Process DocumentationCAUTION

1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in Anthropic's plugin directory. Plus a typed decision layer: which skill, is it safe, ship or slip. Free in-browser or npx pm-

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: process-documentation
description: "Document any business process in a clear, structured format. Use when asked to document a process, write a process guide, create a workflow document, or map out how something works. Produces a complete process document with steps, roles, inputs, outputs, and edge cases."
---

# Process Documentation Skill

Produces clear, structured process documentation that someone new to a role can follow without needing to ask questions.

## Required Inputs
- **Process name**
- **Process description** (rough notes are fine)
- **Who does this process** (roles involved)
- **How often it runs** (daily / weekly / monthly / event-triggered)
- **Tools involved**
- **Known edge cases**

## Output Structure

---

# Process: [Process Name]
**Owner:** [Role] | **Frequency:** [How often] | **Estimated time:** [Duration]

---

### Purpose
[1-2 sentences. Why does this process exist? What breaks if it is not done?]

### Scope
**In scope:** [What this covers]
**Out of scope:** [What it does not cover]

### Prerequisites
- [ ] [Required access or information]
- [ ] [Any dependency that must be completed first]

---

### Roles and Responsibilities

| Role | Responsibility |
|---|---|
| [Role 1] | [What they do] |

---

### Process Steps

**Step 1: [Step name]**
- **Who:** [Role]
- **When:** [Trigger or timing]
- **How:** [Substeps numbered]
- **Output:** [What exists at end of this step]
- **Tool:** [System used]

[Continue for all steps]

---

### Edge Cases and Exceptions

| Situation | What to do | Who to contact |
|---|---|---|
| [Edge case] | [Action] | [Name/role] |

---

### Common Mistakes
[2-4 things people get wrong the first time]

### Escalation Path
[Name/role] → [Next level] → [Final escalation]

### Review
Next review due: [Date]

## Quality Checks

- [ ] Every step has a named role (not "someone" or "the team")
- [ ] Edge cases and exceptions table is complete
- [ ] Prerequisites are listed so someone new can prepare before starting
- [ ] Escalation path is named (specific people or roles, not just "your manager")
- [ ] Review date is set

## Anti-Patterns

- [ ] Do not write steps without specifying who is responsible for each — ownership must be explicit throughout
- [ ] Do not omit the escalation path — every process must say what happens when something goes wrong
- [ ] Do not document the ideal process if the real process differs — document reality, then note improvements separately
- [ ] Do not skip edge cases and exceptions — they are where most process failures actually occur
- [ ] Do not produce documentation without a review date — undated process docs quickly become incorrect

## Example Trigger Phrases
- "Document this process: [description]"
- "Write a process guide for [workflow]"
- "Map out how [process] works"

CAUTIONgrade B · trust 89/100 Install with care. The audit found things worth knowing before you trust its output.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (5)

templates/pm-discovery-agent/skills/assumption-mapper/SKILL.md

templates/pm-discovery-agent/skills/discovery-interview-guide/SKILL.md

templates/pm-discovery-agent/skills/job-story-mapper/SKILL.md

templates/pm-discovery-agent/skills/user-interview-synthesis/SKILL.md

templates/pm-launch-agent/skills/content-calendar/SKILL.md

Gates applied: no_behavioural_pass.