ow-skill-advisor
Decide whether a task needs a new skill. Check skills/ first, then skills.sh and GitHub. Recommend use-existing, install-upstream, write ow-*, or install because the human insisted. Record that install. Do not run a global skills add on your own.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- ow-skill-advisor
- stub
- true
- description
- Decide whether a task needs a new skill. Check skills/ first, then skills.sh and GitHub. Recommend use-existing, install-upstream, write ow-*, or install because the human insisted. Record that install. Do not run a global skills add on your own.
- stub_reason
- Short pointer. See docs/audit/STUB-TRIAGE.md.
03 SKILL.md 正文
Skill advisor
Use this before adding a skill, an MCP, or a plugin. find-skills searches. This file decides.
Order
- Read
registries/skills.json. If a row already covers the job, load it. Say which id. - If the human named a package, check its license and the last commit.
find-skillscan runnpx skills find. Do not runnpx skills add. - Recommend one of four outcomes:
- use-existing when a canonical skill already does the job.
- install-upstream when the license is known, the security check found no secret-stealing or silent global install, and the human agrees.
- write ow-* when the gap is Orchestra policy (routing, gates, receipts) or the upstream repo has no SPDX license.
- install-anyway when the human insists after hearing the advisory. Install the named package only. Record it.
Record
Write .orchestra/user-installed.json in the product repo:
{ "id": "example", "source": "owner/repo", "reason": "human insisted", "date": "YYYY-MM-DD" }
Do not put tokens in that file.
Hard limits
npx skills add --all stays refused. -g and -y stay off unless the human says those flags out loud for one package. A missing license means you write an original ow-* skill and credit the source, or you stop. You do not copy the unlicensed text.
04 同仓库更多 Skills
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
web-design-guidelines
Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices". Do not load on Plan-only or backend-only jobs.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always
using-git-worktrees
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback
unslop
Turns vibecoded, AI-looking UI into a designed interface with its own character. Finds a direction from the product itself, then fixes spacing, color, icons, copy, type, layout, details, visuals and motion in that order, and can generate a real hero visual with an image tool when one is available. Use when the user asks to unslop, polish, clean up or redesign a screen so it stops looking AI-generated, or when a UI shows the usual tells like purple gradients, glows, gradient text, emoji labels, "New ✨" badges, glossy blobs, uppercase tracked labels, pulsing elements or uneven spacing. Works on React, Tailwind, HTML and CSS, for dashboards, apps and landing pages.