Review Changes
gemwalletcom/core
Review and fix local git changes against Gem Wallet Core coding standards and patterns
CLI output standards for worktrunk: message functions, ANSI color nesting and the shell integration that changes directory after the wt command exits.
Install Worktrunk CLI Output Rules
$ npx skills add max-sixty/worktrunk --skill writing-user-outputs -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install max-sixty/worktrunk writing-user-outputs --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/max-sixty/worktrunk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/writing-user-outputs .claude/skills/writing-user-outputs && 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 "writing-user-outputs" agent skill from https://github.com/max-sixty/worktrunk/tree/main/.claude/skills/writing-user-outputs into .claude/skills/writing-user-outputs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-user-outputs", 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/max-sixty/worktrunk/tree/main/.claude/skills/writing-user-outputsType 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 max-sixty/worktrunk --skill writing-user-outputs -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install max-sixty/worktrunk writing-user-outputs --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/max-sixty/worktrunk.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/writing-user-outputs .agents/skills/writing-user-outputs && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "writing-user-outputs" agent skill from https://github.com/max-sixty/worktrunk/tree/main/.claude/skills/writing-user-outputs into .agents/skills/writing-user-outputs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-user-outputs", 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 max-sixty/worktrunk --skill writing-user-outputs -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install max-sixty/worktrunk writing-user-outputs --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/max-sixty/worktrunk.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/writing-user-outputs .cursor/skills/writing-user-outputs && 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 "writing-user-outputs" agent skill from https://github.com/max-sixty/worktrunk/tree/main/.claude/skills/writing-user-outputs into .cursor/skills/writing-user-outputs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-user-outputs", 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/max-sixty/worktrunk.git --path .claude/skills/writing-user-outputs--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 max-sixty/worktrunk --skill writing-user-outputs -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install max-sixty/worktrunk writing-user-outputs --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/max-sixty/worktrunk.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/writing-user-outputs .gemini/skills/writing-user-outputs && 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 "writing-user-outputs" agent skill from https://github.com/max-sixty/worktrunk/tree/main/.claude/skills/writing-user-outputs into .gemini/skills/writing-user-outputs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-user-outputs", 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 max-sixty/worktrunk writing-user-outputsInstalls 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 max-sixty/worktrunk --skill writing-user-outputs -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/max-sixty/worktrunk.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/writing-user-outputs .github/skills/writing-user-outputs && 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 "writing-user-outputs" agent skill from https://github.com/max-sixty/worktrunk/tree/main/.claude/skills/writing-user-outputs into .github/skills/writing-user-outputs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-user-outputs", 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 max-sixty/worktrunk --skill writing-user-outputs -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install max-sixty/worktrunk writing-user-outputs --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/max-sixty/worktrunk.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/writing-user-outputs .opencode/skills/writing-user-outputs && 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 "writing-user-outputs" agent skill from https://github.com/max-sixty/worktrunk/tree/main/.claude/skills/writing-user-outputs into .opencode/skills/writing-user-outputs/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "writing-user-outputs", 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
writing-user-outputs- GitHub stars
- 9.1k
- Token cost
- ~12k tokens
- SKILL.md length
- 4,570 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
CLI output standards for worktrunk: message functions, ANSI color nesting and the shell integration that changes directory after the wt command exits.
- Works in 4 steps: Shell wrapper creates a temp file via… → Shell wrapper sets… → wt writes a raw path to the file → …
- Editing code that calls warning_message, hint_message, error_message or info_message
- SKILL.md covers Shell Integration, Output Functions, stdout vs stderr and When to page output, plus 21 more sections
- Calls git and gh
What it does
This skill documents CLI output rules for worktrunk, a Git worktree manager, and should be loaded before editing any code that calls warning_message, hint_message, error_message, info_message, eprintln or println, or that produces text users see, such as CLI help, progress UI or snapshot text. It covers ANSI color nesting rules, message patterns and the output system architecture.
A key piece of the architecture is shell integration: a shell wrapper creates a temp file and sets WORKTRUNK_DIRECTIVE_CD_FILE, wt writes a path to it, and the wrapper changes directory after wt exits. Command code just calls the output functions and never checks which mode is active. Printing uses eprintln and println re-exported from worktrunk::styling through anstream, which handles color and TTY detection, drops closed-pipe write errors instead of panicking so piping into head works, and strips ANSI when stderr is not a terminal. No std println remains under src, and the import path differs between the binary crate and the library crate.
When your agent uses it
- Editing code that calls warning_message, hint_message, error_message or info_message
- Changing CLI help text, progress output or snapshot text
- Choosing which println or eprintln import to use in worktrunk code
- Debugging ANSI escapes leaking into piped or logged output
Example prompts
- “Add a hint message to the switch command, following the output conventions.”
- “Our wt output prints escape codes when redirected to a file, so find out why.”
- “Convert these println calls in src/ to the styling versions.”
Requirements
- A checkout of the worktrunk repository
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Shell wrapper creates a temp file via mktemp
- Shell wrapper sets WORKTRUNK_DIRECTIVE_CD_FILE
- wt writes a raw path to the file
- Shell wrapper changes directory to that path after wt exits
What it can do on your machine
Read from SKILL.md and the folder at commit 11e8035. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
gitgh
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):
msys2.org
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
Worktrunk CLI Output Rules loads about 12k tokens when it runs. Until then it costs about 90 tokens; SKILL.md has 4,570 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 4,570 words (~11,924 tokens).
“Worktrunk uses one file-based directive for shell integration:”
- name
- writing-user-outputs
- metadata.internal
- true
Files
Just SKILL.md in .claude/skills/writing-user-outputs of max-sixty/worktrunk.
Open the folder on GitHubat commit 11e8035
Compare with similar skills
Worktrunk CLI Output Rules 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 |
|---|---|---|---|---|---|---|
| Worktrunk CLI Output Rules this skillmax-sixty/worktrunk | 9.1k | — | ~12k | Automated safety check: Pass | Custom licence | |
| Review Changesgemwalletcom/core | 149 | — | ~2.4k | Automated safety check: Notes | MIT | |
| Refactortermide/termide | 172 | — | ~2.8k | Automated safety check: Pass | MIT | |
| Rust Buildnubjs/nub | 4.4k | — | ~4.4k | Automated safety check: Pass | MIT | |
| Nv Park And Reviewnovuhq/novu | 40k | — | ~1.6k | Automated safety check: Pass | Custom licence | |
| Finishing a Development Branchobra/superpowers | 297k | 5 repos | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
Refactor
termide/termide
Full-workspace code quality analysis and refactoring with validation
Rust Build
nubjs/nub
A skill your agent uses when building or testing the nub Rust workspace inside a git worktree — cargo build/test/clippy for nub-cli/nub-core/aube in a worktree off origin/main.
Nv Park And Review
novuhq/novu
Commit local changes as a baseline, hop into a lightweight review worktree, run a thermo-nuclear code quality review scoped to ONLY that commit, commit the resulting refactor as a separate follow-up…
Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
Migrate Core Code to Submodules
tinyhumansai/openhuman
Plans and carries out moving non-host-specific code and its tests from the OpenHuman core into vendored tiny submodule libraries, then releases the submodule and re-pins the host.
More from max-sixty/worktrunk
Worktrunk Tend CI Guidance
max-sixty/worktrunk
Adds Worktrunk-specific rules to the tend CI workflows: Codecov polling, Rust test commands, labels and review criteria for pull requests handled in CI.
Worktrunk Release Workflow
max-sixty/worktrunk
Walks a maintainer through cutting a Worktrunk release: sync the release branch, pass two test gates, review the changes, then publish.
Related
Categories
Questions about Worktrunk CLI Output Rules
What does Worktrunk CLI Output Rules do?
CLI output standards for worktrunk: message functions, ANSI color nesting and the shell integration that changes directory after the wt command exits. This skill documents CLI output rules for worktrunk, a Git worktree manager, and should be loaded before editing any code that calls warning_message, hint_message, error_message, info_message, eprintln or println, or that produces text users see, such as CLI help, progress UI or snapshot text. It covers ANSI color nesting rules, message patterns and the output system architecture.
When should I use Worktrunk CLI Output Rules?
Worktrunk CLI Output Rules fits situations like: editing code that calls warning_message, hint_message, error_message or info_message; changing CLI help text, progress output or snapshot text; choosing which println or eprintln import to use in worktrunk code; debugging ANSI escapes leaking into piped or logged output.
How do I install Worktrunk CLI Output Rules in Claude Code?
Run `npx skills add max-sixty/worktrunk --skill writing-user-outputs -a claude-code`. Or copy the skill folder (.claude/skills/writing-user-outputs in max-sixty/worktrunk) into .claude/skills/writing-user-outputs in your project. Claude Code loads it when a task matches its description.
How do I install Worktrunk CLI Output Rules in Codex?
Run `npx skills add max-sixty/worktrunk --skill writing-user-outputs -a codex`. Or copy the skill folder (.claude/skills/writing-user-outputs in max-sixty/worktrunk) into .agents/skills/writing-user-outputs in your project. Codex loads it when a task matches its description.
Can I use Worktrunk CLI Output Rules 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 max-sixty/worktrunk --skill writing-user-outputs -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/writing-user-outputs, .gemini/skills/writing-user-outputs, .github/skills/writing-user-outputs and .opencode/skills/writing-user-outputs in your project.
What does Worktrunk CLI Output Rules need to run?
Going by SKILL.md and its folder, Worktrunk CLI Output Rules needs the command-line tools its instructions call (git and gh). Our summary lists: A checkout of the worktrunk repository.
Does Worktrunk CLI Output Rules access the network?
SKILL.md names 1 domain. As links in the text: msys2.org. This is read from the text; nothing was executed.
Is Worktrunk CLI Output Rules 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 Worktrunk CLI Output Rules use?
Worktrunk CLI Output Rules has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Worktrunk CLI Output Rules use?
About 12k tokens (SKILL.md is roughly 48k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Worktrunk CLI Output Rules?
Skills that share tags, products or a category with Worktrunk CLI Output Rules: Review Changes (gemwalletcom/core, 149 stars), Refactor (termide/termide, 172 stars), Rust Build (nubjs/nub, 4.4k stars) and Nv Park And Review (novuhq/novu, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Worktrunk CLI Output Rules?
max-sixty (a GitHub user) maintains it in max-sixty/worktrunk, which has 9,066 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.
Source: max-sixty/worktrunk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.