Headless Mode
live-codes/livecodes
Run playground without visible UI using SDK methods directly.
Formats Markdown with the Flowmark auto-formatter for typographic cleanup and semantic line breaks, and helps adopt it across a repository.
Install Flowmark Markdown Formatter
$ npx skills add jlevy/repren --skill flowmark -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jlevy/repren flowmark --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jlevy/repren.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/flowmark .claude/skills/flowmark && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "flowmark" agent skill from https://github.com/jlevy/repren/tree/master/.agents/skills/flowmark into .claude/skills/flowmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flowmark", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jlevy/repren/tree/master/.agents/skills/flowmarkType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jlevy/repren --skill flowmark -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jlevy/repren flowmark --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jlevy/repren.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/flowmark .agents/skills/flowmark && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "flowmark" agent skill from https://github.com/jlevy/repren/tree/master/.agents/skills/flowmark into .agents/skills/flowmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flowmark", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jlevy/repren --skill flowmark -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jlevy/repren flowmark --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jlevy/repren.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/flowmark .cursor/skills/flowmark && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "flowmark" agent skill from https://github.com/jlevy/repren/tree/master/.agents/skills/flowmark into .cursor/skills/flowmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flowmark", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jlevy/repren.git --path .agents/skills/flowmark--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jlevy/repren --skill flowmark -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jlevy/repren flowmark --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jlevy/repren.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/flowmark .gemini/skills/flowmark && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "flowmark" agent skill from https://github.com/jlevy/repren/tree/master/.agents/skills/flowmark into .gemini/skills/flowmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flowmark", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jlevy/repren flowmarkInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jlevy/repren --skill flowmark -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jlevy/repren.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/flowmark .github/skills/flowmark && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "flowmark" agent skill from https://github.com/jlevy/repren/tree/master/.agents/skills/flowmark into .github/skills/flowmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flowmark", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jlevy/repren --skill flowmark -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jlevy/repren flowmark --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jlevy/repren.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/flowmark .opencode/skills/flowmark && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "flowmark" agent skill from https://github.com/jlevy/repren/tree/master/.agents/skills/flowmark into .opencode/skills/flowmark/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "flowmark", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
flowmark- GitHub stars
- 374
- Token cost
- ~631 tokens
- SKILL.md length
- 204 words
- Files
- 2 (incl. references)
- Skills in repo
- 2
- Repo updated
- First seen
- Licence
- MIT
At a glance
Formats Markdown with the Flowmark auto-formatter for typographic cleanup and semantic line breaks, and helps adopt it across a repository.
- Cleaning up Markdown that an LLM generated
- SKILL.md covers Format Markdown, Adopt Flowmark in a Repository and Full Documentation
- Calls uvx
- Keeping Markdown diffs small with semantic line breaks
What it does
The skill tells the agent to run Flowmark on Markdown it creates or edits, so committed diffs stay small and readable. The formatter is conservative and never modifies code blocks or inline code. `flowmark --auto FILE` formats in place, `flowmark --auto .` covers a whole tree while respecting .gitignore and .flowmarkignore, and leaving out --auto previews to stdout, with `-` accepting piped input.
If flowmark is not on the PATH, the agent uses the Rust port through a version-pinned uvx runner, never the latest tag, or the Python reference when its library API is needed. For repository adoption, meaning a migration, Makefile wiring, ignore files, commit hooks, CI policy and turning off Prettier or another Markdown formatter, it reads a project-setup reference in full first. Full flag documentation comes from `flowmark --help` and `flowmark --docs` instead of being repeated in the skill.
When your agent uses it
- Cleaning up Markdown that an LLM generated
- Keeping Markdown diffs small with semantic line breaks
- Adopting Flowmark in a repository with hooks or CI
- Replacing Prettier as the Markdown formatter
Example prompts
- “Format README.md with Flowmark.”
- “Set up Flowmark for this repo with a pre-commit hook and a Makefile target.”
- “Replace Prettier for Markdown files with Flowmark and update CI.”
- “Clean up the docs/ folder so the Markdown has consistent line breaks.”
Requirements
- flowmark on the PATH, or uvx to run a version-pinned copy
- Pre-approved tools (allowed-tools): Bash(flowmark:*), Bash(uvx:*), Read, Write
What it can do on your machine
Read from SKILL.md and the folder at commit 885ce5e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
Bash(flowmark:*)Bash(uvx:*)ReadWrite
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
uvx
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Flowmark Markdown Formatter loads about 631 tokens when it runs, and up to ~1.6k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 204 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from jlevy/repren at commit 885ce5e, republished under its MIT licence (© jlevy). 204 words, ~631 tokens.
Download SKILL.mdSave it as
.claude/skills/flowmark/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- flowmark
- description
- Fast, consistent Markdown auto-formatter for typographic cleanup, normalization, and clean semantic line breaks. Use when creating, editing, or cleaning Markdown; formatting LLM-generated docs; adopting Flowmark in a repository; adding Markdown format scripts or commit hooks; or replacing Prettier or another Markdown formatter.
- allowed-tools
- Bash(flowmark:*), Bash(uvx:*), Read, Write
<!-- DO NOT EDIT: `flowmark --install-skill` (format=f03 surface=skill-md) -->Flowmark - Markdown Auto-Formatter
Fast, consistent Markdown auto-formatter. Run it on Markdown you generate or edit so committed diffs stay small and readable. It is conservative and safe to run on every file: it never modifies code blocks or inline code.
Format Markdown
Format in place with all auto-formatting (typography, cleanups, semantic line breaks):
flowmark --auto FILE # one file
flowmark --auto . # whole tree (respects .gitignore and .flowmarkignore)Omit --auto to preview to stdout; pipe stdin with - (e.g. cat FILE | flowmark -).
Use flowmark when it is already on PATH. Otherwise use the fast
Rust port with a version-pinned uvx runner
(never @latest):
uvx --from flowmark-rs==0.3.2 flowmark --auto FILEThe Python reference remains available when its library API or a newer unported patch is required:
uvx --from flowmark==0.7.3 flowmark --auto FILEAdopt Flowmark in a Repository
If this skill came from flowmark --skill, run the same runner with --install-skill
from the project root to materialize the complete bundle.
Then, for a repository-wide migration, Makefile wiring, .flowmarkignore, commit hooks,
CI policy, and disabling Prettier or other competing Markdown formatters, read
project-setup.md in full before editing.
Full Documentation
Flowmark documents itself. Use the CLI rather than reproducing details here:
flowmark --help— every flag:--semantic,--smartquotes,--ellipses,--width,--check, list spacing, and file discovery (--extend-include/--extend-exclude).flowmark --docs— the full guide: configuration, file discovery, editor setup, the Python library API, and installing this skill (flowmark --install-skill).
<!-- This document follows common-doc-guidelines.md.
See github.com/jlevy/practical-prose and review guidelines before editing.
-->© jlevy, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file (references) in .agents/skills/flowmark of jlevy/repren.
- SKILL.md
- references/project-setup.md
Open the folder on GitHubat commit 885ce5e
Compare with similar skills
Flowmark Markdown Formatter next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Flowmark Markdown Formatter this skilljlevy/repren | 374 | — | ~631 | Automated safety check: Pass | MIT | |
| Headless Modelive-codes/livecodes | 1.5k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Building Glamorous TuisDicklesworthstone/meta_skill | 205 | — | ~3.4k | Automated safety check: Pass | Custom licence | |
| MozlintBrowserWorks/waterfox-android | 376 | 1 repos | ~1k | Automated safety check: Pass | Custom licence | |
| Code Qualitywaybarrios/opencode-power-pack | 533 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Precheckayutaz/piper-plus | 218 | — | ~647 | Automated safety check: Pass | MIT |
Similar skills
Building Glamorous Tuis
Dicklesworthstone/meta_skill
Build terminal UIs with Charmbracelet (Bubble Tea, Lip Gloss, Gum).
Mozlint
BrowserWorks/waterfox-android
You MUST use this skill when working with Firefox's linting infrastructure (mozlint), adding new linters, modifying existing linters, running linters, or dealing with linting issues.
Code Quality
waybarrios/opencode-power-pack
Agents should invoke this skill for code reviews, linting/formatting setup, maintainability checks, complexity concerns, warning cleanup, coding standards, or quality gates in Rust, TypeScript…
Precheck
ayutaz/piper-plus
PR 作成前の lint + format + test 一括実行。引数で scope (python/rust/cs/go/js/cpp/all) を指定可能。未指定なら git diff から自動判定。
Prepare Release
ayutaz/piper-plus
9 パッケージ × 5 レジストリの version bump と関連ファイル更新 (Cargo.lock / package-lock.json / Swift checksum / CHANGELOG 昇格) を 1 コマンドで適用案にする read-mostly skill。release-prep (確認用) の続きに呼び、 実 bump 差分の markdown 提案 + 順序付き…
More from jlevy/repren
repren Multi-File Rename and Replace
jlevy/repren
Handles multi-file renames and search-and-replace with the repren CLI: several patterns, swaps and case variants in one previewable pass with backups and undo.
Related
Categories
Questions about Flowmark Markdown Formatter
What does Flowmark Markdown Formatter do?
Formats Markdown with the Flowmark auto-formatter for typographic cleanup and semantic line breaks, and helps adopt it across a repository. The skill tells the agent to run Flowmark on Markdown it creates or edits, so committed diffs stay small and readable. The formatter is conservative and never modifies code blocks or inline code.
When should I use Flowmark Markdown Formatter?
Flowmark Markdown Formatter fits situations like: cleaning up Markdown that an LLM generated; keeping Markdown diffs small with semantic line breaks; adopting Flowmark in a repository with hooks or CI; replacing Prettier as the Markdown formatter.
How do I install Flowmark Markdown Formatter in Claude Code?
Run `npx skills add jlevy/repren --skill flowmark -a claude-code`. Or copy the skill folder (.agents/skills/flowmark in jlevy/repren) into .claude/skills/flowmark in your project. Claude Code loads it when a task matches its description.
How do I install Flowmark Markdown Formatter in Codex?
Run `npx skills add jlevy/repren --skill flowmark -a codex`. Or copy the skill folder (.agents/skills/flowmark in jlevy/repren) into .agents/skills/flowmark in your project. Codex loads it when a task matches its description.
Can I use Flowmark Markdown Formatter in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jlevy/repren --skill flowmark -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/flowmark, .gemini/skills/flowmark, .github/skills/flowmark and .opencode/skills/flowmark in your project.
What does Flowmark Markdown Formatter need to run?
Going by SKILL.md and its folder, Flowmark Markdown Formatter needs the command-line tools its instructions call (uvx). Our summary lists: flowmark on the PATH, or uvx to run a version-pinned copy. Its frontmatter pre-approves these tools: Bash(flowmark:*), Bash(uvx:*), Read, Write.
Does Flowmark Markdown Formatter access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Flowmark Markdown Formatter safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Flowmark Markdown Formatter use?
Flowmark Markdown Formatter is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Flowmark Markdown Formatter use?
About 631 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 943 tokens, read only when the agent opens those files.
What are the alternatives to Flowmark Markdown Formatter?
Skills that share tags, products or a category with Flowmark Markdown Formatter: Headless Mode (live-codes/livecodes, 1.5k stars), Building Glamorous Tuis (Dicklesworthstone/meta_skill, 205 stars), Mozlint (BrowserWorks/waterfox-android, 376 stars) and Code Quality (waybarrios/opencode-power-pack, 533 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Flowmark Markdown Formatter?
jlevy (a GitHub user) maintains it in jlevy/repren, which has 374 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on August 26, 2026.
Source: jlevy/repren on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.