agentleFS
Sign inStart free
fmindfmind/dot/skills/clipboard/SKILL.md

clipboard

Skill13 starsChanged 4 days agoMITView on GitHub

Copy the last requested output to the system clipboard.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Treat /clipboard without arguments as “copy the interesting output I requested in the preceding exchange.” Arguments can select a …

    line 15
  2. Distinctive:

    Avoid OSC 52 in tool output: do not emit OSC 52 escape sequences through tool output.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Clipboard

Treat /clipboard without arguments as “copy the interesting output I requested in the preceding exchange.” Arguments can select a particular result or format.

Workflow

  1. Select the latest requested deliverable: a draft, prompt, command, code snippet, table, or test result. Omit assistant preambles, progress updates, tool logs, and offers to continue unless they are the requested output. Preserve the deliverable verbatim; do not regenerate it or rerun a test. For code or commands, omit the surrounding Markdown fence unless the user requested Markdown. If several outputs are equally plausible, ask which one; never guess unavailable conversation content.

  2. Pipe the text to the helper: pass the selected UTF-8 text to scripts/copy.py on stdin using python -I. Use the tool's structured stdin when available, or a single-quoted heredoc with a delimiter absent from the text; never interpolate the content into shell commands or command-line arguments. The helper bounds its stdin read and rejects deliverables above 1 MiB; use a file for larger content. It strips exactly one final newline, the one a heredoc always adds; pass --keep-final-newline when the deliverable must end with one, such as a whole file.

    python -I ~/.agents/skills/clipboard/scripts/copy.py <<'CLIPBOARD_PAYLOAD'
The selected deliverable goes here, unchanged.
CLIPBOARD_PAYLOAD
  3. Confirm briefly what was copied: do not repeat the payload. The helper checks the clipboard byte for byte and reports success only after verification. If it fails, report the cause, including the native tool's diagnostic it prints, and the relevant recovery from platform behavior; do not claim that the clipboard was updated successfully.

Boundaries

  • Install a missing backend only with consent: the one matching the display server (xclip or wl-clipboard); never sudo.
  • Avoid OSC 52 in tool output: do not emit OSC 52 escape sequences through tool output; captured output may never reach the user's terminal.
  • Copying does not authorize pasting: invocation authorizes replacing the current clipboard; it does not authorize pasting into an application or sending the content elsewhere.

Documentation

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free