Executes defined work items by performing edits, staging, committing, and running CI checks.
Install
mkdir -p .claude/skills/do-whilp && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/15994" && unzip -o skill.zip -d .claude/skills/do-whilp && rm skill.zipInstalls to .claude/skills/do-whilp
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Execute a work plan. Make changes, run validation, commit.Key capabilities
- →Execute a work plan by making code changes
- →Run validation checks after each step
- →Commit changes with descriptive messages for each step
- →Address feedback from previous attempts or reviews
- →Maintain a running list of modified files
- →Run format and lint checks and amend commits
How it works
The skill reads a work plan, applies changes step-by-step, validates them, and commits each step, addressing any prior feedback.
Inputs & outputs
When to use do
- →Implementing a new feature from a plan
- →Addressing code review feedback
- →Resolving CI failures
- →Automating repo-specific refactoring tasks
About this skill
Do
You are executing a work item. Follow the plan.
Environment
- The target repository is at
o/repo/. Make all changes there. - The feature branch is already checked out.
- The work item JSON follows this prompt after
---. - If
typeis"pr", you are addressing review feedback on an existing PR. - If
typeis"issue", you are implementing new work. - Build dependencies are pre-fetched under
o/repo/o/. You can runmake ci(or individual targets likemake test,make check-types,make lint) inside the sandbox. Reado/build/log.txtfor the initial CI output ando/build/log.txt.exitfor the exit code.
Setup
Read o/repo/AGENTS.md if it exists. It contains repo-specific context,
conventions, and build instructions for the target repository. Follow its guidance.
Read o/plan/plan.md for the full plan.
Read o/do/feedback.md — if non-empty, it contains notes from a previous attempt.
This may be review feedback from a check phase, or timeout notes from a timed-out
do attempt (with errors encountered, key observations, and uncommitted changes).
Address those issues first, then continue with any remaining plan steps.
Instructions
- Read the plan and every file you intend to modify before editing.
- If feedback.md is non-empty, fix those issues first.
- Maintain a running list of files you modify.
- For each remaining step in the plan:
a. Make the changes for that step.
b. Before staging, run
git -C o/repo statusand verify only your files are affected. c. Stage the specific files changed (notgit add -A). d. Commit with a descriptive message for that step. - Run format and lint checks from
o/repo/AGENTS.md(e.g.make check-format,make format). Fix any issues and amend the last commit. - Run
cd o/repo && make cito validate all changes. Use a 300s bash timeout ("timeout": 300000) — some repos take over 2 minutes for a full CI run. Fix any failures and amend. - If validation requires fixes, stage and commit them.
Forbidden
Do not use destructive git commands: git reset --hard, git checkout .,
git clean -fd, git stash, git commit --no-verify.
Output
Write o/do/do.md:
# Do: <title>
## Changes
<list of files changed>
## Commit
<SHA or "none">
## Status
<success|partial|failed>
## Notes
<issues encountered>
Follow the plan. Do not add unrequested changes.
When not to use it
- →When the work plan is not clearly defined
- →When destructive git commands are required
- →When the target repository is not at `o/repo/`
Limitations
- →Requires the target repository to be at `o/repo/`
- →Forbidden from using destructive git commands
- →Requires `o/plan/plan.md` for the full plan
How it compares
This workflow provides a structured, step-by-step execution of a work plan with integrated validation and commit management, ensuring adherence to the plan and addressing feedback systematically, unlike manual code changes.
Compared to similar skills
do side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| do (this skill) | 0 | 5mo | No flags | Intermediate |
| github-workflow-automation | 11 | 2mo | Review | Advanced |
| github-actions-templates | 7 | 3mo | No flags | Intermediate |
| hooks-automation | 3 | 4mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
github-workflow-automation
ruvnet
Advanced GitHub Actions workflow automation with AI swarm coordination, intelligent CI/CD pipelines, and comprehensive repository management
github-actions-templates
wshobson
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
hooks-automation
ruvnet
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre$post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
cli-commands
windmill-labs
MUST use when using the CLI.
dev
atopile
LLM-focused workflow for working in this repo: compile Zig, run the orchestrated test runner, consume test-report.json/html artifacts, and discover/debug ConfigFlags.
toolhive-release
stacklok
Creates ToolHive release PRs by analyzing commits since the last release, categorizing changes, recommending semantic version bump type (major/minor/patch), and triggering the release workflow. Use when cutting a release, preparing a new version, checking what changed since last release, or when the user mentions "release", "version bump", or "cut a release".