push
Skill4 starsChanged 28 days agoMITView on GitHub
AI-assisted safety layer for git push operations with quality gates and collaboration guardrails. Use when: pushing commits, force pushing, pushing to protected branches, pushing feature branches. Not for: composing the commit — use /commit; branch and merge strategy decisions — use /git-workflow-guide. Keywords: git push, force push, protected branch, quality gate, push receipt, PR automation.
- Commits and pushes
49 other projects use a version of this.
Adopted by
Most recently taken up by
- HawkingHuang/claude-skillstheir own version, first seen Nov 8, 2026
- tyrantpiper/travel-pwatheir own version, first seen Nov 8, 2026
- quochuydev/kittheir own version, first seen Nov 8, 2026
- laz3rjenkins/atomic-commitstheir own version, first seen Nov 8, 2026
- toy-crane/claude-code-playbook-templatetheir own version, first seen Nov 8, 2026
- egregore-labs/egregoretheir own version, first seen Nov 6, 2026
Used with
Projects with it also use get-pr-reviews, push-everything and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
saffron-healthSkillget-pr-reviews
Get nicely formatted output of the last review comments on a PR. Used internally by other skills.
Also in 3 projects that use this
saffron-healthSkillpush-everything
Stage ALL changes in the repository (not just session changes), commit, and push. Use when you need to commit all pending changes.
Also in 3 projects that use this
NVIDIASkillgenerate-spec
Produce a feature specification covering API changes, backward compatibility, cross-language impact, performance, and a file-level change plan. Use when designing a new feature, planning a significant change, or the user asks to spec something out.
Also in 3 projects that use this
MicrosoftSkillmerge
Merge changes from the topic branch to the merge base branch. Use when the user wants to merge their session's work back to the base branch.
Also in 3 projects that use this
MicrosoftSkillspec-review
Independent, multi-model review of a design or spec **before** any code is written, for the microsoft/winappcli repo. Activate when a contributor asks to "review this spec", "review my design", "review this design doc", "validate this approach", "should we build this", "spec review", "design review", or "feature review". Fans out parallel sub-agents — each doing its OWN research against the real codebase and ecosystem rather than trusting the spec — covering necessity & scope, approach & alternatives, feasibility vs reality, risks & unknowns, DX & user impact, and a different-model-family cross-check. Emits a decision-oriented recommendation (proceed / proceed-with-changes / reconsider) to stdout. This is the PRE-CODE companion to the pr-review skill (which reviews code already written); use spec-review at the design/spec stage, not on an implemented diff. Does NOT write code or edit the spec.
Also in 3 projects that use this
Hugging FaceSkillupdate-docs
Update documentation across the repo after API changes. Finds stale references in docs, examples, docstrings, and fixes them.
Also in 4 projects that use this
- +2 more from saffron-health
Other versions49 projects use a version of this.
Word for word · 1
- AsiaOstrich/universal-dev-standards★ 84100% same
Edited · 0
None found.
Wrote their own version · 48
- openai/symphony★ 27ksame name
- kdlbs/kandev★ 1.1ksame name
- cashew-labs/libretto★ 898same name
- saffron-health/libretto★ 883same name
- egregore-labs/egregore★ 293same name
- Mooshieblob1/MooshieUI★ 222same name
- team-mirai-volunteer/mirai-gikai★ 214same name
- sterlingcrispin/claude_slash_commands★ 200same name
- Nucleify/Nucleify★ 171same name
- kv0906/pm-kit★ 138same name
38 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ac-coverageSkill
- adrSkill
- ai-collaboration-standardsSkill
- ai-friendly-architectureSkill
- ai-instruction-standardsSkill
- api-designSkill
- atddSkill
- auditSkill
- bddSkill
- brainstormSkill
- changelogSkill
- checkinSkill
- ci-cdSkill
- code-reviewSkill
- commitSkill
- contract-testSkill
- databaseSkill
- deploySkill
- methodologySkill
- dev-workflowSkill
- docgenSkill
- documentation-guideSkill
- durableSkill
- e2eSkill
- error-code-guideSkill
- git-workflow-guideSkill
- incidentSkill
- journey-test-assistantSkill
- knowledge-graphSkill
- logging-guideSkill
- metricsSkill
- migrateSkill
- observabilitySkill
- orchestrateSkill
- planSkill
- prSkill
- discoverSkill
- project-structure-guideSkill
- refactorSkill
- releaseSkill
- requirementSkill
- retrospectiveSkill
- reverseSkill
- runbookSkill
- securitySkill
- scanSkill
- skill-builderSkill
- sloSkill
- spec-deriveSkill
- sddSkill
- sweepSkill
- tddSkill
- coverageSkill
- testing-guideSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
14 rules. 0 are common, 6 are distinctive, and 8 are very specific to this project.
0
Common
Most of the 42 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 34
When /push is invoked, Claude executes the following steps natively:
- Very specific: line 37
Run git rev-parse --abbrev-ref HEAD to get current branch.
- Distinctive: line 39
If protected: show warning + pending commits, require explicit user confirmation before proceeding.
- Very specific: line 42
If --force or --force-with-lease flag detected: Run git log origin/<branch>..HEAD --oneline to find commits that will be overwritten.
- Very specific: line 43
Run git log origin/<branch>..HEAD --oneline to find commits that will be overwritten.
- Distinctive: line 47
Run each configured gate in sequence using Bash tool:
- Distinctive: line 54
If any required gate fails: abort with error message.
- Distinctive: line 58
If push fails: show git error and suggest remediation.
- Very specific: line 74
If auto_pr=true AND repo_mode=team AND no open PR exists for this branch: Suggest running /pr-automation-assistant to create a Pull Request.
- Very specific: line 83
Before pushing, the assistant detects whether the target branch is a protected branch (e.g., main, master, release/*, hotfix/*).
- Very specific: line 93
When --force is detected, shows the impact before allowing execution.
- Distinctive: line 118
After a successful push, outputs a structured receipt for audit trail purposes.
- Distinctive: line 140
After pushing a feature branch, prompts user to create a Pull Request if none exists.
- Very specific: line 220
After /push completes, the AI assistant should suggest:
“Common” is measured: kept by at least 6 in 10 of the 42 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Push Assistant | 推送助手
Language: English | 繁體中文
Version: 2.0.0 Created: 2026-04-23 Applicability: Claude Code Skills
AI-assisted safety layer for git push. Detects protected branches, enforces force-push guardrails, runs pre-push quality gates, outputs a structured push receipt, and integrates with PR automation.
git push 的 AI 輔助安全層。偵測保護分支、強制 force-push 護欄、執行 pre-push 品質 gate、輸出結構化推送收據,並整合 PR 自動化。
Core Standard | 核心標準
This skill implements .standards/push-standards.ai.yaml.
Workflow | 執行工作流程
When /push is invoked, Claude executes the following steps natively:
Step 1: Detect Protected Branch
Run git rev-parse --abbrev-ref HEAD to get current branch.
Compare against protected_branches list (default: main, master, release/, hotfix/).
If protected: show warning + pending commits, require explicit user confirmation before proceeding.
Step 2: Detect Force Push
If --force or --force-with-lease flag detected:
Run git log origin/<branch>..HEAD --oneline to find commits that will be overwritten.
Show count and author list. Require user to type yes, force push to proceed.
Step 3: Run Pre-Push Quality Gates
Run each configured gate in sequence using Bash tool:
lint: detect and run project lint commandtest: detect and run project test commandtype-check(optional): TypeScript type checkac-coverage(optional): acceptance criteria coveragesecurity-scan(optional): security vulnerability scan
If any required gate fails: abort with error message.
Step 4: Execute Push
Run git push <remote> <branch> [--force].
If push fails: show git error and suggest remediation.
Step 5: Emit Push Receipt
Output structured receipt to console (and optionally to ~/.uds/push-history.jsonl):
{
"branch": "<branch>",
"commit_sha": "<sha>",
"gates_passed": ["lint", "test"],
"force_push": false,
"timestamp": "<ISO8601>",
"target_remote": "origin"
}Step 6: PR Integration
If auto_pr=true AND repo_mode=team AND no open PR exists for this branch:
Suggest running /pr-automation-assistant to create a Pull Request.
Features | 功能說明
1. Push Target Risk Detection | 推送目標風險偵測
Before pushing, the assistant detects whether the target branch is a protected branch (e.g., main, master, release/*, hotfix/*).
推送前偵測目標分支是否為保護分支(例如 main、master、release/*、hotfix/*)。
- Displays a warning with branch name and commit list
- Requires explicit user confirmation before proceeding
- Aborts push if user does not confirm
2. Force-Push Guardrails | Force-Push 護欄
When --force is detected, shows the impact before allowing execution.
偵測到 --force 時,推送前顯示影響範圍。
- Calculates commits that will be overwritten on remote
- Shows count and authors of overwritten commits
- Requires user to type a confirmation string (
yes, force push) - Records
force_push: truein the push receipt
3. Pre-Push Quality Gates | Pre-Push 品質 Gate
Runs configured quality gates in sequence before pushing.
推送前依序執行已設定的品質 gate。
| Gate | Description | 說明 |
lint | Run project lint command | 執行 lint 檢查 |
test | Run project test command | 執行測試 |
type-check | TypeScript type checking (optional) | TypeScript 型別檢查(選用) |
ac-coverage | Acceptance criteria coverage check (optional) | AC 覆蓋率檢查(選用) |
security-scan | Security vulnerability scan (optional) | 安全掃描(選用) |
4. Push Receipt | 推送收據
After a successful push, outputs a structured receipt for audit trail purposes.
推送成功後輸出結構化收據,供稽核追蹤使用。
{
"branch": "feature/my-feature",
"commit_sha": "a1b2c3d",
"gates_passed": ["lint", "test"],
"gates_skipped": false,
"force_push": false,
"timestamp": "2026-04-23T10:00:00Z",
"target_remote": "origin"
}Optionally appended to ~/.uds/push-history.jsonl for persistent audit trail.
可選擇附加到 ~/.uds/push-history.jsonl 以持久化稽核追蹤。
5. PR Automation Integration | PR 自動化整合入口
After pushing a feature branch, prompts user to create a Pull Request if none exists.
推送 feature branch 後,若尚無 PR,提示使用者建立 Pull Request。
- Checks if an open PR exists for the branch
- Prompts user to run
pr-automation-assistant - Skipped in
single-ownerrepo mode or when--no-prflag is used
Usage | 使用方式
# Standard push (runs quality gates automatically)
/push
# Push with force (shows overwritten commits, requires confirmation)
/push --force
# Push to a specific remote branch
/push --target main
# Skip quality gates (emergency use)
/push --skip-gates
# Push without PR prompt
/push --no-pr
# Force push without PR prompt (e.g., updating a personal branch)
/push --force --no-prArguments | 參數說明
| Argument | Description | 說明 |
--force | Enable force push with guardrail checks | 啟用 force push,含護欄確認 |
--target <branch> | Specify target remote branch explicitly | 明確指定目標遠端分支 |
--skip-gates | Skip pre-push quality gates (emergency only) | 跳過品質 gate(僅緊急情況) |
--no-pr | Suppress PR automation prompt after push | 推送後不提示建立 PR |
Configuration | 設定
Configure via uds.project.yaml:
push:
repo_mode: team # "team" | "single-owner"
protected_branches:
- main
- master
- "release/*"
- "hotfix/*"
push_gates:
default:
- lint
- test
optional:
- type-check
- ac-coverage
- security-scan
receipt:
output: console # "console" | "file" | "both"
file_path: "~/.uds/push-history.jsonl"
auto_pr: true # prompt to create PR after push to non-protected branchOptions | 選項模式
| Option File | Mode | Description | 說明 |
options/push/team-mode.md | team | Full collaboration guardrails (default) | 完整協作護欄(預設) |
options/push/single-owner-mode.md | single-owner | Reduced friction for personal repos | 個人 repo 低摩擦模式 |
Next Steps Guidance | 下一步引導
After /push completes, the AI assistant should suggest:
推送完成。建議下一步 / Push complete. Suggested next steps:
- 執行
/pr-automation-assistant建立或更新 Pull Request ⭐ Recommended / 推薦 — 確保協作流程完整 / Ensure complete collaboration workflow- 執行
/checkin確認程式碼簽入品質 — 下次提交前的品質確認 / Quality verification before next commit- 查看
~/.uds/push-history.jsonl確認推送紀錄 — 稽核追蹤 / Audit trail verification
Related Standards | 相關標準
- Push Standards — Core push safety rules
- Git Workflow — Branching strategy
- Commit Message — Commit conventions
- PR Automation — Pull Request automation
Version History | 版本歷程
| Version | Date | Changes |
| 2.0.0 | 2026-04-28 | Restore workflow execution steps (XSPEC-097 採用層解耦); remove deprecation notice |
| 1.0.0 | 2026-04-23 | Initial release — XSPEC-081 Phase 1 |
License | 授權
This skill is released under MIT License and CC BY 4.0.
Source: universal-dev-standards
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

