Skip to content
Back to skills

Write

ASecurity

Draft, edit, or review language while preserving meaning and voice. Use when explicitly invoked or when Hope PR Writing calls Write for a PR or MR title and description; not for ordinary writing requests alone.

  • 8 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added August 30, 2026
ai-agents

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 30, 2026

npx -y skills add dkstm95/hope --skill write --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Write?

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

Security grade badge for Write
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/dkstm95-write/badge)](https://www.skillsdirectory.com/skills/dkstm95-write)

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: write
description: Draft, edit, or review language while preserving meaning and voice. Use when explicitly invoked or when Hope PR Writing calls Write for a PR or MR title and description; not for ordinary writing requests alone.
---

# Hope Write

Use when the person invokes `$hope:write`, `/hope:write`, or the host's equivalent
skill command or picker, or when Hope PR Writing calls Write for a PR or MR title
and description. For that handoff, preserve the supplied facts and constraints
and return the text to PR Writing without requiring a separate user invocation.

Continue follow-ups within the invoked task without requiring another invocation.
Ordinary requests and other skill calls do not activate Write; continue their
authorized work through the ordinary workflow. Reading a shared reference does
not invoke its skill.

Read `references/writing-standard.md` and apply it to the requested text.
Infer drafting, editing, or review from the request. A review reports problems
without editing; an edit makes the authorized change.

Within another task, preserve its scope, authority, workflow, output, and
completion conditions. Improve its language in the same session without a
separate workflow, worker, or artifact.

Use the current language unless the person or project chooses another. Read
translated text for naturalness, then compare versions for meaning drift.

Return the requested text, edit result, or material review findings; do not
return the standard or a checklist.

Files in this skill

  • SKILL.md1.9 KB
  • agents/openai.yaml330 B
  • assets/hope-protected-light.png96.6 KB
  • references/writing-standard.md2.5 KB

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.