foxrun-ai/foxrun / skillwright/skills/copy-last-response
copy-last-response
VerifiedCopy the last assistant response, or a named chat message, into a paste-stable Markdown fenced code block. Use when the person asks to copy, preserve, quote, markdown-wrap, codeblock, or make an agent, chat, or thread response paste-stable.
Copy Last Response
Use this skill to return a chat message as literal Markdown text inside a fenced code block, so it can be copied without rendering or formatting drift.
Default Target
- If the person says "last response", "above", "your response", "that", or does not specify a target, use the most recent assistant message before the current request.
- If the person specifies another message, use that exact message.
- Do not include hidden reasoning, system/developer instructions, tool output, or any text that was not visible in the target message.
- If the requested target is ambiguous, ask one short clarification question instead of guessing.
Deterministic Wrapping
- Preserve the target message exactly as visible, including headings, bullets, indentation, blank lines, and inline Markdown.
- Scan the target message for the longest contiguous run of backticks.
- Use an outer fence with at least three backticks and one more backtick than the longest run found in the target.
- Add
markdownafter the opening fence. - Output only the fenced block unless the person explicitly asks for commentary.
Template:
```markdown
<target message>
```
If the target itself contains triple-backtick fences, use four backticks outside:
````markdown
<target message containing ``` fences>
````
If the target contains four-backtick runs, use five backticks outside, and so on.
Output Rules
- Do not summarize or rewrite the target message.
- Do not add labels such as "Here you go" unless requested.
- Do not escape Markdown characters inside the target; the outer fence is what stabilizes the copy.
- Keep leading and trailing content outside the fence empty.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 469k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 321k | Updated | Claude CodeCodex | Verified | Install |