Giving Feedback
mohitagw15856/pm-claude-skills
Turn a vague concern into specific, kind, actionable feedback.
Help users deliver high-impact feedback that drives behavior change while maintaining strong relationships and psychological safety through proven frameworks like GAIN and Radical Candor.
MITAuto-check passed
Install Giving Feedback
$ npx skills add RefoundAI/lenny-skills --skill giving-feedback -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install RefoundAI/lenny-skills giving-feedback --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/giving-feedback .claude/skills/giving-feedback && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "giving-feedback" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/giving-feedback into .claude/skills/giving-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "giving-feedback", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/RefoundAI/lenny-skills/tree/main/skills/giving-feedbackType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add RefoundAI/lenny-skills --skill giving-feedback -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install RefoundAI/lenny-skills giving-feedback --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/giving-feedback .agents/skills/giving-feedback && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "giving-feedback" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/giving-feedback into .agents/skills/giving-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "giving-feedback", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RefoundAI/lenny-skills --skill giving-feedback -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install RefoundAI/lenny-skills giving-feedback --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/giving-feedback .cursor/skills/giving-feedback && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "giving-feedback" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/giving-feedback into .cursor/skills/giving-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "giving-feedback", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/RefoundAI/lenny-skills.git --path skills/giving-feedback--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add RefoundAI/lenny-skills --skill giving-feedback -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install RefoundAI/lenny-skills giving-feedback --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/giving-feedback .gemini/skills/giving-feedback && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "giving-feedback" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/giving-feedback into .gemini/skills/giving-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "giving-feedback", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install RefoundAI/lenny-skills giving-feedbackInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add RefoundAI/lenny-skills --skill giving-feedback -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/giving-feedback .github/skills/giving-feedback && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "giving-feedback" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/giving-feedback into .github/skills/giving-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "giving-feedback", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add RefoundAI/lenny-skills --skill giving-feedback -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install RefoundAI/lenny-skills giving-feedback --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/RefoundAI/lenny-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/giving-feedback .opencode/skills/giving-feedback && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "giving-feedback" agent skill from https://github.com/RefoundAI/lenny-skills/tree/main/skills/giving-feedback into .opencode/skills/giving-feedback/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "giving-feedback", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
giving-feedback- GitHub stars
- 1.4k
- Token cost
- ~2.2k tokens
- SKILL.md length
- 1,328 words
- Files
- 3 (incl. references)
- Skills in repo
- 76
- Repo updated
- First seen
- Licence
- MIT
At a glance
Help users deliver high-impact feedback that drives behavior change while maintaining strong relationships and psychological safety through proven frameworks like GAIN and Radical Candor.
- Works in 4 steps: Preparation - Help the user structure… → Roleplay - Use the AI Voice Mode prompt… → Refinement - Review a draft of the… → …
- SKILL.md covers How to Help, Core Principles, Templates & Frameworks and Questions to Help Users, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Giving Feedback is an agent skill from RefoundAI/lenny-skills. Help users deliver high-impact feedback that drives behavior change while maintaining strong relationships and psychological safety through proven frameworks like GAIN and Radical Candor.
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files, including reference files (for example `references/artifacts.md` and `references/guest-insights.md`).
The repository describes itself as: 86 product management skills from Lenny's Podcast for Claude Code and AI agents. Hiring, user research, strategy, shipping, and more. The licence is MIT.
Example prompts
- “/giving-feedback”
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Preparation - Help the user structure their thoughts using the GAIN framework to ensure feedback is goal-oriented and evidence-based.
- Roleplay - Use the AI Voice Mode prompt to simulate the conversation and practice responding to potential defensiveness.
- Refinement - Review a draft of the feedback to remove judgmental labels and ensure the user is 'staying on their side of the net.'
- Debrief - Analyze the results of a feedback session and plan for necessary follow-up actions and commitments.
What it can do on your machine
Read from SKILL.md and the folder at commit 13598cc. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Giving Feedback loads about 2.2k tokens when it runs, and up to ~22k if it reads all its reference files. Until then it costs about 51 tokens; SKILL.md has 1,328 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from RefoundAI/lenny-skills at commit 13598cc, republished under its MIT licence (© RefoundAI). 1,328 words, ~2,230 tokens.
Download SKILL.mdSave it as
.claude/skills/giving-feedback/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- giving-feedback
- description
- Help users deliver high-impact feedback that drives behavior change while maintaining strong relationships and psychological safety through proven frameworks like GAIN and Radical Candor.
Giving Effective Feedback
Transform difficult conversations into catalysts for growth and high performance.
Help the user with giving effective feedback using insights from 30 guests and posts across Lenny's Podcast and Newsletter.
How to Help
- Preparation - Help the user structure their thoughts using the GAIN framework to ensure feedback is goal-oriented and evidence-based.
- Roleplay - Use the AI Voice Mode prompt to simulate the conversation and practice responding to potential defensiveness.
- Refinement - Review a draft of the feedback to remove judgmental labels and ensure the user is 'staying on their side of the net.'
- Debrief - Analyze the results of a feedback session and plan for necessary follow-up actions and commitments.
Core Principles
Care personally and challenge directly
Kim Scott: "Radical Candor is just what happens when you care personally and challenge directly at the same time. And I think it's probably best understood by what it's not because we all fail on one of those two dimensions or both of them multiple times a day."
Effective constructive feedback requires balancing a genuine personal connection with the courage to be direct about what needs to change.
Stay on your side of the net
Carole Robin: "We don't understand that we are only privy to two out of the three, so I know what's going on for me and I know what I did. I have no idea what happened on your end."
Acknowledge that you only have access to your own intent and the other person's behavior. Speak only to the impact that behavior had on you.
Frame feedback as a joint effort
Alisa Cohn: "You know, Matilda, I want to chat with you about the way you're interacting with your peers. So what I'm hearing from them is that you're missing deadlines on a regular basis and not letting them know you're missing the deadlines, and that also you're not fully keeping your team up to speed. And so they're kind of confused running around. Now, we both know that the most important way you can be successful here and also achieve your goals is to make sure that you are working with your peers in a way that's consistent and that they can count on you and you can count on them."
Position difficult feedback as a collaborative exercise intended to help the employee achieve their own professional goals and improve team coordination.
Prioritize mutual understanding
Rachel Lockett: "There's a misguided view that the goal is to convince the other person that what they're doing is wrong. Actually, the goal of any conflict is to create mutual understanding."
Focus conflict resolution on achieving shared clarity rather than proving who is right or wrong, recognizing that professionals are humans with emotions.
Separate identity from behavior
Dr. Becky Kennedy: "The idea of being good inside inherently requires us to separate behavior and identity. We infer a lot from people's behavior. Someone's late to work a lot, 'Oh, that person's lazy.' The quickest way to have an unproductive conversation is to lose sight of the fact that someone's good inside."
Avoid labeling employees with character traits like lazy. Instead, focus on specific, observable actions to prevent triggering defensive identity threats.
Dial down self-judgment
Matt Abrahams: "Strive for connection over perfection by daring to be dull. Just give the feedback. By doing that, you dial down the volume of self-evaluation, freeing up resources that can be used to really help you succeed."
Prioritize the needs of the recipient and the core message over your own performance anxiety or internal critic during the delivery.
Foster public debate through trust
Jeetu Patel: "Every management book that you read will tell you in public criticize in private. I fundamentally disagree with that notion. What you have to do is, is establish enough trust among the team so that you are comfortable critiquing and debating in public."
Build a foundation of trust that allows for rigorous critique of ideas in transparent forums rather than behind closed doors.
Commit to the growth journey
Alisa Cohn: "Hope for the future is so important. I know this is going to be challenging for you to hear, not going to promote you, but I want you to know this. It's really important to me that you're able to succeed in your career here, and so I want to continue to help you find opportunities to build your skills and to advance."
Reaffirm your commitment to an employee's future even when delivering difficult news, such as a denied promotion or performance gap.
Show full SKILL.md (575 more words)Show less
Templates & Frameworks
- GAIN Framework for Feedback (Introducing the GAIN framework for feedback: an evidence-based approach to giving feedback that people love, appreciate, and act on) - A four-part evidence-based framework for giving feedback that people are receptive to and act on. GAIN stands for Goal, Actions, Impacts, Next actions. The core
- Three Realities Model (Stay on Your Side of the Net) (Healing your co-founder relationship) - A framework for having difficult conversations without triggering defensiveness. In any interaction between two people, there are three realities: Person A's in
- GAIN Feedback Preparation Template (Introducing the GAIN framework for feedback: an evidence-based approach to giving feedback that people love, appreciate, and act on) - A fill-in template with prompts to prepare GAIN-framed feedback before a conversation. Available for download.
- Next Actions techniques for closing feedback conversations (Introducing the GAIN framework for feedback: an evidence-based approach to giving feedback that people love, appreciate, and act on) - Five specific techniques for turning feedback into concrete commitments
- AI Voice Mode role-play prompt for practicing feedback (Introducing the GAIN framework for feedback: an evidence-based approach to giving feedback that people love, appreciate, and act on) - A detailed prompt template for using AI voice mode to practice feedback conversations before having them
- Vocabulary of Feelings (Carole Robin) - A reference list of actual feeling words to help people accurately identify their emotions and avoid using 'I feel that...' statements.
- Observations vs. Judgments distinction (Introducing the GAIN framework for feedback: an evidence-based approach to giving feedback that people love, appreciate, and act on) - A core principle in GAIN feedback: share observations of actions and impacts, never judgments (critical or flattering)
- Acknowledge Your Own Contributions (Introducing the GAIN framework for feedback: an evidence-based approach to giving feedback that people love, appreciate, and act on) - A feedback principle where the giver names their own role in the problem to preempt defensiveness and model vulnerability
- Three Questions for Joint Problem-Solving (Healing your co-founder relationship) - A framework for generating solutions to co-founder or interpersonal conflicts by simultaneously answering three questions.
See references/artifacts.md for the full list with details.
Questions to Help Users
- "What is the specific, observable behavior you want to address, and what was its impact on you or the team?"
- "What is the shared goal that both you and the recipient ultimately care about in this situation?"
- "How have you contributed to the current situation or the problem you are addressing?"
- "Are you currently feeling a distancing emotion like anger, or a connecting emotion like hurt or fear?"
- "What specific commitments or 'who, what, by when' actions do you want to see as a result of this talk?"
- "How can you frame this feedback to move toward a gain rather than just away from a pain?"
Common Mistakes to Flag
- Prioritizing personal comfort - Withholding feedback to avoid an awkward moment is a selfish choice that stunts the other person's professional growth.
- The generic feedback request - Asking 'do you have any feedback for me?' rarely yields honest criticism; you must ask specific questions about what you should stop or start doing.
- Using distancing emotions - Using anger to create space during a conflict prevents the vulnerability required to repair and strengthen the relationship.
- Ignoring non-verbal cues - Failing to observe how the recipient is reacting can lead to your message being dismissed or causing unintended emotional harm.
Deep Dive
For all 27 sourced insights from 30 guests, see references/guest-insights.md
Related Skills
- Hiring Product Talent
- Interviewing Evaluating Candidates
- Org Design
- Building Growth Team
© RefoundAI, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 2 other files (references) in skills/giving-feedback of RefoundAI/lenny-skills.
- SKILL.md
- references/artifacts.md
- references/guest-insights.md
Open the folder on GitHubat commit 13598cc
Compare with similar skills
Giving Feedback next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Giving Feedback this skillRefoundAI/lenny-skills | 1.4k | — | ~2.2k | Automated safety check: Pass | MIT | |
| Giving Feedbackmohitagw15856/pm-claude-skills | 1.4k | — | ~897 | Automated safety check: Pass | MIT | |
| Feedbackcodewhale-hq/Codewhale | 41k | — | ~272 | Automated safety check: Pass | MIT | |
| Give Hard Feedback Kindlymohitagw15856/pm-claude-skills | 1.4k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Feedback Masterydavila7/claude-code-templates | 32k | 2 repos | ~2.9k | Automated safety check: Pass | MIT | |
| Feedbacknexu-io/nexu | 3.3k | — | ~660 | Automated safety check: Warn | MIT |
Similar skills
Feedback
codewhale-hq/Codewhale
Report a Codewhale bug or idea as a GitHub issue. An agent skill from codewhale-hq/Codewhale.
Give Hard Feedback Kindly
mohitagw15856/pm-claude-skills
Give someone difficult feedback — a report, a peer, a friend — so it actually lands and helps, without crushing them or dodging the point.
Feedback Mastery
davila7/claude-code-templates
Navigate difficult conversations and deliver constructive feedback using structured frameworks.
Feedback
nexu-io/nexu
Send feedback to the Nexu team. An agent skill from nexu-io/nexu.
Feishu Drive
openclaw/openclaw
Feishu cloud-storage and comment workflows. An agent skill from openclaw/openclaw.
More from RefoundAI/lenny-skills
All 76 skills in this repoCustomer Interviews
RefoundAI/lenny-skills
Help users conduct high-impact customer interviews that move beyond surface-level feature requests to identify root emotional frustrations and specific causal triggers.
Time Energy Management
RefoundAI/lenny-skills
Help users master their personal output by shifting from reactive scheduling to intentional energy management, internal trigger mastery, and proactive boundary setting.
User Onboarding Activation
RefoundAI/lenny-skills
Help users reach their first moment of core value by optimizing the first-run experience, removing friction, and aligning product design with psychological triggers.
Acquisition Channels
RefoundAI/lenny-skills
Help users identify unique distribution advantages and master the lifecycle of acquisition channels to build a sustainable engine for growth and retention.
AI Assisted Prototyping
RefoundAI/lenny-skills
Help users build functional product prototypes from natural language or visual mocks using AI coding tools.
AI Evals
RefoundAI/lenny-skills
Help users build robust infrastructure for measuring, monitoring, and iterating on AI product performance using human, code-based, and LLM-as-a-judge methodologies.
Questions about Giving Feedback
What does Giving Feedback do?
Help users deliver high-impact feedback that drives behavior change while maintaining strong relationships and psychological safety through proven frameworks like GAIN and Radical Candor. Giving Feedback is an agent skill from RefoundAI/lenny-skills. Help users deliver high-impact feedback that drives behavior change while maintaining strong relationships and psychological safety through proven frameworks like GAIN and Radical Candor.
How do I install Giving Feedback in Claude Code?
Run `npx skills add RefoundAI/lenny-skills --skill giving-feedback -a claude-code`. Or copy the skill folder (skills/giving-feedback in RefoundAI/lenny-skills) into .claude/skills/giving-feedback in your project. Claude Code loads it when a task matches its description.
How do I install Giving Feedback in Codex?
Run `npx skills add RefoundAI/lenny-skills --skill giving-feedback -a codex`. Or copy the skill folder (skills/giving-feedback in RefoundAI/lenny-skills) into .agents/skills/giving-feedback in your project. Codex loads it when a task matches its description.
Can I use Giving Feedback in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add RefoundAI/lenny-skills --skill giving-feedback -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/giving-feedback, .gemini/skills/giving-feedback, .github/skills/giving-feedback and .opencode/skills/giving-feedback in your project.
What does Giving Feedback need to run?
SKILL.md names no scripts, command-line tools or credentials: Giving Feedback is instructions for the agent only.
Does Giving Feedback access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Giving Feedback safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Giving Feedback use?
Giving Feedback is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Giving Feedback use?
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 20k tokens, read only when the agent opens those files.
What are the alternatives to Giving Feedback?
Skills that share tags, products or a category with Giving Feedback: Giving Feedback (mohitagw15856/pm-claude-skills, 1.4k stars), Feedback (codewhale-hq/Codewhale, 41k stars), Give Hard Feedback Kindly (mohitagw15856/pm-claude-skills, 1.4k stars) and Feedback Mastery (davila7/claude-code-templates, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Giving Feedback?
RefoundAI (a GitHub organization) maintains it in RefoundAI/lenny-skills, which has 1,381 GitHub stars. The repository holds 76 skills in this directory. The repository was last updated on July 16, 2026.
Source: RefoundAI/lenny-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.