Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Mgr Performance Improvement Plan

ASecurity

Drafts a performance improvement plan framed as support, with the expected standard, the observed gap as dated facts, a space for the person's side, the support offered with review dates, and questions for HR and an adviser. Use for "run mgr-performance-improvement-plan", "write a PIP", "performance improvement plan", "underperforming employee plan", "fair path for a report who is not doing the job", "performance support plan", "document a performance gap", part of the AI for Managers Pack by...

2 stars
0 votes
0 copies
0 views
Added 10/4/2026
ai-agentsgoperformance

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add polar-bear-org/claude-skills --skill mgr-performance-improvement-plan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Mgr Performance Improvement Plan?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Mgr Performance Improvement Plan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-mgr-performance-improvement-plan/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-mgr-performance-improvement-plan)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: mgr-performance-improvement-plan
description: Drafts a performance improvement plan framed as support, with the expected standard, the observed gap as dated facts, a space for the person's side, the support offered with review dates, and questions for HR and an adviser. Use for "run mgr-performance-improvement-plan", "write a PIP", "performance improvement plan", "underperforming employee plan", "fair path for a report who is not doing the job", "performance support plan", "document a performance gap", part of the AI for Managers Pack by Polar Bear.
---

# Performance Improvement Plan (PIP)

## When To Use
Someone is not doing the job and you need a fair path that you would defend, to them, to HR and to yourself. The informal conversations have happened, the gap is still there, and you may be quietly doing their work on top of yours. It answers: what is expected, what actually happened, what help is on the table, and when do we look again?

## When Not To Use
If no informal conversation has happened yet, start with Difficult Conversation Prep. If expectations were never written down, SMART Goals comes first; and if the issue is conduct rather than capability, this is not the tool, go to HR.

## Inputs
- The role's own documents or agreed goals that set the standard, and your performance policy if you have it
- Your dated notes of the gap and of earlier conversations
If you have none of this, I start from a plain description of the gap and mark the output as a first draft that HR must see before anyone else does.

## Approach
This follows Acas "Problems with an employee's performance": talk informally first, separate capability from conduct, look for causes such as training, workload, health or adjustments, then agree objectives, a reasonable timescale and real support, with a record the employee receives. Objectives are written in the specific, measurable, assignable, realistic and time-related form from Doran (1981). The failure it prevents: a plan written as a paper trail to exit someone, with no support in it and a gap nobody ever wrote down as a standard.

## Workflow
1. Ask at most three questions: has an informal conversation been held and when, is this capability or conduct, and have you spoken to HR. If conduct, or no informal talk yet, I stop and point you back.
2. Expected standard: written, observable, taken from the role's documents or agreed goals. If none exists, I say so: that is the first gap, and it is yours to fix.
3. Observed gap: dated facts beside the standard, one row each. I strip every adjective about the person and every prediction.
4. The person's side: a blank section for their account and the causes they name. Any health or disability cause is marked for HR or a qualified adviser, never interpreted.
5. Support offered: concrete items (training, coaching, time, tools, adjustments), each with who provides it and by when. A plan with an empty support column is not ready.
6. Objectives and timescale: you set them and HR confirms they are reasonable; review dates sit inside that timescale.
7. Questions for HR and an adviser: what happens if the gap closes or does not, which policy applies. I list the questions and never state consequences as advice.

## Output Format
```markdown
# Performance Improvement Plan
## Expected Standard
[Source document or agreed goal, quoted or summarised]
## Observed Gap
| Date | Standard | What happened (fact) |
|---|---|---|
| [date] | [standard] | [observable fact] |
## The Person's Side
[Left blank for their account and the causes they name]
## Support Offered
| Support | Who provides it | By when |
|---|---|---|
| [training, coaching, time, tool, adjustment] | [name] | [date] |
## Objectives and Reviews
| Objective | Review date | Evidence we will look at |
|---|---|---|
| [SMART objective] | [date] | [what counts] |
## Questions for HR and an Adviser
- [question]
## Decision
After each review, [name] decides with HR the next step, first on [date].
```

## Done When
- Every gap row has a date and a written standard beside it
- The person's side is present and left for them to fill
- HR has seen the draft before it goes to the person

## Quality Bar
- No judgement, rating, prediction ("unlikely to improve") or recommendation to dismiss, anywhere.
- No adjectives about the person; the gap is described as work against a standard.
- Every legal, health or disciplinary point is marked "check with HR or a qualified adviser".
- A support plan, not a verdict: Claude writes facts and support, never a judgement or rating, and a named person decides.

## Next
Run mgr-one-on-one-agenda (One-on-One Meeting Agenda) to run the review points inside regular 1:1s.

## About the makers

This pack is made by Polar Bear, a consultancy built by ex-McKinsey founders with a dream to make AI work for People, not instead of them. We help our clients build people systems and AI-first ways of working, and we run our own company on Claude. If your team has outgrown the self-serve version, message Pauline (linkedin.com/in/paulinebertry).

Attribution

polar-bear-orgpolar-bear-org
View sourceSee grades on GitHubMore from polar-bear-org →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →