Skip to content
Back to skills

Prompts

ASecurity

This is the Pi runtime entry point for the `/create-skill` command. The canonical, authoritative command definition lives in the OpenCode tree at: `.skilled/commands/create/skill.md` Read that file in full and follow it exactly as the command's instructions. It is the single source of truth for this command's routing, assets, execution targets, and presentation. Treat everything below the frontmatter there as your operating contract. Arguments passed to this prompt are available as $ARGUMENTS...

  • 36 stars
  • 0 votes
  • 0 copies
  • 6 views
  • Added September 3, 2026
ai-agents

Security analysis

A100/100

Pro scans all 21 files and shows the line behind each finding

Scanned September 21, 2026

npx -y skills add MichelKerkmeester/opencode--spec-kit-skilled-agent-orchestration --skill prompts --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Prompts?

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

Security grade badge for Prompts
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/michelkerkmeester-prompts-skilled-agent-harness-spec-dri/badge)](https://www.skillsdirectory.com/skills/michelkerkmeester-prompts-skilled-agent-harness-spec-dri)

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
<!-- Generated by sync-prompts-pi.cjs from .skilled/commands/create/skill.md — do not edit by hand. -->
# Pi entry: /create-skill

This is the Pi runtime entry point for the `/create-skill` command. The canonical, authoritative command definition lives in the OpenCode tree at:

`.skilled/commands/create/skill.md`

Read that file in full and follow it exactly as the command's instructions. It is the single source of truth for this command's routing, assets, execution targets, and presentation. Treat everything below the frontmatter there as your operating contract.

Arguments passed to this prompt are available as $ARGUMENTS and map to the canonical command's $ARGUMENTS / positional $1..$N inputs.

User request: $ARGUMENTS

Files in this skill

  • agent-router.md736 B
  • create-agent.md736 B
  • create-benchmark.md752 B
  • create-changelog.md752 B
  • create-command.md744 B
  • create-diagram.md744 B
  • create-diff.md732 B
  • create-feature-catalog.md776 B
  • create-manual-testing-playbook.md808 B
  • create-readme.md740 B
  • create-repo-rule.md752 B
  • create-skill-parent.md764 B
  • create-skill.md736 B
  • create-with-human-voice.md780 B
  • deep-agent-improvement.md776 B
  • deep-ai-council.md748 B
  • deep-model-benchmark.md768 B
  • deep-research.md740 B
  • deep-review.md732 B
  • deep-skill-benchmark.md768 B

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.