giving-feedback
Skill0 starsChanged 2 months agoMITView on GitHub
Apply this skill whenever Nick is preparing to give feedback to someone — a direct report, a peer, a founder, a collaborator, or anyone else. Trigger on any signal that feedback is being planned or crafted: "I need to tell X that...", "how do I say this to...", "I want to give feedback on...", "how do I bring this up with...", "I'm going to talk to [person] about...", or any situation where Nick is trying to communicate a criticism, concern, or improvement suggestion to another person. Use this skill proactively even if Nick doesn't say the word "feedback" — if he's preparing to deliver a hard message, this skill applies.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- RefoundAI/lenny-skillstheir own version, first seen Jul 15, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- RefoundAI/lenny-skills★ 1.3ksame name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- blog-cold-readSkill
- content-proportion-checkSkill
- defensibility-checkSkill
- hamming-taste-principlesSkill
- idea-to-briefSkill
- learning-mediumSkill
- linear-write-cleanupSkill
- portable-handoffSkill
- saddles-positioningSkill
- session-stateSkill
- skill-auditSkill
- strategy-decisionsSkill
- transcript-auditSkill
- uncertainty-killerSkill
- writing-craftSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 37
No one has ever said no to this phrasing.
- Distinctive: line 40
Don't stage-manage the conversation.
- Distinctive: line 48
When Nick is preparing feedback for bioprocessing practitioners or technical collaborators, two additional considerations apply:
- Distinctive: line 55
Before helping Nick draft feedback, ask or infer:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Giving Feedback
Grounded in Adam Grant's framework: criticism buried in compliments backfires. The feedback sandwich — praise, criticism, praise — fails because opening praise seems insincere (people brace for the blow) and closing praise buries the message via primacy/recency effects. The recipient remembers first and last; the criticism gets lost in the middle.
Core principle
Be radically candid. Make the feedback feel like an act of investment, not judgment.
Four-step framework
1. Explain why you're giving the feedback
Signal that you're in their corner, not above them. This single move makes feedback ~40% more effective:
"I'm sharing this because I think highly of your work and I know you can reach that level."
Frame it around their potential and your belief in them — not your authority or expertise.
2. Take yourself off a pedestal
Reduce the power differential. Make it a peer conversation, not a verdict from on high:
"I've benefited a lot from people pushing me, and I want to pay that forward." "I'm still working on this myself — I thought if I noticed it, it might be useful to hear."
This is especially important when Nick (as a first-time Head of Marketing) is giving feedback up, across, or to senior practitioners who may be skeptical.
3. Ask if the person wants feedback
Giving people agency dramatically reduces defensiveness:
"I noticed a couple of things and wondered if you'd want some feedback."
No one has ever said no to this phrasing. Ownership over the choice to receive = openness to the content.
4. Have a transparent dialogue, not a manipulative monologue
Don't stage-manage the conversation. State what you observed, name your concern, check if they saw it the same way, then co-decide what to do:
"Here's what I observed. Here's why it concerned me. Do you see it the same way? Here's what I think we might do — what do you think?"
The goal is joint diagnosis, not delivery of a verdict.
Applying to Nick's context
When Nick is preparing feedback for bioprocessing practitioners or technical collaborators, two additional considerations apply:
- Credibility gap is real: Practitioners may be skeptical of marketing perspective on their domain. Lean heavily into steps 2 and 3 — humility and consent disarm this.
- Be specific and observational: "The way this was described in the job posting" not "your messaging is unclear." Practitioners respond to concrete evidence, not abstract critique.
Quick diagnostic
Before helping Nick draft feedback, ask or infer:
- Who is the recipient and what's the power dynamic?
- What's the specific behavior or output being addressed?
- What outcome does Nick want from the conversation?
Then apply the four steps to shape the approach.
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
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.

