Skip to content
Business
Skill

/paste

When you want to clean and reformat content (usually from your terminal) for pasting into Slack, Notion, Twitter/X, LinkedIn, email, GitHub, or plain text. Strips ANSI codes, box-drawing chars, terminal prompt artifacts, and applies destination-specific formatting. Default input

BOOST
From plugin
makerskills
86422 skills
Install
$ npx -y skills add coreyhaines31/makerskills --skill paste --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/paste

Context preview

The summary Claude sees to decide when to auto-load this skill.

When you want to clean and reformat content (usually from your terminal) for pasting into Slack, Notion, Twitter/X, LinkedIn, email, GitHub, or plain text. Strips ANSI codes, box-drawing chars, terminal prompt artifacts, and applies destination-specific formatting. Default input

SKILL.md

paste.SKILL.md
name: paste
description: When you want to clean and reformat content (usually from your terminal) for pasting into Slack, Notion, Twitter/X, LinkedIn, email, GitHub, or plain text. Strips ANSI codes, box-drawing chars, terminal prompt artifacts, and applies destination-specific formatting. Default input is the system clipboard; default output is both the clipboard and a chat preview. Triggers on "/paste", "/paste [destination]", "clean this for X," "format for slack/notion/twitter/linkedin/email/github," "render as markdown," "paste-ready," "strip formatting," "make this copy-pastable." Default destination is plain. Also scans for secrets (API keys, tokens, .env values) and warns before copying anything sensitive.
metadata:
  version: 0.2.0

/paste — Clean content for any destination

Cleans terminal output (ANSI, box-drawing, prompt artifacts, etc.) and reformats per destination rules. Reads clipboard by default, writes back to clipboard + previews in chat.

Step 1 — Get the content

In order: 1. If the user included content in the prompt (pasted, or referenced from earlier in the conversation), use that. 2. Else, read the clipboard (commands below). 3. If both empty, ask the user what to paste.

**Clipboard commands by platform** (read / write):

| Platform | Read | Write | |---|---|---| | macOS | `pbpaste` | `pbcopy < "$f"` | | Linux (Wayland) | `wl-paste -n` | `wl-copy < "$f"` | | Linux (X11) | `xclip -selection clipboard -o` | `xclip -selection clipboard < "$f"` | | Windows | `powershell Get-Clipboard -Raw` | `powershell "Get-Content -Raw '$f' \| Set-Clipboard"` |

`$f` is the temp file from the write procedure in Step 6. Always copy from a file, never from a heredoc or `echo`.

No clipboard (a remote, headless, or chat-bot agent): skip the clipboard, take content from the prompt, and return the cleaned text in a code fence.

Step 2 — Parse destination

| Invocation | Destination | |---|---| | `/paste` | **plain** (default) | | `/paste plain` | plain | | `/paste slack` | slack | | `/paste notion` | notion | | `/paste twitter` or `/paste x` | twitter | | `/paste linkedin` or `/paste li` | linkedin | | `/paste email` | email (plain) | | `/paste email rich` or `/paste email html` | email (rich/HTML) | | `/paste github` or `/paste gh` | github | | `/paste markdown` or `/paste md` | markdown render | | `/paste html` | render to HTML file + open in browser |

If ambiguous, ask. Per-destination rules live in `references/destinations.md`.

Step 3 — Scan for secrets

Before any cleaning or copying, scan against patterns in `references/secret-patterns.md`.

If any match: 1. **Stop.** Don't copy yet. 2. Report what was detected with the value **masked** (first 4 + last 4 chars only — e.g. `sk-12...wxyz`). 3. Ask: *"Spotted [type] in the content. Continue, redact (replace with `[REDACTED]`), or abort?"* 4. Default to **abort** if no clear answer.

Step 4 — Universal cleaning

Strip from the content:

  • **ANSI escape codes** — `\x1b\[[0-9;]*[a-zA-Z]` and related (color codes, cursor movement, screen control)
  • **Box-drawing chars** — `╭ ─ ╮ │ ╰ ╯ ╞ ╡ ╤ ╧ ┌ ┐ └ ┘ ├ ┤ ┬ ┴ ┼ ━ ┃ ┏ ┓ ┗ ┛` etc. Replace with simpler equivalents (`-`, `|`) or remove entirely depending on context.
  • **Terminal prompt artifacts** — leading `$ `, `> `, `❯ `, `% `, `# ` (when first non-whitespace on a line that looks like a shell prompt)
  • **Carriage returns** (`\r`) — replace with `\n` or delete
  • **Trailing whitespace** per line
  • **Excess blank lines** — collapse 3+ consecutive blank lines to 2

Step 5 — Apply destination rules

Read `references/destinations.md` and apply the relevant transform.

Step 6 — Output

**Clipboard write procedure** (every destination that writes to the clipboard):

1. **Write the cleaned content to a temp file with your agent's file-write tool**, e.g. `/tmp/paste-<slug>.txt`. Never pipe it through a shell heredoc or `echo`: agent harnesses can hard-wrap heredocs (~70 chars) and indent every line, so the paste comes out broken while the chat looks fine. 2. **Copy from the file** with the write command from Step 1. 3. **Verify the round trip.** Read the clipboard back and compare it to the file, e.g. `pbpaste | cmp -s - "$f" && echo match` (swap in the platform's read command; on Windows, `powershell "(Get-Clipboard -Raw) -eq (Get-Content -Raw '$f')"`). On a mismatch, report it and fall back to showing the text in a code fence. 4. **Build the chat preview from what you read back**, not from what you meant to copy. A preview from memory is how a mangled copy ships looking clean. 5. **Delete the temp file** once verified. It can hold anything the user copied, including text the secret scan let through.

| Destination | Output behavior | |---|---| | plain / slack / notion / twitter / linkedin / email / github | (a) Show preview in a code fence in chat. (b) Clipboard write procedure above; preview comes from the read-back. | | email rich | Render to HTML, write to `/tmp/paste-<timestamp>.html`, open it in the browser (`open` on macOS, `xdg-open` on Linux, `start` on Windows). Skip clipboard (the user copies from browser to preserve rich text). | | markdown | Render the cleaned markdown directly in chat (most agent UIs render it). Also copy raw markdown to the clipboard via the write procedure. Offer: *"Open as HTML too?"* — if yes, write and open. | | html | Render to HTML, write to `/tmp/paste-<timestamp>.html`, open it in the browser. Skip clipboard. |

After output, report a one-line summary of what was cleaned (e.g., *"Stripped 12 ANSI codes, 4 box-drawing chars, 1 prompt artifact. Character count: 248 / 280 (X). Clipboard round-trip verified."*).

Length warnings

Twitter and LinkedIn have practical limits. the user said "let me trim" — don't refuse or auto-truncate.

  • **Twitter/X**: warn if >280 chars. Note the overage.
  • **LinkedIn**: warn if >400 chars (comfort line, not hard limit).
  • Other destinations: no length warning.

URL handling for social destina

Read more
Ships withmakerskills

AI agent skills for the personal operator's craft. Decisions, research, second-brain workflows, content rotation, scenario modeling, CFO cadence, domain hunts, and the meta-skills to author more. Built for founders and indie operators.

Get the whole plugin

Other skills on makerskills.