agentleFS
itseffiitseffi/agentic-os/.agents/skills/difficult-conversations/SKILL.md

difficult-conversations

Skill114 starsChanged 10 months agoMITView on GitHub

Prepare for challenging conversations using Prepare-Listen-Empathize-Clarify-Solve framework.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 4 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Before any conversation you're dreading or that has conflict potential.

    line 12
  2. Distinctive:

    Create openers that are:

    line 29
  3. Very specific:

    Use open questions (what/how/when):

    line 41
  4. Distinctive:

    Avoid "why" framing (feels accusatory)

    line 42
  5. Distinctive:

    Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

    line 81

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Difficult Conversation Prep

Prepare for challenging work conversations using a structured framework.

When to Use

Before any conversation you're dreading or that has conflict potential.

The Framework: Prepare-Listen-Empathize-Clarify-Solve

1. Preparation Notes

Document:

  • Your intent (what you want to achieve)
  • Non-negotiables (what you won't compromise on)
  • Specific facts/examples (concrete, not accusations)
  • Language traps to avoid
  • Desired outcome
  • Success criteria
  • Medium choice (in-person/video/async)

2. Opening Lines (3-5 options)

Create openers that are:

  • Neutral, non-accusatory
  • Reference concrete impact
  • Invite their perspective

Examples:

  • "I wanted to talk about [situation] because I've noticed [impact]..."
  • "I'd like to understand your perspective on [issue]..."
  • "Can we discuss [topic]? I want to make sure we're aligned..."

3. Questions to Ask (5-7)

Use open questions (what/how/when):

  • Avoid "why" framing (feels accusatory)
  • Include one perspective-taking question
  • Include one constraints question

4. Anticipate Reactions

Prepare responses for:

  • Denial: [De-escalating response]
  • Deflection: [Redirect response]
  • Emotional reaction: [Calming response]
  • Counter-accusation: [Non-defensive response]

5. Clarify and Solve

  • State shared goals
  • Present options with trade-offs
  • Agree on commitments
  • Assign owner and timeline
  • Schedule follow-up

Self-Management Checklist

  • Deep breaths before starting
  • Slow speaking pace
  • Use pauses deliberately
  • Notice body tension
  • Stay curious, not defensive

Output

  • 1-page prep doc
  • Opening lines (3-5)
  • Questions list
  • Reactions/responses table
  • Close and next steps
  • Escalation flags (if HR/compliance needed)

When Not to Use

Do not use this skill when the request is unrelated, low-stakes, or better handled by a simpler direct response.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.