Agent skill

Give Hard Feedback Kindly

by mohitagw15856 in 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.

MITAuto-check passed

Install Give Hard Feedback Kindly

skills CLI
$ npx skills add mohitagw15856/pm-claude-skills --skill give-hard-feedback-kindly -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mohitagw15856/pm-claude-skills give-hard-feedback-kindly --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/give-hard-feedback-kindly .claude/skills/give-hard-feedback-kindly && rm -rf skills-src

Use ~/.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/

Facts

Skill name
give-hard-feedback-kindly
GitHub stars
1.4k
Token cost
~1.2k tokens
SKILL.md length
603 words
Files
1
Skills in repo
1,348
Repo updated
First seen
Licence
MIT

At a glance

Give someone difficult feedback — a report, a peer, a friend — so it actually lands and helps, without crushing them or dodging the point.

  • Works in 6 steps: Get specific. Vague feedback ("be more… → Care and be clear at once. Genuine care… → Open honestly, get to the point. Signal… → …
  • Asked how do I give hard feedback
  • SKILL.md covers What This Skill Produces, Required Inputs, Framework: Direct And Kind,… and Output Format, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Give Hard Feedback Kindly is an agent skill from 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. Use when asked how do I give hard feedback, tell someone something difficult, address a problem with someone, or have a tough conversation about their [work/behavior]. Produces a read on what you actually need to say (the specific behavior and its impact, not a vague vibe), a structure that's direct and kind at once, the exact opening and words, how to invite their side and…

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.

When your agent uses it

  • Asked how do I give hard feedback
  • Tell someone something difficult
  • Address a problem with someone
  • Have a tough conversation about their [work/behavior]

Example prompts

  • “/give-hard-feedback-kindly”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Get specific. Vague feedback ("be more professional") can't be acted on and feels like an attack — pin the exact behavior and its concrete…
  2. Care and be clear at once. Genuine care for the person and directness about the problem — not one softened by the other. Skip the…
  3. Open honestly, get to the point. Signal it's meant constructively, then say the thing — burying the lede prolongs the discomfort and…
  4. Attack the behavior, not the character. "When X happened, the impact was Y" lands; "you're careless/lazy" wounds and triggers defense.
  5. Invite their side. Ask genuinely for their perspective — you may be missing context, and it makes it a conversation, not a verdict.
  6. Land on a path forward. End with what good looks like and a concrete next step — feedback without a path is just criticism.

What it can do on your machine

Read from SKILL.md and the folder at commit 1cbf1f0. 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

Give Hard Feedback Kindly loads about 1.2k tokens when it runs. Until then it costs about 161 tokens; SKILL.md has 603 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~161
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 603 words, ~1,178 tokens.

Download SKILL.mdSave it as .claude/skills/give-hard-feedback-kindly/SKILL.md (or your agent's skills folder).
name
give-hard-feedback-kindly
description
Give someone difficult feedback — a report, a peer, a friend — so it actually lands and helps, without crushing them or dodging the point. Use when asked how do I give hard feedback, tell someone something difficult, address a problem with someone, or have a tough conversation about their [work/behavior]. Produces a read on what you actually need to say (the specific behavior and its impact, not a vague vibe), a structure that's direct and kind at once, the exact opening and words, how to invite their side and land on a path forward, and the traps (sandwiching it away, going vague, making it about character).

Give Hard Feedback Kindly

Most people botch hard feedback two ways: they soften it until the point disappears (kind but useless), or they deliver it bluntly and defensively (clear but wounding). The skill is doing both at once — direct and caring. This helps you pin down the specific thing to say, structure it so it lands and helps, and handle their reaction — so the person leaves clear on what to change and still intact.

What This Skill Produces

  • The actual message — the specific behavior and its concrete impact (not a vague "you need to improve" or a mood)
  • A direct-and-kind structure — care for the person + clarity on the problem, without the compliment-sandwich that buries it
  • The opening and words — how to start (signal it's constructive, get to the point) and the specific phrasing
  • Space for their side — how to invite their perspective genuinely, not as a formality
  • A path forward — what good looks like and the concrete next step, so it's help, not just criticism
  • The traps — sandwiching the point into oblivion, going vague to avoid discomfort, and attacking character instead of behavior

Required Inputs

Ask for these if not provided:

  • The issue — the specific behavior/problem (push for specifics if it's vague)
  • The impact — what it's actually affecting (why it matters)
  • The relationship — report, peer, boss, friend, family (changes tone and standing)
  • History — first time raising it, or a pattern
  • Your goal — change the behavior while keeping the relationship

Framework: Direct And Kind, About Behavior

  1. Get specific. Vague feedback ("be more professional") can't be acted on and feels like an attack — pin the exact behavior and its concrete impact.
  2. Care and be clear at once. Genuine care for the person and directness about the problem — not one softened by the other. Skip the compliment sandwich that hides the message.
  3. Open honestly, get to the point. Signal it's meant constructively, then say the thing — burying the lede prolongs the discomfort and confuses them.
  4. Attack the behavior, not the character. "When X happened, the impact was Y" lands; "you're careless/lazy" wounds and triggers defense.
  5. Invite their side. Ask genuinely for their perspective — you may be missing context, and it makes it a conversation, not a verdict.
  6. Land on a path forward. End with what good looks like and a concrete next step — feedback without a path is just criticism.
Show full SKILL.md (210 more words)Show less

Output Format

Hard feedback: [the issue] · to [person] · [relationship]

What to actually say: [the specific behavior + its concrete impact]. Open with: [signal constructive intent + get to the point]. The message (direct + kind):

[Behavior + impact, plainly and caringly — no sandwich, no character attack]. Invite their side: "[genuine ask for their perspective]". Path forward: [what good looks like + the concrete next step]. Avoid: compliment-sandwiching it away · vagueness · making it about who they are.

Quality Checks

  • The feedback is specific (behavior + impact), not vague
  • It's direct and kind at once, without a burying sandwich
  • Opens honestly and gets to the point
  • Targets behavior, not character
  • Genuinely invites the person's perspective
  • Ends with a concrete path forward

Anti-Patterns

  • The compliment sandwich that hides the message.
  • Vagueness to avoid discomfort ("just do better").
  • Character attacks ("you're lazy") instead of behavior.
  • No path forward — criticism with no next step.
  • Not inviting their side — a verdict, not a conversation.

Example Trigger Phrases

  • "I need to give a team member hard feedback about missed deadlines."
  • "How do I tell a friend something difficult without hurting them?"
  • "Help me address a problem with a coworker's behavior."
  • "I have to have a tough conversation about someone's work. What do I say?"
  • "How do I give critical feedback that actually lands?"

© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/give-hard-feedback-kindly of mohitagw15856/pm-claude-skills.

Open the folder on GitHubat commit 1cbf1f0

Compare with similar skills

Give Hard Feedback Kindly 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.

Give Hard Feedback Kindly compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Give Hard Feedback Kindly this skillmohitagw15856/pm-claude-skills1.4k—~1.2kAutomated safety check: PassMIT
Giving FeedbackRefoundAI/lenny-skills1.4k—~2.2kAutomated safety check: PassMIT
Feedbackcodewhale-hq/Codewhale41k—~272Automated safety check: PassMIT
Feedback Masterydavila7/claude-code-templates33k2 repos~2.9kAutomated safety check: PassMIT
Feedbacknexu-io/nexu3.3k—~660Automated safety check: WarnMIT
Feedbacktinyfish-io/tinyfish-cookbook2.2k—~600Automated safety check: PassMIT

Similar skills

  • Giving Feedback

    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.

    1.4k GitHub stars~2.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Feedback

    codewhale-hq/Codewhale

    Report a Codewhale bug or idea as a GitHub issue. An agent skill from codewhale-hq/Codewhale.

    41k GitHub stars~272 tokensUpdated today
    Auto-check passed
  • Feedback Mastery

    davila7/claude-code-templates

    Navigate difficult conversations and deliver constructive feedback using structured frameworks.

    33k GitHub starsUsed in 2 repos~2.9k tokens
    Business, Finance & HRAuto-check passed
  • Feedback

    nexu-io/nexu

    Send feedback to the Nexu team. An agent skill from nexu-io/nexu.

    3.3k GitHub stars~660 tokensUpdated 5 mo ago
    Productivity & AutomationAuto-check: warnings
  • Feedback

    tinyfish-io/tinyfish-cookbook

    File structured feedback about TinyFish — bug reports, confusing setup steps, missing features, or a doctor diagnostic report.

    2.2k GitHub stars~600 tokensUpdated 2 days ago
    Testing & QAAuto-check passed
  • UX Feedback

    sickn33/agentic-awesome-skills

    Add appropriate user feedback states (loading, success, error, empty) to a component or page

    47k GitHub starsUsed in 1 repo~994 tokens
    Auto-check passed

More from mohitagw15856/pm-claude-skills

All 1,348 skills in this repo
  • Car Tco

    mohitagw15856/pm-claude-skills

    Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Cs Health Scorecard

    mohitagw15856/pm-claude-skills

    Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.

    1.4k GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Exit Waterfall

    mohitagw15856/pm-claude-skills

    Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Feature Prioritisation

    mohitagw15856/pm-claude-skills

    Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.

    1.4k GitHub stars~2k tokensUpdated yesterday
    Auto-check passed
  • Fire Number

    mohitagw15856/pm-claude-skills

    Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.

    1.4k GitHub stars~1.1k tokensUpdated yesterday
    Auto-check passed
  • Freelance Rate

    mohitagw15856/pm-claude-skills

    Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.

    1.4k GitHub stars~1.2k tokensUpdated yesterday
    Auto-check passed

Questions about Give Hard Feedback Kindly

What does Give Hard Feedback Kindly do?

Give someone difficult feedback — a report, a peer, a friend — so it actually lands and helps, without crushing them or dodging the point. Give Hard Feedback Kindly is an agent skill from 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.

When should I use Give Hard Feedback Kindly?

Give Hard Feedback Kindly fits situations like: asked how do I give hard feedback; tell someone something difficult; address a problem with someone; have a tough conversation about their [work/behavior].

How do I install Give Hard Feedback Kindly in Claude Code?

Run `npx skills add mohitagw15856/pm-claude-skills --skill give-hard-feedback-kindly -a claude-code`. Or copy the skill folder (skills/give-hard-feedback-kindly in mohitagw15856/pm-claude-skills) into .claude/skills/give-hard-feedback-kindly in your project. Claude Code loads it when a task matches its description.

How do I install Give Hard Feedback Kindly in Codex?

Run `npx skills add mohitagw15856/pm-claude-skills --skill give-hard-feedback-kindly -a codex`. Or copy the skill folder (skills/give-hard-feedback-kindly in mohitagw15856/pm-claude-skills) into .agents/skills/give-hard-feedback-kindly in your project. Codex loads it when a task matches its description.

Can I use Give Hard Feedback Kindly 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 mohitagw15856/pm-claude-skills --skill give-hard-feedback-kindly -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/give-hard-feedback-kindly, .gemini/skills/give-hard-feedback-kindly, .github/skills/give-hard-feedback-kindly and .opencode/skills/give-hard-feedback-kindly in your project.

What does Give Hard Feedback Kindly need to run?

SKILL.md names no scripts, command-line tools or credentials: Give Hard Feedback Kindly is instructions for the agent only.

Does Give Hard Feedback Kindly 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 Give Hard Feedback Kindly 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 Give Hard Feedback Kindly use?

Give Hard Feedback Kindly 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 Give Hard Feedback Kindly use?

About 1.2k tokens (SKILL.md is roughly 4.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Give Hard Feedback Kindly?

Skills that share tags, products or a category with Give Hard Feedback Kindly: Giving Feedback (RefoundAI/lenny-skills, 1.4k stars), Feedback (codewhale-hq/Codewhale, 41k stars), Feedback Mastery (davila7/claude-code-templates, 33k stars) and Feedback (nexu-io/nexu, 3.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Give Hard Feedback Kindly?

mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,434 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 9, 2026.

Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.