SkillAgentSearch skills...

do

Work on a GitHub issue (run from worktree)

Install / Use

npx skills add fotoetienne/gru

Installs into whichever agent you are using.

About this skill
⚡

Claude Commands

Claude Code slash commands

Quality Score

62/100

Supported Platforms

Claude Code

Our assessment of do

do scores 62/100 on our quality scale, 4050th of 4,617 Development & Engineering skills we index.

Its Claude Commands is 4.2 KB long, well organised into 8 sections and no code examples: a solid amount of guidance for an agent.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
26/30
Structure
13/20
Description
8/15
Adoption
0/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 34 days ago, so do is actively maintained.
  • Our last check on 2026-10-20 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 80/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

do compared with similar skills

All 4 of these similar skills score higher than do; compare them before choosing.

SkillScoreStarsUpdatedFormat
do (this skill)by fotoetienne62034d agoClaude Commands
claude-memby thedotmack100113.5ktodayCLAUDE.md
taste-skillby Leonxlnx100110.6ktodayCLAUDE.md
Agent-Reachby Panniantong100109.2ktodayCLAUDE.md
Understand-Anythingby Egonex-AI10090.9k10d agoCLAUDE.md

Frequently asked questions

How do I install do?
Run npx skills add fotoetienne/gru. The install tabs above show the steps for each supported agent.
Which AI agents does do work with?
It is written for Claude Code, as a Claude Commands file. Other agents that read the same format can often use it too.
Is do safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 80/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is do still maintained?
The repository was last updated 34 days ago, so do is actively maintained.

description: Work on a GitHub issue (run from worktree) allowed-tools: Bash(gh:), Bash(gh pr checks:), Bash(git:), Bash(cargo:), Bash(just:*), Read, Glob, Grep, Edit, Write, Task, TodoWrite, WebFetch argument-hint: "<issue# or URL>"

Work on a GitHub issue.

Issue: $ARGUMENTS

When Running Under Gru

This command is being orchestrated by Gru. GitHub operations (claiming issue, creating PR, posting updates) are handled automatically. Focus on:

  1. understanding the issue (details provided by Gru)
  2. planning the implementation
  3. writing clean code
  4. testing thoroughly
  5. committing your changes

Gru will handle:

  • Fetching issue details
  • Creating pull requests
  • Posting status updates
  • Merging and cleanup

Workflow:

1. Check if Decomposition is Needed

  • Assess the issue's complexity:

    • Does it involve multiple distinct components or systems?
    • Does it have multiple acceptance criteria?
    • Would it take more than a few hours to complete?
    • Does it mix different types of work (backend + frontend + docs)?
  • If the issue is complex and should be broken down:

    • Recommend to the user: "This issue seems complex. Run /decompose $ARGUMENTS to break it into smaller sub-issues first."
    • Stop the fix workflow here - wait for user to decompose
  • If the issue is focused and ready to fix:

    • Proceed to the next step

2. Verify Worktree Setup

  • Confirm current directory is a git worktree with git rev-parse --git-dir
  • Check current branch matches expected pattern minion/issue-<number>-<minion-id>
  • If not in correct worktree, remind user to run /setup-worktree first

3. Plan the Fix

  • Explore the codebase to understand the relevant code
  • Create a detailed plan using TodoWrite with specific steps to fix the issue
  • Consider tests that need to be added or updated

4. Implement the Fix

  • Work through each todo item
  • Write clean, minimal code changes
  • Add or update tests as needed
  • Check CLAUDE.md for project-specific build/test commands
  • Run tests to verify the fix

5. Code Review

  • Make a commit with the changes, prefixing the commit message with your Minion ID (from the branch name), e.g. [M042] Fix null pointer in parser
  • Use the Agent tool with subagent_type='code-reviewer' to perform an autonomous code review
  • Wait for the review agent to complete and read its full output before proceeding
  • The code-reviewer agent will analyze the changes for:
    • Code correctness and logic errors
    • Security vulnerabilities
    • Error handling gaps
    • Edge cases
    • Adherence to project conventions (check CLAUDE.md)
    • Test coverage
  • Address any issues raised by the code-reviewer before proceeding
  • If the review identifies significant problems, iterate on the implementation
  • Do NOT push your branch or write PR_DESCRIPTION.md until you have read and addressed all review findings

6. Finish Your Work

When your implementation is complete and ready for human review:

  1. Commit your implementation changes with a descriptive commit message prefixed with your Minion ID (from the branch name), e.g. [M042] Fix null pointer in parser
  2. Push the branch to the remote repository
  3. Write PR_DESCRIPTION.md in the root of the repository with this format:
    ## Summary
    - Key change 1
    - Key change 2
    
    ## Test plan
    - How you tested this
    - Commands run: cargo test, just check, etc.
    
    ## Notes
    - Context reviewers should know
    - Follow-up work if any
    

DO NOT commit PR_DESCRIPTION.md - Gru will read this file locally from your worktree, use it to create the PR description, mark the PR ready, and then delete it automatically.

IMPORTANT: Only write PR_DESCRIPTION.md when work is truly complete and ready for human review. If work is still in progress, don't create this file - Gru will create a draft PR instead.

7. Iterate on Feedback

  • Look at CI check results
  • Address any issues raised by the CI checks
  • Read review comments
  • Determine which comments require changes. Sometimes reviewers are wrong!
  • Make the necessary changes
  • For any comments that you've determined don't require changes, acknowledge them
  • Make a reply that addresses each comment and includes a summary of the changes made
  • Repeat until the PR is ready to merge

Related Skills

View on GitHub
GitHub Stars0
CategoryDevelopment
Updated1mo ago
Forks0

Trust signals

80/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

1 medium1 low