionable, so they're counted as a tally mark and filed. This skill writes the version that lands: the right representative for the issue, a concrete ask they can actually act on, your local stake stated plainly, and a reason it's in their interest — then a follow-up that turns one letter into pressure.
What This Skill Produces
- The right target: which representative and level of government actually owns this issue (writing your national rep about a pothole wastes everyone's time)
- A targeted letter or call script: specific ask → your constituent stake → why it serves them → a requested response by a date, in a tone that's firm without being the rage-email that gets ignored
- The credibility hooks: you're a constituent (say so, with your area), the issue's local impact, and any personal story that makes it real
- A follow-up plan: what to do with silence, a template response, or a brush-off — because one letter is a data point; persistence plus visibility is leverage
Required Inputs
Ask for (if not already provided):
- The issue and the specific outcome wanted (a vote, a meeting, an intervention, a service fix) — "do something about X" isn't an ask
- Where the user lives (to identify the right rep) and whether they know who represents them at each level
- Their personal stake and any story: how this affects them or their community concretely
- What's been tried (a prior ignored letter changes the strategy toward escalation/ visibility)
Framework
- Get the level of government right. Pothole/parking/local-service → councillor/ local. Schools, policing, state services → state/regional. National law, federal agencies → national rep. A letter to the wrong level is a guaranteed non-answer; identify the owner first (route to the "who represents me" lookup where needed).
- Lead with one specific, actionable ask. Not "care about housing" but "vote yes on Bill 12," "hold a surgery on the ward closure," "instruct the council to fix the drainage on Elm Street." An office can act on a specific ask and can't act on a feeling. One ask per letter.
- Establish constituent standing immediately. Reps prioritize the people who vote for them. State that you're a constituent and your area up top — it moves the letter from "public" to "must-log-and-respond" in most offices.
- Make it their interest, and make it human. Briefly, why acting serves them (constituent concern, local visibility, a problem they'd own if it worsens), plus one concrete human detail that a staffer remembers. Anger without an ask reads as noise; a specific local story with an ask reads as a live issue.
- Request a response, then follow up. Ask for a reply by a reasonable date. Then the escalation ladder for the likely outcomes: silence → a chasing note + a call → the ward surgery/town hall; a form reply → a pointed follow-up naming it; and, where appropriate, multiplying voices (neighbors sending their own) and local-press visibility. Persistence is the actual lever.
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 · 106 lines · 115 tokens per session scan A 2210c642053f
elected-rep-letter is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 115 tokens to every session and 1,318 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
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.
control-plane-descriptors
Control plane descriptor and instance implementation patterns.