Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
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
  • 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

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Write Product Documentation

ASecurity

Create fact-based product documentation from code and release evidence. Use for manuals, operations, installation, specifications, acceptance, release notes, FAQs, or claim audits.

92 stars
0 votes
0 copies
0 views
Added 9/22/2026
ai-agentssecuritydocumentation

Security Analysis

A100/100

Scanned 9/22/2026

Install to Claude Code

$npx -y skills add aAAaqwq/AGI-Super-Team --skill write-product-documentation --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Write Product Documentation?

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

Security grade badge for Write Product Documentation
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aaaaqwq-write-product-documentation-agi-super-team/badge)](https://www.skillsdirectory.com/skills/aaaaqwq-write-product-documentation-agi-super-team)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: write-product-documentation
description: Create fact-based product documentation from code and release evidence. Use for manuals, operations, installation, specifications, acceptance, release notes, FAQs, or claim audits.
---

# Write Product Documentation

Write from verified product behavior, not aspiration. Give each document one audience and one job, while preserving a shared fact base.

## Workflow

1. **Freeze scope.** Record product version, commit/tag, platform, deployment mode, audience, and date. Do not mix future features or another branch into current instructions.
2. **Build a fact matrix.** Map each claim to code, configuration, test, screenshot, runtime evidence, and known limitation. Mark facts as verified, inferred, planned, or unknown.
3. **Choose the document role.** Use a product description for value and boundaries, a full user manual for end-to-end operation, a daily guide for routine use, a technical specification for implementation, and an acceptance document for testable outcomes.
4. **Design the user journey.** Lead from prerequisites to first success, normal operation, exceptions, recovery, data handling, and support. Explain parameters in business terms.
5. **Write exact side-effect semantics.** State what preview/dry-run does for each operation. Distinguish “processed,” “request sent,” “artifact received,” “verified,” and “persisted.”
6. **Separate platforms and versions.** Put Windows/macOS differences where users encounter them. Never let an old platform prerequisite leak into a new implementation.
7. **Use honest product language.** Explain value first, but avoid unsupported detection, compliance, ROI, security, or availability guarantees. State human decision points and external dependencies.
8. **Create acceptance traceability.** Turn every important promise into a precondition, action, expected result, evidence, and failure criterion.
9. **Validate the deliverable.** Check links, headings, terminology, screenshots, version strings, commands, privacy, accessibility, rendering, and consistency against the fact matrix.
10. **Retire stale documents.** Archive superseded evidence with a replacement link; do not leave multiple files claiming to be the current source of truth.

## Writing rules

- Use the reader's language before internal implementation names.
- Define one term once and reuse it consistently.
- Give copyable commands only after verifying them on the scoped version.
- Keep screenshots synthetic or redacted and bind each screenshot to the documented version/platform.
- Distinguish product boundary, known limitation, expected degradation, and defect.
- Do not hide real side effects under “preview” wording.
- Keep legal/privacy/security claims aligned with the current architecture and policy review.

## References

- Read [document-system.md](references/document-system.md) to select document types, structures, and validation gates.
- Read [project-evidence.md](references/project-evidence.md) for examples and contradictions found in this repository's documentation set.

Attribution

aAAaqwqaAAaqwq
View sourceMore from aAAaqwq →
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

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 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', ...

686011 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.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, 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.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →