ワンクリックで
github-workflow
Standardized Git + GitHub workflows for AI agents. Branching, committing, PRs, reviews, CI checks.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Standardized Git + GitHub workflows for AI agents. Branching, committing, PRs, reviews, CI checks.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Generic end-of-conversation sweep -- works in any project, at any point. Looks at what the current repo actually has (docs, planning files, agent context, changelog, ADRs, memory layers...) and proposes which of them to extend with the learnings, decisions, and follow-ups that surfaced in the conversation. Then prepares a paste-ready resume prompt for after /compact. Use when the user says "wrapup", "wrap up", "wrap things up", "lass uns wrappen", or before /compact.
Create Excalidraw diagram JSON files that make visual arguments -- workflows, architectures, concepts. Use when the user wants to visualize systems, processes, or ideas as .excalidraw files. Covers design methodology, section-by-section building, render-validate loop, and quality checklist.
Manage Webflow sites via the official Webflow MCP server -- pages, CMS, assets, components, styles, variables, custom code, comments, localization, and publishing. Covers the headless Data API tools and the Designer API tools (which need the Webflow Designer open in the foreground). Use when: reading, auditing, or editing a Webflow site; building or duplicating pages; managing CMS collections or assets; or adding legal/marketing pages. This plugin ships the Webflow MCP server; just authenticate (OAuth).
Turn an existing skill or a fresh idea into a catalog-ready shareable skill -- run the quality gate, decide public-vs-private catalog and standalone-vs-bundle placement, pick the category, scaffold SKILL.md (+ optional .plugin.json), update the catalog docs, and open a PR to main. Use when adding a new skill to this repo, promoting a personal or ad-hoc skill into a shareable one, or routing a skill into the right catalog.
Manage Paperclip AI companies, agents, issues, projects, goals, routines, costs, and secrets via REST API. Use when creating companies, hiring agents, assigning tasks, managing budgets, approving hires, or checking dashboards on a Paperclip instance.
Publish or update an HTML5 game on itch.io via the butler CLI. Covers install, login, channel push with versioning, and first-time page setup. Use when deploying a web game build (e.g. dist/) to an itch.io channel.
| name | github-workflow |
| description | Standardized Git + GitHub workflows for AI agents. Branching, committing, PRs, reviews, CI checks. |
| metadata | {"category":"engineering"} |
Standardized Git + GitHub workflows for AI agents.
Use this skill for all Git operations: branching, committing, PRs, reviews, CI checks.
main ← Protected. Never push directly (shared repos).
└── feat/<name> ← Feature branches. One per task.
└── fix/<name> ← Bug fixes.
└── chore/<name> ← Maintenance, docs, config.
💡 Using OpenClaw + symlinked skills? Work in the
-devworktree, not the stable copy. Seeopenclaw-skill-importskill for details.
cd <repo> # or <repo>-dev if using worktrees
git checkout main && git pull origin main
git checkout -b feat/<descriptive-name>
# Conventional Commits (required)
git add -A
git commit -m "feat: add BLE client provider
- Global keepAlive provider for connection persistence
- Scan, connect, disconnect lifecycle"
Commit message format:
feat: New featurefix: Bug fixchore: Maintenancedocs: Documentationrefactor: Code restructuringgit push origin feat/<name>
gh pr create \
--title "feat: Add BLE client provider" \
--body "## Summary
- What changed and why
## Testing
- How it was tested" \
--base main
After creating a PR, always assign yourself and apply relevant labels:
# Self-assign
gh api repos/<owner>/<repo>/issues/<pr-number>/assignees \
-X POST -f 'assignees[]=<your-github-username>'
# Check available labels
gh label list --repo <owner>/<repo>
# Apply matching labels (e.g. enhancement, bug, documentation)
gh api repos/<owner>/<repo>/issues/<pr-number>/labels \
-X POST -f 'labels[]=enhancement'
Label mapping:
| PR Type | Label |
|---|---|
feat: | enhancement |
fix: | bug |
docs: | documentation |
chore: / refactor: | (no default -- use best match if available) |
# Check PR status
gh pr checks <pr-number> --repo <owner/repo>
# View failed logs
gh run view <run-id> --repo <owner/repo> --log-failed
If a PR accidentally includes the wrong commits, edit the branch -- don't close and recreate:
# Remove the last N commits but keep changes staged
git reset --soft HEAD~N
# Or interactively pick which commits to keep
git rebase -i HEAD~N
# Force push the corrected branch -- ONLY if the branch is yours and no one else has pulled it
git push --force-with-lease origin <branch-name>
The PR stays open, history gets clean. Closing + recreating adds noise.
⚠️ Force push is a last resort. Only use it on your own feature branches, never on main or shared branches. Prefer --force-with-lease over --force (safer: fails if someone else pushed in the meantime). If you find yourself force pushing often, something is wrong upstream.
# Push fixes to same branch
git add -A && git commit -m "fix: address review feedback"
git push origin feat/<name>
After pushing fixes:
Reply to each review comment -- explain what you changed, or ask a question if the finding is unclear:
# Reply to a specific review comment
gh api repos/<owner>/<repo>/pulls/<pr-number>/comments/<comment-id>/replies \
-X POST -f body="Fixed -- added null check as suggested."
Dispute findings when appropriate -- if a reviewer's conclusion is wrong, reply with reasoning directly on their comment. Don't silently ignore it.
Request re-review -- always @mention the reviewer so they know fixes are ready:
# Request re-review from the reviewer
gh api repos/<owner>/<repo>/pulls/<pr-number>/requested_reviewers \
-X POST -f 'reviewers[]=<reviewer-username>'
# Or leave a comment @mentioning them
gh pr comment <pr-number> --repo <owner>/<repo> \
--body "@<reviewer-username> Review feedback addressed -- ready for re-review. See replies on your comments for details."
gh pr merge <pr-number> --squash --delete-branch
| Task | Command |
|---|---|
| List open PRs | gh pr list --repo <owner/repo> |
| View PR details | gh pr view <number> --repo <owner/repo> |
| List issues | gh issue list --repo <owner/repo> |
| Create issue | gh issue create --title "..." --body "..." |
| Check CI runs | gh run list --repo <owner/repo> --limit 5 |
| View run logs | gh run view <id> --log-failed |
| Clone repo | gh repo clone <owner/repo> |
| Fork repo | gh repo fork <owner/repo> |
| Create repo | gh repo create <name> --public --source=. --push |
| API query | gh api repos/<owner>/<repo>/pulls --jq '.[].title' |
main on shared repos. Always PR. No exceptions -- not for docs, not for typos, not for "small" changes."fixed stuff" messages.git pull --rebase origin main to avoid merge commits.Closes #X in the PR body, but GitHub's auto-close only triggers on merge -- and the owner can always reopen if needed.feat/, fix/, docs/, chore/. Never work directly on main, even locally.Avoid Race Conditions: Before working on any PR (review, push, merge), agents MUST check if it's still open.
STATE=$(gh pr view <N> --json state --jq .state)
if [ "$STATE" != "OPEN" ]; then
echo "⚠️ PR <N> is $STATE. Aborting to avoid conflicts."
exit 0
fi
ManniTheRaccoon/y-watch ✅Yesterday-AI/agentic-foundation 🔀How to set up a GitHub account for a new AI agent:
Create a new GitHub account using the agent's email:
<yourname+agentname@yesterday-ai.de>
Example: alex+manni@yesterday-ai.de
ssh-keygen -t ed25519 -C "agentname@yesterday-ai.de" -f ~/.ssh/id_ed25519_agentname
~/.ssh/config:
Host github.com
IdentityFile ~/.ssh/id_ed25519_agentname
gh CLIgh auth login
ABCD-1234)gh auth statusWith a @Yesterday-AI org admin:
gh api user/repository_invitations --method GET then PATCHAuthored by ManniTheRaccoon. 🦝