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 Investigation Report

ASecurity

Structures an investigation report that keeps allegation, evidence, findings of fact and open questions apart, leaves the decision to a named decision maker and indexes the evidence log. Use for "run hr-investigation-report", "write up the investigation", "investigation report template", "investigation findings", "how do I write an investigation report", "interviews are done, what now", "separate findings from the decision", part of the AI for HR Pack by Polar Bear.

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

Works with

cli

Security Analysis

A100/100

Scanned 10/4/2026

$npx -y skills add polar-bear-org/claude-skills --skill hr-investigation-report --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Hr Investigation Report?

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

Security grade badge for Hr Investigation Report
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-hr-investigation-report/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-hr-investigation-report)

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-investigation-report
description: Structures an investigation report that keeps allegation, evidence, findings of fact and open questions apart, leaves the decision to a named decision maker and indexes the evidence log. Use for "run hr-investigation-report", "write up the investigation", "investigation report template", "investigation findings", "how do I write an investigation report", "interviews are done, what now", "separate findings from the decision", part of the AI for HR Pack by Polar Bear.
---

# Investigation Report Template

## When To Use
Interviews are done and you must write up what was found without deciding the outcome in the same document. The investigator's job ends at the facts; someone else decides what happens. This answers: what was alleged, what evidence there is, what the investigator found as fact, and what is still open.

## When Not To Use
If interviews have not happened yet, go back to the Workplace Investigation Plan. If a decision has been made and a hearing follows, use Written Warning for the letters.

## Inputs
- Where the people involved work (country, and state or province where it matters)
- The terms of reference and the evidence log from the plan
- Interview notes, and the investigator's own findings in their words
If you have none of this, I start from the allegations and the evidence list and mark the output as a first draft with every finding left blank.

## Approach
The shell follows Acas, investigations for discipline and grievance, step 6, what happens after an investigation (acas.org.uk/investigations-for-discipline-and-grievance-step-by-step/step-6-what-happens-after-an-investigation). Findings belong to the investigator: Claude arranges what the investigator states and never supplies a finding. The failure it prevents: a report that ends "and a final warning is appropriate", which blurs investigator and decision maker and hands the other side an easy appeal.

## Workflow
1. Ask three questions: where do the people involved work; who is the investigator and who is the decision maker (they must be different people); did the terms of reference ask for a recommendation.
2. Set one section per allegation, word for word from the terms of reference. No new allegations appear here; anything new goes back to whoever set the terms.
3. Under each allegation, list the evidence by log reference (EV1, EV2) and summarise what each item shows, without weighing one account against another.
4. Enter the investigator's findings exactly as stated, split into facts established and facts not established, plus mitigating circumstances raised and open questions. If the investigator has not stated a finding, the line stays "[finding to be written by the investigator]". I never fill it and never say who is telling the truth.
5. If a recommendation was asked for, limit it to one of the three routes Acas names: formal action, informal action or no further action. Never a sanction; Acas says investigators do not discuss potential sanctions.
6. Index every item in the evidence log in the appendix. Any item withheld, for example for data protection, is listed with the reason and marked for an adviser.

## Output Format
```markdown
# Investigation Report
## Scope
[Terms of reference, investigator (role), commissioned by (role), dates]
## Allegation A1: [as in the terms of reference]
| Evidence ref | What it shows |
|---|---|
| EV1 | [summary, no weighing] |
- Facts established (investigator): [as stated]
- Facts not established (investigator): [as stated]
- Mitigating circumstances raised: [as stated]
- Open questions: [list]
## Route recommended (only if asked)
[Formal action / informal action / no further action, as stated by the investigator]
## Evidence index
| Ref | Item | Source | Date | Included or withheld (reason) |
|---|---|---|---|---|
| EV1 | [item] | [source] | [date] | [included] |
## Adviser questions
- [Confirm with a qualified adviser for [country]: disclosure of evidence, withheld items, time limits]
## Decision
[Named decision maker, not the investigator] decides whether to proceed and how by [date].
```

## Done When
- Each allegation matches the terms of reference word for word
- Every finding is attributed to the investigator; none is written by Claude
- There is no sanction anywhere in the report
- The evidence index covers every log item, with withheld items explained

## Quality Bar
- Evidence and findings sit in separate places, never in one sentence
- No credibility language about any witness or the subject ("honest", "evasive", "reliable")
- Accounts that conflict are both recorded; the report does not pick one
- The decision maker is named and is not the investigator
- 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-written-warning (Written Warning) if the decision maker opens a hearing.

## 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 →