Skip to content
Back to skills

Memory Writing

ASecurity

Write deliberate source-attributed local memory.

  • 123 stars
  • 0 votes
  • 0 copies
  • 3 views
  • Added August 31, 2026
ai-agents

Security analysis

A100/100

Scanned August 31, 2026

npx -y skills add docmancer/docmancer --skill memory-writing --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Memory Writing?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Memory Writing
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/docmancer-memory-writing/badge)](https://www.skillsdirectory.com/skills/docmancer-memory-writing)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: docmancer-memory-writing
description: Write deliberate source-attributed local memory.
---

# Write Docmancer memory

Use this skill only when the user explicitly asks to preserve a durable fact, decision, preference, rule, or workflow.

1. Run `docmancer ask "topic"` before creating a possible duplicate.
2. Write one readable Markdown file with `docmancer write` and an explicit project-relative path.
3. Read the returned stable `docmancer://memory/<id>` address before a later edit or move.
4. Pass the current content hash to `docmancer edit` or `docmancer move`.

Never write secrets or credentials. Never enable capture, connect Cloud, publish Team files, or trash existing files without explicit user authorization.

Attribution

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

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.