Agent skill
markdown-output
Enforce Markdown output formatting policy whenever the user asks for full Markdown source code, raw Markdown, or copyable Markdown documents. Use whenever the user says "output markdown", "give me the markdown source", "markdown 源码", "raw markdown", or similar requests for Markdown content that is meant to be copied as-is rather than rendered.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/markdown-output
SKILL.md
Markdown Output Policy
This skill defines mandatory formatting rules for generating full Markdown source code. These rules have higher priority than any stylistic formatting preferences.
Fencing Rules
- Always wrap the entire Markdown document in triple tildes (
~~~). - Never use triple backticks (
```) as the outermost fence. - Triple backticks (
```) are allowed only inside the document for code examples. - Avoid nested triple backticks. If a code block inside the document
itself needs to show triple backticks, use an increased-count fence
(e.g.
~~~~) or indent-based code blocks instead. - The output must be copyable in its entirety without rendering breaks.
Link Formatting Rules
- In Markdown links, insert one space between the URL and the closing
parenthesis:
- Correct:
[text](https://example.com ) - Wrong:
[text](https://example.com)
- Correct:
- After a bare URL (not inside a link), always insert one space before
any following character, including punctuation:
- Correct:
https://example.com ,下一段文字 - Wrong:
https://example.com,下一段文字
- Correct:
Examples
Fencing — correct
My Document
Some text and a code block:
console.log("hello");
Fencing — wrong (uses triple backticks as outer fence)
Do not produce output like this:
```
# My Document
…
```
Link — correct
See [GitHub](https://github.com ) for details.
Link — wrong
See [GitHub](https://github.com) for details.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?