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

Hr Performance Improvement Plan

ASecurity

Drafts a passable Performance Improvement Plan with the specific gap and dated examples, SMART expectations, the support offered, review points and the possible outcomes, after a pre-check of who decided a PIP is warranted. Use for "run hr-performance-improvement-plan", "write a PIP", "performance improvement plan", "how to write a performance improvement plan", "PIP template", "put someone on a PIP", "our PIPs never work", "set PIP check-ins", part of the AI for HR Pack by Polar Bear.

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 hr-performance-improvement-plan --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Hr Performance Improvement Plan?

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

Security grade badge for Hr Performance Improvement Plan
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-hr-performance-improvement-plan/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-hr-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: hr-performance-improvement-plan
description: Drafts a passable Performance Improvement Plan with the specific gap and dated examples, SMART expectations, the support offered, review points and the possible outcomes, after a pre-check of who decided a PIP is warranted. Use for "run hr-performance-improvement-plan", "write a PIP", "performance improvement plan", "how to write a performance improvement plan", "PIP template", "put someone on a PIP", "our PIPs never work", "set PIP check-ins", part of the AI for HR Pack by Polar Bear.
---

# Performance Improvement Plan (PIP)

## When To Use
Everyone says nobody comes back from a PIP, and you need one that is actually passable. A manager has a documented performance gap, coaching has not closed it, and you need a plan that states the standard, the help and the dates so the employee can genuinely meet it.

## When Not To Use
If the issue is conduct (lateness as a rule breach, rudeness, a policy breach) rather than capability, use Disciplinary Procedure. If the person is still in probation, use Probation Review. If someone has already decided the person is leaving, stop: a PIP does not replace that decision, and writing one as a formality is the failure this skill exists to prevent.

## Inputs
- Who decided a PIP is warranted, and when; what coaching or feedback came first, with dates
- The gap (specific work, dates, effect, from the manager's records) and the role's expectations
If you have none of this, I start from the pre-check alone and mark the output as a first draft; I do not write a gap from impressions.

## Approach
The plan follows the SHRM guidance on performance improvement plans (shrm.org, "8 Steps for Effective Performance Improvement Plans"): a documented gap, a clear standard, support, regular check-ins and a stated end. Each expectation is written to SMART, from Doran's 1981 Management Review paper (summary at en.wikipedia.org/wiki/SMART_criteria). The judgment is that a PIP is expectations plus support, never a rating: it describes work, not the person. The failure it prevents: a plan full of adjectives ("lacks ownership") that nobody could pass because nobody can say what passing looks like.

## Workflow
1. Ask three questions: who decided a PIP is warranted and on what date; where does the person work (country, and state or province where it matters); how long a plan and how often you will meet (SHRM describes a minimum of 30 days, with 60 or 90 more usual; you set it).
2. Run the pre-check and stop if any line fails: a named manager made the call; coaching came first; this is capability, not misconduct; no decision to dismiss has been made. If the stated purpose is to exit someone, I say so and do not draft.
3. Write the gap as observable facts only: the work, the date, the effect. Strip every adjective about the person; if a line cannot be made factual, it goes back to the manager.
4. Turn each gap into one SMART expectation: specific, measurable, assignable, realistic, time-related. Keep it to three or four; ten objectives is a plan built to fail.
5. List support against each expectation: training, resources, manager time, and adjustments to consider. If the manager cannot commit to the check-ins, the plan does not start.
6. Set review points weekly or every two weeks, each with a short written summary of the manager's facts. Leave, sickness, health or disability raised during the plan pauses it for an adviser.
7. State the possible outcomes plainly (met, extended, next step under your procedure), who decides and when, and the adviser questions for the person's country.

## Output Format
```markdown
# Performance Improvement Plan
**Employee:** [name] **Manager:** [name] **Dates:** [start] to [end] **PIP decided by:** [name] on [date]
## The gap
| Work or task | Date | What happened | Effect |
|---|---|---|---|
| [example: report] | [date] | [fact from the manager] | [effect] |
## Expectations and support
| Expectation (SMART) | Measure | By | Support offered | Owner |
|---|---|---|---|---|
| [expectation] | [measure] | [date] | [training, time, resource] | [name] |
## Check-ins
| Date | Progress (manager's facts) | Support given | Employee's comments |
|---|---|---|---|
| [date] | [facts] | [support] | [their words] |
## Possible outcomes
[Met: plan closes. Extended: to [date], reason recorded. Not met: next step under [procedure].]
## Adviser questions
- [Confirm with a qualified adviser for [country]: status of a PIP, leave or health during the plan, next step]
## Decision
[Named person] decides the outcome at the final review on [date], from the check-in record.
```

## Done When
- The pre-check passes and names who decided a PIP is warranted, with the date
- Every gap line is a dated fact about work; no adjective describes the person
- Each expectation meets all five SMART tests and has support against it
- Check-in dates are in the manager's diary and the outcome decider is named

## Quality Bar
- Never write an assessment or rating of the person (attitude, commitment, potential, fit); the plan measures work against the expectation
- No invented targets, dates or durations; unknowns stay [placeholders]
- Check-in notes are the manager's facts, never Claude's evaluation
- Claude writes the process, never the verdict: it never screens, ranks, scores or reads people, a named person decides and signs every decision about someone, and every legal point goes to a qualified adviser for the country it concerns.

## Next
Run hr-disciplinary-procedure (Disciplinary Procedure) so the next step after the plan is written before it is needed.

## 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', ...

698431 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 →