PM Skills is a collection of plain-Markdown instructions that teach AI assistants structured methods for handling professional, personal, and life-admin tasks. People use it with Claude, ChatGPT, Gemini, Cursor, Codex, and other supported agents for work such as writing product requirements, reviewing documents, or planning difficult situations.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/give-hard-feedback-kindly)<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/give-hard-feedback-kindly"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/give-hard-feedback-kindly/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/mohitagw15856/pm-claude-skills/give-hard-feedback-kindly"><img src="https://agentmods.dev/badge/rules/mohitagw15856/pm-claude-skills/give-hard-feedback-kindly.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00132 | $0.01069 |
| Opus 5 | $0.00066 | $0.00535 |
| Sonnet 5 | $0.00026 | $0.00214 |
| Haiku 4.5 | $0.00013 | $0.00107 |
Grade A, and why
give-hard-feedback-kindly scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- 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.
- 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.
- Open honestly, get to the point. Signal it's meant constructively, then say the thing — burying the lede prolongs the discomfort and confuses them.
- Attack the behavior, not the character. "When X happened, the impact was Y" lands; "you're careless/lazy" wounds and triggers defense.
- Invite their side. Ask genuinely for their perspective — you may be missing context, and it makes it a conversation, not a verdict.
- Land on a path forward. End with what good looks like and a concrete next step — feedback without a path is just criticism.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 13d ago First seen · 71 lines · 132 tokens per session scan A 4c0df8c46dca
give-hard-feedback-kindly is a cursor rule published in the GitHub repository mohitagw15856/pm-claude-skills (1,357 stars, last pushed yesterday), licensed MIT. It adds 132 tokens to every session and 1,069 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other cursor rules, from other repositories
cursor
Always-on my-adhd-caveman. Off with "stop adhd-caveman" or "normal mode".
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.
dev-standard
Apache Superset development standards and guidelines for Cursor IDE.
cli-error-handling
CLI command error handling patterns.
prefer-direct-imports-over-module-mocks
Prefer extracting a testable core over vi.mock / vi.resetModules when unit tests need to reach production logic entangled with config, env, or singletons.