ow-forge
Turn a plain request into a short brief before any other skill runs. Use at the start of a job. Do not rewrite the user's words in secret.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- ow-forge
- description
- Turn a plain request into a short brief before any other skill runs. Use at the start of a job. Do not rewrite the user's words in secret.
03 SKILL.md 正文
Prompt forge
Run this before classify, then ow-focus. Then do the work. Ask only when the task is truly ambiguous.
Brief
| Field | Write |
|---|---|
| Intent | What the user wants done |
| Kind | college, personal, hiring-cv, or none |
| Route | One capability from the graph |
| Acceptance | How we will know it worked |
| Refs | Named files, links, or library rows |
| Constraints | What must not change |
| Out of scope | What this pass will not do |
Show the brief in a few lines. Do not wait for approval unless a requirement that changes product behavior is missing.
New product
When the intent or the acceptance line is unclear and the job is a new product, run grilling before the brief is treated as settled. Then domain-modeling writes the glossary and any ADR.
For a startup idea, ask one scope question: expand, hold, or reduce. Record the answer in the brief. Do not start a second product in the same pass.
Load line
Before a write that loads something, name only what this task uses:
Load: skill-a, skill-b
MCP: playwright
Libraries: gsap
Omit a line that would be empty. Omit the whole note when the task loads nothing new. A skill the human names wins unless it is unsafe. A missing tool stops. Do not install it.
Preconditions
- The task names the files or the acceptance line.
Procedure
- The task's paths and acceptance line win.
- Write the brief fields that are still missing. Stop when the acceptance line is clear.
Output
The change, the command that checked it, and what that command printed.
Verify
Say the work is done only after that command has been run.
Skip
Skip when the human says skip orchestra. Do not add a second conductor.
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.