
Implementation Kickoff
OfficialFreeStreamline your code implementation process with ease.
Free · Opens the source repo
What Implementation Kickoff does
The Implementation Kickoff skill provides a structured approach for developers to transition from planning to execution within a Git workflow. It creates an isolated worktree that allows users to implement changes without affecting their current branches or checkouts. This skill is particularly useful for teams that need to maintain a clean Git history while managing multiple tasks simultaneously. By fetching the latest version of the main branch and applying task changes in a controlled environment, developers can ensure that their work is based on the most recent codebase.
This skill emphasizes the importance of maintaining a clear boundary between different tasks and preventing any unwanted changes to the main repository. It allows for the recording of all relevant task information, including requirements and success criteria, ensuring that the implementation is aligned with the project's goals. The process involves creating a detached worktree, which provides a safe space for implementation without committing changes until they are ready for review. This approach minimizes the risk of introducing errors into the main branch and helps maintain a clean project history.
The skill also includes mechanisms for handling pull requests, allowing users to take over existing PRs seamlessly. It ensures that all relevant metadata is preserved during the transition, maintaining the integrity of the original work while facilitating collaboration. Developers can leverage this skill when they need to implement features or fixes without disrupting ongoing work, making it an essential tool for teams focused on agile development practices.
In summary, the Implementation Kickoff skill is designed for developers who require a reliable method for managing their code changes in a collaborative environment. It streamlines the process of transitioning from planning to execution, ensuring that code is implemented correctly and efficiently without compromising the integrity of the main repository.
When to use it
Use this skill when you need to implement changes based on a defined scope without affecting your current Git branches.
When not to use it
Avoid this skill during investigation phases or when user approval for implementation has not been secured.
What you can build with it
Transitioning from Planning to Execution
Use this skill to move from an agreed implementation scope to actual coding without affecting your main branches.
Managing Multiple Tasks in Parallel
When working on several features, this skill helps you maintain a clean Git history while implementing changes.
Taking Over Existing Pull Requests
Easily take over and complete another author's pull request while preserving all relevant metadata and context.
How to install Implementation Kickoff
View source1. Install with the skills CLI
npx skills add openai/openai-agents-python/implementation-kickoff --agent claude-code2. Or install it manually
Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.
Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs
Inside SKILL.md
Written by openaiImplementation Kickoff
Use this skill as the explicit transition from an agreed implementation scope to isolated execution. Keep the user's original checkout and existing branches unchanged, and finish with a clean local branch that is ready for the user to push.
Non-negotiable boundaries
- Treat explicit invocation of this skill as authorization to fetch, create one dedicated worktree, rebase or replay task-owned changes, create the final local branch, stage task-owned files, and create one local commit. It never authorizes push, pull-request creation, or any GitHub mutation.
- Do not start during an investigation-only phase or before a required user approval. Finish planning and any required implementation scope contract first.
- Use read-only GitHub access when remote PR evidence is required.
- Preserve unrelated and user-owned changes. Do not remove an existing worktree or rewrite an existing branch to make room for this workflow.
1. Establish the task boundary
Record the original requirement, success criteria, intended target (origin/main unless the user states otherwise), task-owned paths, compatibility boundary, intentionally unsupported cases, and required repository skills. For a multi-step task, create and maintain the repository's required ExecPlan, but keep operational artifacts out of the shipped-path manifest unless they are intended deliverables.
If the current directory is a worktree previously created for this same task in the current conversation, resume it. Otherwise, continue from the user's current checkout only long enough to create a new worktree.
2. Create a detached worktree from current main
- Verify the source checkout's raw status without modifying it.
- Fetch
origin main. If the fetch fails, stop rather than claiming a stale ref is current. - Record the fetched
origin/maincommit. - Choose a unique task-oriented path under the configured Codex worktree root. Check both the filesystem and
git worktree list; never reuse or delete a collision. - Run
git worktree add --detach <worktree> origin/mainand perform all subsequent implementation work there. - Confirm the new worktree is detached at the recorded commit and initially clean.
Do not create the final branch yet. A detached worktree makes the eventual $pr-draft-summary branch suggestion authoritative and prevents temporary naming from becoming accidental output.
3. Implement without task commits
Keep the task diff uncommitted through implementation, focused tests, formatting, and review fixes. Track new files explicitly because ordinary diff statistics omit untracked files. Use the applicable repository skills and references, including $implementation-strategy before user-facing or runtime changes.
Do not create checkpoint commits. If an external interruption requires extra protection, leave the dedicated worktree intact or use a clearly named temporary stash; restore the changes before continuing and do not treat the stash as a deliverable.
Taking over an existing pull request
When the user asks to complete another author's pull request:
- Refresh the PR metadata, head, discussion, and complete three-dot diff through read-only access.
- Confirm that the PR is still an appropriate takeover source. Do not treat an already merged PR as an active takeover.
- Apply the original PR's complete task diff onto the worktree based on current
origin/main; do not derive the final branch from the contributor branch and do not preserve its intermediate commit topology. - Record the original PR number, PR author login, verified commit identity, existing valid
Co-authored-bytrailers, linked issues, and the original intent that the replacement must preserve. - If a valid author identity cannot be obtained from the PR's commits, stop before committing and ask the user. Never invent an email address.
4. Replay the complete task onto the latest main
After implementation, focused tests, and formatting are stable, fetch origin main again. If it advanced:
- Confirm that every local change is task-owned.
- Save tracked and untracked task changes in a uniquely named temporary stash.
- Rebase the detached HEAD onto
origin/main. With no task commits, this updates the empty local commit range to the new base. - Reapply the stash and confirm it was removed only after a clean application.
- Resolve conflicts only when the requirement and surrounding source make the correct result unambiguous. Otherwise preserve the stash and conflict evidence, then stop for user direction.
- Rerun formatting and every focused check affected by the new base.
Record this observed origin/main commit as the final-base candidate. Do not call an older base "latest" merely because its changes appear unrelated.
5. Complete final review and verification
Run the repository's applicable completion gates against the complete task-owned diff on the final-base candidate. For runtime code, tests, examples, build or test behavior, or behavior-impacting docs, run $implementation-final-review and the required $code-change-verification sequence in their mandated order. Honor their fingerprint and invalidation rules.
Skip those skills only when their own repository rules say the task is ineligible, such as a repo-meta-only change. Do not weaken an eligible gate merely because the diff is small.
Do not create the branch or commit when review is non-converging, verification fails, required evidence is missing, or the final content lacks clean-review credit.
6. Generate the complete PR handoff
Invoke $pr-draft-summary only after review and verification apply to the final content. Give it a self-contained packet containing the original requirement, implementation scope contract, important decisions and intent, complete changed-path inventory including untracked files, final diff and statistics, compatibility notes, issue references, and takeover provenance.
The worktree is intentionally detached. Tell $pr-draft-summary to treat the current branch value HEAD as "no branch yet" and require a concrete unused branch-name suggestion; never accept HEAD as the suggestion. The description must explain the complete final change and its motivation, not only the last review fix.
For a takeover, begin the description with prose such as This pull request supersedes #<number> and .... Preserve any separate issue-closing line only when the final implementation actually resolves that issue.
If the diff, scope, base, behavior claim, issue relationship, or provenance changes after generation, regenerate the entire PR handoff.
7. Recheck main and create one commit
Fetch origin main once more immediately before creating the branch. If it differs from the final-base candidate, return to section 4 and repeat replay, affected checks, final review, verification, and PR handoff. Once stable:
- Check whether the suggested branch exists locally, remotely, or in another worktree. Ask
$pr-draft-summaryfor the next available numeric suffix and regenerate the handoff before creating a colliding branch. - Create the exact suggested branch in the task worktree.
- Stage only the task-owned shipped-path manifest, including intended new files. Inspect the staged diff before committing.
- Use the PR draft title as the commit subject.
- For a takeover, add the verified original PR author as
Co-authored-by: Name <email>, retain distinct valid co-author trailers from the imported commits, and deduplicate identities. - Create exactly one commit. Let repository hooks run normally.
Branch creation and committing identical content are repository bookkeeping and do not invalidate clean content review. If a hook or manual fix changes task content, stop, classify the change under $implementation-final-review, and rerun every invalidated gate and $pr-draft-summary before replacing or amending the commit.
8. Validate and hand off
Run python .agents/skills/implementation-kickoff/scripts/validate_handoff.py --repo <worktree> --base <final-base> --expected-branch <branch>. For a takeover, also pass --required-trailer-email <verified-email> for each identity that must be credited.
Independently confirm that the committed diff has the reviewed content fingerprint when final review supplied one. The validator checks Git topology and repository cleanliness; it does not replace semantic review or fingerprint verification.
Leave the worktree in place. Report the worktree path, final observed base commit, branch, commit SHA and subject, verification results, review status, PR title and description, and whether takeover provenance was included. Treat the worktree path and validator output as local diagnostics: never include them in the PR title, PR description, or other copy-ready external text. State explicitly that nothing was pushed and no pull request was created.
Failure behavior
- Fetch failure: stop without creating or updating the final branch.
- Worktree or branch collision: preserve the existing target and choose a new unused path or regenerated branch suggestion.
- Replay conflict: retain recoverable task changes and ask for direction when the correct resolution is ambiguous.
- Review or verification failure: leave the detached task worktree for continuation; do not package a commit as ready.
- Commit-hook mutation: invalidate affected evidence and repeat the required gates.
- Non-clean or multi-commit final state: do not hand off as complete until corrected without discarding user-owned work.
Frequently asked questions about Implementation Kickoff
Similar skills
Release Candidate Preparation
Streamline your OpenAI Agents release process.
Gitmoji
Generate expressive commit messages with emojis.
GitHub Release
Automate your GitHub library release process effortlessly.
Commit Message Storyteller
Generate meaningful commit messages from your git diffs.
Author Contributions
Trace author contributions across branches in Git.
Git Flow Branch Creator
Automate Git Flow branch creation based on your changes.
