The conversation you've rehearsed five times in your head, structured for the one time you'll actually have it.
The tool that turns a feedback conversation you keep postponing into a specific behavior, a specific impact, and a specific ask, short enough to have this week instead of next quarter.
Feedback conversations get postponed because the discomfort feels immediate while the cost of avoiding it feels distant, right up until it isn't. Most postponed feedback isn't complicated. It's one specific behavior and one specific ask, buried under weeks of imagining how badly it could go.
This tool separates the structure of what to say from the anxiety about saying it, and gets the actual conversation down to something you can have this week.
The conversation, structured.
Same feedback, same discomfort, run two ways.
A team lead has a direct report who consistently interrupts a more junior colleague in meetings, and has been meaning to raise it for a month.
You ask Claude how to give difficult feedback. You get a solid general framework: use "I" statements, be specific, focus on behavior not character.
Sound advice that leaves you exactly where you started: staring at a blank plan, still not sure what the first sentence out of your mouth should actually be.
It builds the actual conversation for this specific situation:
- →The specific pattern named: three meetings, one colleague, a visible drop in their participation
- →An opening line that names it in the first thirty seconds, no compliment sandwich
- →A prepared line for the most likely reaction, so the message survives the first pushback
It ends with the specific, observable ask, not "be better about this" but a concrete behavior change, and a closing line that keeps the relationship intact regardless of how the conversation goes.
The cold version told you the principles. This gave you the actual sentence to open with.
- ✦Managers with a recurring issue they haven't named directly yet
- ✦Anyone who's rehearsed a conversation in their head more than once without having it
- ✦Team leads addressing a behavior affecting the wider team
- →difficult-feedback.zip — a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →difficult-feedback-skill.md — plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts — anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, Gemini, and the API
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude gives you general feedback-conversation principles, be specific, use I-statements, that still leave you staring at a blank page. This builds the actual opening line, the specific behavior and impact, a prepared response to likely pushback, and the concrete ask, for your specific situation.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Tool itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full — see our refund policy.
Difficult Feedback is a conversation-structuring tool. Not a substitute for HR guidance on formal processes, and not appropriate for conversations with active legal or disciplinary implications.