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/support-a-friend-in-crisis)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/support-a-friend-in-crisis"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/support-a-friend-in-crisis/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/support-a-friend-in-crisis"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/support-a-friend-in-crisis.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 | $0.00137 | $0.01241 |
| Opus 5 | $0.00068 | $0.00620 |
| Sonnet 5 | $0.00027 | $0.00248 |
| Haiku 4.5 | $0.00014 | $0.00124 |
Grade A, and why
support-a-friend-in-crisis 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 13d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Support a Friend in Crisis
When someone you care about is going through something awful, the fear of saying the wrong thing makes many people freeze and pull away — exactly when their friend needs them most. Showing up well is a skill: it's less about perfect words and more about presence, not-fixing, and concrete help. This tells you what to say (and the clichés to avoid), how to be there over time, and when it's beyond what a friend can hold.
What This Skill Produces
- What to actually say — simple, genuine words that acknowledge their pain, and the well-meant clichés to avoid ("everything happens for a reason," "at least...," "let me know if you need anything")
- Presence over fixing — how to just be there and listen, rather than rushing to solve or advise (most people want to feel accompanied, not fixed)
- Concrete help — specific, low-burden offers ("I'll drop off dinner Tuesday") instead of the vague "let me know," which they'll never take up
- Showing up over time — how to keep supporting past the first week, when everyone else has moved on and it's often hardest
- Looking after yourself — supporting someone in crisis is draining; how to sustain it without burning out
- The professional line — a clear flag for when it's beyond a friend (self-harm risk, deep depression, danger) and how to steer them to real/crisis help
Required Inputs
Ask for these if not provided:
- What they're facing — the crisis (loss, illness, breakup, job loss, mental health)
- Your relationship — how close, and how they tend to cope
- What's worrying you — saying the wrong thing, not knowing how to help, or concern for their safety
- What you've done so far — and how they've responded
- Any risk signs — anything suggesting they need professional/crisis support
Framework: Be There, Help Concretely, Know The Line
- Acknowledge simply. Genuine, plain words ("I'm so sorry, this is awful, I'm here") beat any clever comfort. Don't reach for silver linings or fixes.
- Be present, don't fix. Listen, sit with them, let them feel it — most people in pain want company and validation, not solutions or advice they didn't ask for.
- Avoid the clichés. "Everything happens for a reason," "at least...", "stay strong," and the vague "let me know if you need anything" all land badly — steer clear.
- Offer concrete help. Replace "let me know" with specific, easy-to-accept offers (a meal, a ride, handling one task) — people in crisis can't organize help, so make it effortless.
- Keep showing up. Support fades after the first wave; being there weeks later — a check-in text, remembering — matters enormously when others have moved on.
- Protect yourself. You can't pour from empty; pace your support and get your own.
- Know the line. If there's risk of self-harm, severe depression, or danger, gently but clearly help them get professional or crisis support — a friend isn't a substitute.
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.
- 13d ago First seen · 72 lines · 137 tokens per session scan A 30613432dbfa
support-a-friend-in-crisis is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 137 tokens to every session and 1,241 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 2026-08-30.
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.