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.
npx skills add cnfeat/top-pm-skills --skill having-difficult-conversationsgit clone --depth 1 https://github.com/cnfeat/top-pm-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/skills/cnfeat/top-pm-skills/having-difficult-conversations)<a href="https://agentmods.dev/skills/cnfeat/top-pm-skills/having-difficult-conversations"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/having-difficult-conversations/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/skills/cnfeat/top-pm-skills/having-difficult-conversations"><img src="https://agentmods.dev/badge/skills/cnfeat/top-pm-skills/having-difficult-conversations.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 | $0.00050 | $0.01335 |
| Opus 5 | $0.00025 | $0.00668 |
| Sonnet 5 | $0.00010 | $0.00267 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
having-difficult-conversations 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 10d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Having Difficult Conversations
Help the user navigate tough conversations with courage and skill using frameworks from 43 product leaders.
How to Help
When the user asks for help with a difficult conversation:
- Understand the situation - Ask what kind of conversation (feedback, performance, firing, conflict resolution, delivering bad news) and what makes it difficult for them
- Check their preparation - Ensure they have specific examples, a clear desired outcome, and have thought through the other person's perspective
- Choose the right framework - Match the situation to the appropriate structure (SBI, CORE, NVC, or Radical Candor)
- Role-play if helpful - Offer to practice the conversation so they can hear how it sounds and anticipate reactions
Core Principles
Radical Candor: Care personally AND challenge directly
Kim Scott: "Radical Candor is what happens when you care personally and challenge directly at the same time." Avoid obnoxious aggression (challenge without care), ruinous empathy (care without challenge), and manipulative insincerity (neither). Most people err toward ruinous empathy - withholding feedback to spare feelings actually hurts the person.
Use the Situation-Behavior-Impact framework
Paige Costello: "Situation, behavior, impact. The situation is on Tuesday in that meeting at 3:00. Behavior, you interrupted me while I was saying this thing. Impact, made me feel like you weren't listening." Keep it objective and specific. Describe what a camera would have recorded, not your interpretation of their motives.
Distinguish feelings from attributions
Carole Robin: "'I feel that you don't care' and 'I feel you're being insensitive' are not feelings. That's where we make our biggest mistakes." Use actual emotion words (hurt, disappointed, anxious) not "I feel that" or "I feel like" which introduce stories and accusations.
Stay on your side of the net
Carole Robin: "Stick with the two realities you know - your intent and their behavior. We get in trouble the minute we think we know the other person's reality." Only speak to what you observed and how it impacted you. Don't assume their motives.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 85 lines · 50 tokens per session scan A 5cc761e2c8c1
having-difficult-conversations is a skill published in the GitHub repository cnfeat/top-pm-skills (48 stars, last pushed 2mo ago), licensed MIT. It adds 50 tokens to every session and 1,335 once invoked, about $0.0003 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…