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/small-talk-survival)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/small-talk-survival"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/small-talk-survival/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/small-talk-survival"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/small-talk-survival.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 | $0.00132 | $0.01070 |
| Opus 5 | $0.00066 | $0.00535 |
| Sonnet 5 | $0.00026 | $0.00214 |
| Haiku 4.5 | $0.00013 | $0.00107 |
Grade A, and why
small-talk-survival 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 12d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Small-Talk Survival
Small talk feels pointless and excruciating to a lot of people — but it's the bridge every real connection crosses first. The good news: it's a learnable skill, not a personality trait. This gives you openers that fit the moment, the trick to keeping conversation flowing (genuine curiosity + follow-up questions), how to steer past the weather toward something you'd actually enjoy talking about, and clean ways to exit — for the specific situation you're dreading.
What This Skill Produces
- Openers for the setting — situation-appropriate ways to start (a comment on the shared context beats a canned line)
- The keep-it-flowing technique — genuine curiosity and follow-up questions ("oh, how come?") that carry a conversation, plus the small self-disclosures that make it two-way
- The upgrade path — how to move past surface topics to something more interesting, so it's not just weather-and-weekend
- Graceful exits — polite, non-awkward ways to end a conversation and move on
- The reframe — small talk as a low-stakes bridge to real connection (and that the other person often finds it hard too), which lowers the pressure
Required Inputs
Ask for these if not provided:
- The situation — the event/setting you're facing (party, work event, meeting new people, a specific person)
- What's hard — starting, keeping it going, running out of things to say, or exiting
- Your goal — just survive it, or actually connect with someone
- Any specifics — who'll be there, shared context to draw on
Framework: Open, Flow, Deepen, Exit
- Open from the shared context. The setting hands you material — the event, the food, the reason you're both there. A genuine comment or question beats a memorized line.
- Be curious, ask follow-ups. The secret to flowing conversation is genuine interest — ask a question, then follow up on their answer ("what was that like?"). People enjoy being asked about.
- Disclose a little. Pure Q&A feels like an interview; add small bits about yourself so it's mutual.
- Steer toward the interesting. Nudge past weather/logistics toward what someone's into, excited about, or working on — that's where small talk becomes real talk.
- Exit gracefully. Have a couple of clean lines ("I'm going to grab a drink — it was great talking to you") so you're never trapped or abrupt.
- Reframe the stakes. It's a low-stakes bridge, the other person often finds it hard too, and a slightly awkward moment is completely forgettable.
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.
- 12d ago First seen · 67 lines · 132 tokens per session scan A 96dddb3eb00a
small-talk-survival is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,352 stars, last pushed 4d ago), licensed MIT. It adds 132 tokens to every session and 1,070 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.