본문으로 건너뛰기
cccskills
무료GitHub에 공개

ctrl-clip

⧉ Copy a message to the system clipboard cleanly formatted — no blockquote pipes, no terminal bars, no Claude commentary. Use whenever you draft a message the user will paste (Slack, Teams, PR comment, email) to add a clickable "⧉ ctrl + click" copy link under it, and when the user says "/ctrl-clip", "copy that", "put it on the clipboard" (in any language). Optional argument picks the target format: slack (default), md, plain.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

연동 도구Slack
설치 방법 보기

포함된 파일(4)

  • SKILL.md4.8 KB
  • clip-setup.sh8.3 KB
  • clip-url-handler.sh925 B
  • clip.sh1.8 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

⧉ ctrl-clip

Source: https://github.com/geanruca/ctrl-clip (MIT). Also installable as a Claude Code plugin: /plugin marketplace add geanruca/ctrl-clip then /plugin install ctrl-clip@ctrl-clip. Usage: /ctrl-clip [slack|md|plain] [what to copy].

Put text on the user's clipboard so it pastes cleanly. The built-in /copy copies the raw markdown of the last response — blockquotes turn into >/│ pipes and the commentary comes along. This skill copies only the content meant to be pasted, reformatted for its destination.

1. Decide WHAT to copy

Arguments: $ARGUMENTS

  • If the arguments describe the content ("the Slack reply", "the PR description", "the second draft"), copy that.
  • Otherwise copy the most recent drafted message in the conversation (a Slack reply, comment, email, PR text). If the last response had no draft, copy the whole last response.
  • Copy only the draft — never your own framing ("Here's a draft:", "Let me know if…", labels, explanations).
  • Keep the wording verbatim. Reformat, don't rewrite. Don't translate.

2. Format for the target

First word of the arguments selects the format; default is slack.

slack (default — also Teams, WhatsApp, chat)

  • No blockquotes (>), no headings (#), no tables, no horizontal rules.
  • Tables → one line per row: Label: value, value.
  • Bold: *text* (single asterisks). Italic: _text_. Keep inline `code` and fenced blocks.
  • Bullets with - ; blank line between paragraphs.
  • Links as bare URLs.

md (PR descriptions, Azure DevOps / GitHub comments, docs)

  • Keep standard Markdown (headings, **bold**, lists, tables, code fences).
  • Still no blockquotes unless the content genuinely quotes someone.

plain (email body, forms, anything without markup)

  • No markup at all: strip *, _, backticks, #. Bullets become - .
  • Tables → Label: value lines.

3. Copy

  1. Write the formatted text with the Write tool to clip.txt in the session scratchpad directory (fall back to /tmp/claude-clip.txt if there is none). Using a file avoids every shell quoting problem with $, backticks and quotes.
  2. Run:
    ${CLAUDE_SKILL_DIR}/clip.sh <that file>
    
    The script strips leftover >/│/⏺ markers and trailing whitespace, then copies via wl-copy, xclip, xsel, pbcopy, or OSC 52 (in that order).

4. Confirm

Reply with a single line: the script's ⧉ Copied … output plus the format used, e.g. ⧉ Copied 6 lines / 412 chars (slack). Do not echo the copied text again. If the script fails, show its error line.

Inline ⧉ copy link (whenever you draft a message to paste)

Every draft the user will paste somewhere gets a clickable copy icon (⧉, two overlapping squares) labeled ctrl + click, as a reminder of how to trigger it.

<CLIP_DIR> below is the absolute path of ~/.cache/claude-clip, for example /home/alice/.cache/claude-clip. The "Drafts to paste" rule loaded at session start spells it out. If that rule is not in your context, run ${CLAUDE_SKILL_DIR}/clip-setup.sh once: it registers the Ctrl+click handler if needed and prints CLIP_DIR=…. Never write ~ or $HOME into a path or link — neither is expanded.

  1. Write the formatted text (section 2, no blockquote markers) with the Write tool to <CLIP_DIR>/<id>.claudeclip. <id> is a short unique slug matching [A-Za-z0-9_-]{1,64}, e.g. slack-33247-review.
  2. In the response, show the draft as a blockquote — every line prefixed with > , blank lines as >. The bar is how the user sees exactly what gets copied; nothing else goes inside it.
  3. Right under the blockquote, on its own line: [⧉ ctrl + click](file://<CLIP_DIR>/<id>.claudeclip)

The user Ctrl+clicks the link (a plain click does nothing). If copying breaks, check <CLIP_DIR>/handler.log first — no entry means the click never reached the handler.

Why file://: Claude Code's fullscreen TUI refuses clicks on non-allowlisted schemes (custom claude-clip:// links are never dispatched), but it opens local file:// links with xdg-open. *.claudeclip is registered as application/x-claude-clip, whose default app is clip-url-handler.sh: it copies the file via clip.sh and shows a desktop notification.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Automate ActiveCampaign tasks via Rube MCP (Composio): manage contacts, tags, list subscriptions, automation enrollment, and tasks. Always search tools first for current schemas.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

davepoon/buildwithclaude3.7천2026년 10월 19일 업데이트

Pull the ads a competitor is running right now on Meta (Facebook/Instagram) and Google, then extract the hooks, offers, CTAs and landing pages worth modelling. Use when writing ad copy, planning creative tests, choosing a landing page angle, or when the user asks "what is X advertising", "what ads does X run", "find competitor ad hooks". Reads live Ad Library and Ads Transparency data through the Tracetify MCP; falls back to a manual Ad Library walkthrough when the connector is absent.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

davepoon/buildwithclaude3.7천2026년 10월 19일 업데이트

Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

davepoon/buildwithclaude3.7천2026년 10월 19일 업데이트

Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

davepoon/buildwithclaude3.7천2026년 10월 19일 업데이트

Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

davepoon/buildwithclaude3.7천2026년 10월 19일 업데이트

Checks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open source agentwhy CLI over the session records Claude Code already keeps on disk. Use when the user asks whether the agent or a subagent read their .env or other secrets, which private files a session touched, whether a key leaked into the conversation, or which key to rotate. Runs locally and never prints a secret value.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

davepoon/buildwithclaude3.7천2026년 10월 19일 업데이트

davepoon의 스킬 모두 보기

이 스킬의 문제 신고