Skip to content
Agentmart
Submit a tool

org-output

Answer the user's prompt with the final reply formatted as a paste-ready Emacs org-mode subtree, starting at a given heading level.

Skill by gagnonlg

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/gagnonlg-org-output

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Answer the user's prompt with the final reply formatted as a paste-ready Emacs org-mode subtree, starting at a given heading level.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/org-output

What's inside

Skill name
org-output
Description
Answer the user's prompt with the final reply formatted as a paste-ready Emacs org-mode subtree, starting at a given heading level.
License
MIT
Instructions
62 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Org-mode output (paste-ready)

Raw arguments: `$ARGUMENTS`

The user will copy your final reply with `/copy` and paste it directly into an
existing org file. The final reply must therefore be a clean org subtree and
nothing else.

## Step 1: Parse the arguments

- If the first whitespace-separated token is a positive integer, that is the
  **base heading level** (N). The rest is the **prompt**.
- Otherwise N = 1 and the whole argument string is the **prompt**.

## Step 2: Do the work

Answer the prompt, using tools as needed. Keep any narration between tool calls
minimal. Everything the user needs must be in the **final message**, because
only that message gets copied.

## Step 3: Final reply = one org subtree, nothing else

The final message must:

- Start on the very first line with a level-N heading: N asterisks, a space,
  and a short descriptive title (N=2 gives `** Title`).
- Contain **no** preamble ("Here's...", "Sure"), **no** closing remarks or
  offers of follow-up, and **no** mention of these instructions.
- Contain **no** Markdown code fence around the output. Output raw org text.
- Contain **no** file-level keywords (`#+TITLE`, `#+OPTIONS`, `#+STARTUP`, etc.).
  It's a subtree, not a document.
- End with the last line of content. Don't add trailing separators.

### Headings
- Sub-sections use N+1, N+2, and so on. Never go shallower than N, and never skip levels.
- Don't indent body text under headings.
- Never start a non-heading line with `*` in column 0.

### Inline markup
- Bold `*bold*`, italic `/italic/`, underline `_underline_`, strike `+strike+`
- Code, commands, identifiers, paths: `~code~`
- Literal values: `=verbatim=`
- Never use Markdown backticks, `**bold**`, or `# headings`.

### Links
- `[[https://example.com][description]]`
- Files: `[[file:path/to/file.py::42][file.py:42]]` (prefer absolute paths so
  links still work after pasting into a file elsewhere)

### Lists
- Unordered `- item` (nest with 2 spaces); ordered `1. item`
- Description lists: `- term :: description`
- Checkboxes: `- [ ] todo` / `- [X] done`

### Blocks
Use org blocks, never Markdown fences:

#+begin_src python
print("hello")
#+end_src

From gagnonlg/claude-workspace, MIT.

Signals

Stars
0
Forks
1
Open issues
0
Last commit (this folder)
Oct 15, 2026 (14 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from gagnonlg

Cite this page

org-output skill. Agent Mart. https://agentmart.dev/skills/gagnonlg-org-output (last updated 2026-10-24)