ship
End-to-end git workflow: commit changes, push to branch, and open a PR.
Skill by tezansahu
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tezansahu-ship
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/ship
What's inside
- Skill name
ship- Description
- End-to-end git workflow: commit changes, push to branch, and open a PR. Handles both staged and unstaged changes. When files are staged, commits them directly. When nothing is staged, discovers all changed files, groups them logically, and creates progressive commits before pushing and opening a PR. Triggers on: "/ship", "ship these changes", "commit push and PR", "commit the staged stuff and open a PR", "push and PR", "create commits from staged changes and raise a PR", "ship it". Do NOT trigger for plain commit-only requests (/commit) or general git questions.
- License
- GPL-3.0
- Instructions
- 116 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- staged-workflow.md · references/
- unstaged-workflow.md · references/
SKILL.md (first lines)
## Overview
Ship all pending work: commit, push, and open a crisp PR. Works in two modes:
| Mode | Trigger | Behavior |
|------|---------|----------|
| **Staged** | Files are staged (`git diff --staged` is non-empty) | Single commit of staged files |
| **Auto-group** | Nothing staged, but unstaged/untracked changes exist | Discover → group → progressive commits |
## Workflow
### 1. Detect mode & prepare
```bash
git diff --staged --name-status
```
- **Non-empty** → **Staged mode**: follow [references/staged-workflow.md](references/staged-workflow.md)
- **Empty** → check for unstaged/untracked changes:
```bash
git status --porcelain
```
- **Non-empty** → **Auto-group mode**: follow [references/unstaged-workflow.md](references/unstaged-workflow.md)
- **Empty** → nothing to ship. Stop and tell the user.
### 2. Resolve branch
```bash
git rev-parse --abbrev-ref HEAD
```
- **On `main` (or `master`)**: create a new feature branch:
```bash
git checkout -b u/tezansahu/<camelCaseDescriptor>
```
Derive `<camelCaseDescriptor>` from the changes (e.g., `addShipSkill`, `fixLatencyMetrics`, `authAndDocs`). Always camelCase, always `u/tezansahu/` prefix.
- **On a feature branch**: stay on it.
### 3. Commit
Use Conventional Commits prefixes (`feat:`, `fix:`, `docs:`, `chore:`, `refactor:`, `test:`, `perf:`). Focus on **why**, not just what.
```bash
git commit -m "$(cat <<'EOF'
<type>: <concise 1-line summary>
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
EOF
)"
```
Use the exact model name matching the current session (default: `Claude Sonnet 4.6`).
- **Staged mode**: single commit of all validated staged files.
- **Auto-group mode**: progressive commits — stage and commit one group at a time per the approved plan. Verify each with `git log -1 --oneline` before moving to the next.
**Hard rules:**
- Never `--amend` — always create a new commit
- Never `--no-verify` — if a hook fails: diagnose, explain to user, propose fix, wait for confirmation, then create a new commit
- Verify after commit: `git log -1 --oneline`
### 4. Push
```bash
# Check if upstream is set:
git rev-parse --abbrev-ref --symbolic-full-name @{u} 2>/dev/null
# No upstream (new branch):
git push -u origin <branch>
# Upstream already set:
git push
```
Never force-push.
### 5. Open PR
Analyze all commits on the branch:
```bash
git log main..<branch> --oneline
```
```bash
gh pr create --title "<concise title under 70 chars>" --body "$(cat <<'EOF'
## Summary
- <bullet 1>
- <bullet 2 if needed>
## Test plan
- [ ] <what to verify>
---
Co-authored with [GitHub Copilot](https://github.com/features/copilot)
EOF
)"
```
**PR rules:**
- Title: short, factual, under 70 chars
- Summary: 1–3 bullets — what changed and why. For multi-commit PRs, summarize the overall change
- Test plan: concrete checkboxes, not boilerplate
- Footer: `Co-authored with [GitHub Copilot](https://github.com/features/copilot)` when running as Copilot; `Co-authored with [Claude Code](https://claude.com/claude-code)` for Claude Code sessions
Return the PR URL to the user.
## Secret files
In both modes, warn and exclude these from staging/committing:
- `.env`, `.env.*`
- `credentials.json`, `**/credentials.json`
- `*.pem`, `*.key`, `*.p12`, `*.pfx`
- Any file matching common secret patternsFrom tezansahu/ai-garage, GPL-3.0.
More from tezansahu/ai-garage
- 0.605score
generate-structurizr-c4-diagram
tezansahu
Generate C4 software-architecture diagrams in Structurizr DSL from a codebase, folder(s), a description, docs, or an existing diagram, then render them in the…
SkillBFreshness: B★ 16Claude Code +9 - 0.605score
arxiv-submission
tezansahu
Submit a paper to arXiv as a preprint.
SkillBFreshness: B★ 16Claude Code +9 - 0.605score
insight-extractor
tezansahu
Extract key, actionable insights from knowledge resources and save as structured markdown files in the knowledge/insights/ folder.
SkillBFreshness: B★ 16Claude Code +9 - 0.602score
evaluate-skill-with-copilot-sdk
tezansahu
Evaluate a skill with the GitHub Copilot SDK — measure its triggering accuracy and compare its output quality against a no-skill baseline.
SkillBFreshness: B★ 16Claude Code +9 - 0.580score
skill-creator
tezansahu
Create new skills, modify and improve existing skills, and measure skill performance.
SkillBFreshness: B★ 16Claude Code +9 - 0.575score
tdd
tezansahu
Test-driven development.
SkillBFreshness: B★ 16Claude Code +9 - 0.572score
to-spec
tezansahu
Turn the current conversation into a spec and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
SkillBFreshness: B★ 16Claude Code +9 - 0.572score
to-tickets
tezansahu
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker —…
SkillBFreshness: B★ 16Claude Code +9 - 0.564score
implement
tezansahu
Implement a piece of work based on a spec or set of tickets.
SkillBFreshness: B★ 16Claude Code +9 - 0.555score
model-deployer
tezansahu
Generate deployment artifacts for ML models -- FastAPI serving code, Dockerfiles, cloud configs, batch prediction scripts, and monitoring setup.
SkillCFreshness: C★ 16Claude Code +9 - 0.555score
model-trainer
tezansahu
End-to-end machine learning model training for tabular data -- from baseline to optimized model with proper cross-validation, metric logging, and…
SkillCFreshness: C★ 16Claude Code +9 - 0.555score
nn-architect
tezansahu
Design and implement neural network architectures in PyTorch or Keras from task descriptions.
SkillCFreshness: C★ 16Claude Code +9
Signals
- Stars
- 16
- Forks
- 8
- Open issues
- 1
- Last commit (this folder)
- Jul 7, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- GPL-3.0
- Repository
- github.com/tezansahu/ai-garage
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tezansahu
- 0.605score
generate-structurizr-c4-diagram
tezansahu
Generate C4 software-architecture diagrams in Structurizr DSL from a codebase, folder(s), a description, docs, or an existing diagram, then render them in the…
SkillBFreshness: B★ 16Claude Code +9 - 0.605score
insight-extractor
tezansahu
Extract key, actionable insights from knowledge resources and save as structured markdown files in the knowledge/insights/ folder.
SkillBFreshness: B★ 16Claude Code +9 - 0.605score
arxiv-submission
tezansahu
Submit a paper to arXiv as a preprint.
SkillBFreshness: B★ 16Claude Code +9 - 0.602score
evaluate-skill-with-copilot-sdk
tezansahu
Evaluate a skill with the GitHub Copilot SDK — measure its triggering accuracy and compare its output quality against a no-skill baseline.
SkillBFreshness: B★ 16Claude Code +9 - 0.580score
skill-creator
tezansahu
Create new skills, modify and improve existing skills, and measure skill performance.
SkillBFreshness: B★ 16Claude Code +9 - 0.575score
tdd
tezansahu
Test-driven development.
SkillBFreshness: B★ 16Claude Code +9
Cite this page
ship skill. Agent Mart. https://agentmart.dev/skills/tezansahu-ship (last updated 2026-10-24)