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/jury-duty-navigator)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/jury-duty-navigator"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/jury-duty-navigator/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/jury-duty-navigator"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/jury-duty-navigator.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 | $0.00135 | $0.01389 |
| Opus 5 | $0.00068 | $0.00694 |
| Sonnet 5 | $0.00027 | $0.00278 |
| Haiku 4.5 | $0.00014 | $0.00139 |
Grade A, and why
jury-duty-navigator 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 9d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Jury Duty Navigator Skill
A jury summons lands with a jolt of dread and a stack of questions: is this even real, do I have to, what about work, can I move it? Most of that dread is uncertainty, and the summons itself answers much of it. This skill demystifies the process, helps you respond correctly and on time (missing a real summons has real consequences), and — where you have a genuine hardship or conflict — helps you request a deferral or excusal the legitimate way. It routes anything binding to the court, and it does not help anyone dodge a civic duty they're able to serve.
What This Skill Produces
- A response plan: what the summons requires and by when, so nothing is missed (responding on time is itself often mandatory)
- A scam check: real courts don't demand payment, gift cards, or SSNs by phone — the "you missed jury duty, pay a fine now" call is a common scam, and this flags it
- A deferral or excusal request, if you genuinely qualify: the legitimate grounds (dates, hardship, caregiving, medical, prior commitments) and how to ask, on the court's own process
- The logistics: work notification and your pay/leave rights (routed to verify), what to bring, and a plain what-to-expect-on-the-day walkthrough to defuse the fear
Required Inputs
Ask for (if not already provided):
- What the summons says (jurisdiction, dates, what response it requires and by when)
- Whether there's a genuine conflict or hardship (a booked trip, a caregiving duty, a medical issue, exam dates) — vs simple reluctance
- Work situation and whether they know their employer's jury-leave policy / legal protections
- First-timer nerves vs specific procedural questions
Framework
- Confirm it's genuine, then respond on time. Verify the summons is from the real court (via the court's own published contact, not a number in a suspicious message) and calendar the response deadline immediately — in many places responding is compulsory even if you'll seek to be excused. On-time response is the first duty.
- Screen the scam version. A phone call or text claiming you missed jury duty and must pay a fine / buy gift cards / confirm your SSN to avoid arrest is fraud — no court works that way. If that's what prompted this, the skill's main job is to stop the user paying and route them to report it.
- Separate genuine conflict from reluctance — honestly. Legitimate grounds for deferral (moving the date) or excusal (being released) typically include prebooked travel, caregiving with no alternative, medical issues, financial hardship, or recent prior service — and they vary by court. The skill helps make a real case the proper way; it will not manufacture an excuse or coach evasion for someone simply unwilling.
- Make the request the court's way. Draft the deferral/excusal request to the court's stated process and grounds, with the documentation they ask for, submitted by their deadline. Prefer deferral (serve later) over excusal where the issue is timing — courts grant it more readily.
- Sort work, pay, and the day itself. Notify the employer (jury leave is often legally protected — route to verify local rights and any pay/reimbursement), pack what the summons requires, and walk through the actual day (check-in, waiting, selection, that most summoned people aren't seated) so the unknown stops being scary.
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.
- 9d ago First seen · 110 lines · 135 tokens per session scan A c39759f31fbb
jury-duty-navigator is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 135 tokens to every session and 1,389 once invoked, about $0.0007 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.