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

Uxr Participant Database

ASecurity

Writes a Participant Database Plan with the minimum fields kept, consent to be contacted again, contact limits and rest periods, an opt-out and deletion route, named access and a contact log per study, and never scores, ranks or profiles participants. Use for "run uxr-participant-database", "participant panel", "research participant database", "we keep recruiting the same customers", "recontact consent", "research panel rules", "who owns the participant spreadsheet", part of the UX Research w...

2 stars
0 votes
0 copies
0 views
Added 10/5/2026
ai-agentsgodatabaseperformance

Works with

cli

Security Analysis

A100/100

Scanned 10/5/2026

$npx -y skills add polar-bear-org/claude-skills --skill uxr-participant-database --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Uxr Participant Database?

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

Security grade badge for Uxr Participant Database
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/polar-bear-org-uxr-participant-database/badge)](https://www.skillsdirectory.com/skills/polar-bear-org-uxr-participant-database)

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: uxr-participant-database
description: Writes a Participant Database Plan with the minimum fields kept, consent to be contacted again, contact limits and rest periods, an opt-out and deletion route, named access and a contact log per study, and never scores, ranks or profiles participants. Use for "run uxr-participant-database", "participant panel", "research participant database", "we keep recruiting the same customers", "recontact consent", "research panel rules", "who owns the participant spreadsheet", part of the UX Research with Claude Pack by Polar Bear.
---

# Participant Database Plan

## When To Use
The team keeps recruiting the same five friendly customers from a spreadsheet nobody owns. Run it when a list of past participants starts to grow, or before you build a panel. It answers: what may we keep about people who agreed to be contacted again, and how do we stop over-using them?

## When Not To Use
For one study's recordings, transcripts and deletion dates, use Research Data Handling Plan. To recruit for a single study, use Participant Recruitment Brief, which may draw on this panel.

## Inputs
- How past participants are stored today (columns only, not the rows) and who can open it
- Any recontact wording already used, and your privacy lead's rules
- Anonymise first: replace names with P1, P2, remove contact details, employers and anything that identifies a person
If you have none of this, I start from the purpose of the panel and mark the output as a first draft.

## Approach
Participant panels within the participants component of ResearchOps 101 (Kate Kaplan, NN/g, 16 Aug 2020), with data minimisation from the GOV.UK Service Manual page Managing user research data and participant privacy. The judgment: a panel holds contact rules, not opinions about people. The failure it prevents: a "great participant, very articulate" column that quietly decides who the product hears from, and a spreadsheet of personal data with no owner and no way out.

## Workflow
1. Ask three questions: what is the panel for, who will own it by name, and what has your privacy lead said about recontact consent?
2. Write the purpose line: the panel exists to recruit real people for future studies, nothing else (no marketing, no sales).
3. Set the minimum fields: id, contact route, consent to recontact (date, wording version), behaviours relevant to recruiting, last contacted, studies taken part in, opt-out status. Every extra field needs a written reason. Refuse fields such as quality, articulate, good participant, ratings, sentiment or reliability.
4. Record consent to be contacted again separately from study consent, with the date; renewed after [period set by privacy lead]; check with your privacy lead or a qualified adviser.
5. Set contact limits and rest periods [you set]: no more than [n] invites per [period], a rest after taking part, and a share of fresh people each round [share you set].
6. Write the opt-out and deletion route, one step, honoured within [period]; access by named roles only.
7. Define the contact log per study: date, study, invited or took part. No notes on how a participant performed. Close with: check with your privacy lead or a qualified adviser.

## Output Format
```markdown
# Participant Database Plan
**Owner:** [name, role] | **Privacy lead:** [name] | **Purpose:** recruiting real people for future studies only
## Fields kept
| Field | Why it is needed |
|---|---|
| [id / contact route / recontact consent date and version / relevant behaviours / last contacted / studies / opt-out] | [reason] |
**Fields refused:** quality, ratings, sentiment, reliability, any judgement of a person
**Recontact consent:** [wording version], [how recorded], renewed after [period set by privacy lead]
## Contact limits
- Invites: [n per period, you set]; rest after taking part: [period you set]; fresh people per round: [share you set]
**Opt-out and deletion:** [one-step route], honoured within [period]; deleted by [role]
## Access
| Role | Can see | Can edit |
|---|---|---|
| [role] | [fields] | [yes / no] |
## Contact log
| Date | Study | Participant id | Invited or took part |
|---|---|---|---|
| [date] | [study] | [P1] | [invited / took part] |
## Decision
[Owner] adopts these rules and [privacy lead] approves fields and renewal by [date]; existing lists are cleaned or deleted by [date].
```

## Done When
- Every field has a reason, and no field judges a person
- Recontact consent is separate, dated and versioned
- Opt-out is one step and has an owner

## Quality Bar
- Contact limits are set by you, never by a default number
- The log records contact, never performance
- Privacy points close with "check with your privacy lead or a qualified adviser"
- The panel holds contact rules, not judgements: no participant is scored, ranked or profiled

## Next
Run uxr-interview-guide (User Interview Guide) to prepare the sessions the booked people will join.

## 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', ...

698461 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 →