一键导入
skill-author
Research a domain by reading provided reference material, then produce a reusable SKILL.md that teaches any agent how to work in that domain.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Research a domain by reading provided reference material, then produce a reusable SKILL.md that teaches any agent how to work in that domain.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
How authenticated HTTP calls to the Opal backend work — the host/guest architecture, fetchWithCreds, the fetch allowlist, and the OpalBackendClient migration. Read this before adding, modifying, or debugging any backend call.
Learn how to make widgets on canvas
Produce high-quality React apps from natural language descriptions.
Teaches you how to properly operate in the sandboxed environment you're in.
Learn how to present your work as a structured surface — a curated manifest of artifacts that the user's application renders in real time.
Learn how to use `window.opalSDK` inside your sandboxed React component to read files, call host services, and listen for events from the application.
| name | Skill Author |
| description | Research a domain by reading provided reference material, then produce a reusable SKILL.md that teaches any agent how to work in that domain. |
You are now acquiring the meta-skill of writing skills. After reading this document, you will know how to produce high-quality SKILL.md files that teach other agents new capabilities.
Given a domain (implied by the user's objective), you will:
/mnt/references/ for domain groundingSKILL.md fileA skill must be reusable across many requests in its domain. It captures the judgment and expertise of the domain — not the specifics of any one request.
BAD: A recipe skill that includes carbonara-specific instructions. GOOD: A recipe skill that teaches how to structure ANY recipe with proper timing, technique sequencing, and ingredient proportions.
The test: if your skill only works for the first request that triggered it, you've written an answer, not a skill. Rewrite it.
The skill name must describe the domain of knowledge, not the first thing you're asked to build. The domain is the subject-matter expertise; applications are what you build WITH that expertise.
BAD: "Competitive Wobbling Scorecard Generation" — too narrow, only works for scorecards. GOOD: "Competitive Wobbling" — works for scorecards, training guides, match commentary, athlete profiles, etc.
BAD: "Italian Pasta Recipe Creation" — fuses a cuisine with a format. GOOD: "Culinary Arts" — works for any recipe, any cuisine, any format.
/mnt/references/): domain-specific documents, data,
rules, and standards that ground the skill in real knowledge. Always check
for and read reference material first.When reference material exists, it is the primary source of truth. Your parametric knowledge fills in general framing and structure, but domain- specific facts MUST come from the references.
---
name: [Human-readable skill name]
description: [1-2 sentence description of what this skill enables]
---
# [Skill Name]
[Opening paragraph: "You are now acquiring the skill of..."]
## What You're Building
[Describe the RANGE of artifacts this skill enables — not just one type. The
skill should support multiple applications within the domain.]
## Memory Integration
Check `/mnt/memory.md` for user preferences before generating.
## Domain Expertise
[The reusable judgment framework synthesized from references. Rules, heuristics,
quality criteria, common mistakes, tradeoffs. This is the CORE of the skill —
the expertise that makes output substantive rather than shallow.]
## Output Format
[Exact file names, structure, and how to save them]
/mnt/references/system_write_file as SKILL.mdSave the skill as SKILL.md and call system_objective_fulfilled with a
summary of what the skill teaches.