Skip to content
Back to skills

Writing Skills

ASecurity

Create or refine a reusable SKILL.md workflow in the harness's discoverable skills directories.

  • 42 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agents

Security analysis

A100/100

Scanned November 11, 2026

npx -y skills add acyclic-labs/sdk --skill writing-skills --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Writing Skills?

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

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

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: writing-skills
description: Create or refine a reusable SKILL.md workflow in the harness's discoverable skills directories.
---

Choose a narrow, repeatable task that benefits from instructions beyond the agent's general capabilities. Inspect nearby skills and the existing tool surface before adding another workflow.

Create a folder named for the skill with a SKILL.md containing YAML frontmatter: a lowercase hyphenated name and a description that says what it does and when to use it. Keep the body focused on decisions, required inputs, observable outcomes, and constraints. Use existing tools and filesystem conventions; a skill does not introduce a new tool or grant authority.

Delete duplicated prompt instructions and generic advice. Add supporting files only when they supply necessary detail or reliable reusable execution, and link them where needed. Exercise the workflow on representative tasks when permitted, including a case that should not activate it. Separate format validation from evidence that the workflow works; preserve user edits when revising an existing skill.

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.

View all in ai-agents →

Comments

Loading comments…

Newsletter

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