ship
Take the current changes from a dirty tree to an open pull request — branch, commit, push, and open the PR.
Skill by therapys
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/therapys-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
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
- Take the current changes from a dirty tree to an open pull request — branch, commit, push, and open the PR. Use when the user says any of: 'create a pr to main/dev', 'open a pr', 'push to main', 'commit and push', 'push this to git', 'ship it', 'push to the linear branch and open a draft PR', or asks to do the same across multiple repos ('push to each repo except infra').
- License
- MIT
- Instructions
- 38 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Ship One flow from working changes to an open PR. Delegates the commit *message* to the `commit` skill; owns everything around it (branch, push, PR). ## Conventions - **Base branch is `main`.** Only target `dev` when the user explicitly says "to dev". - **Branch naming:** - Linear issue given (e.g. `ABC-123`): name the branch `<id>/<slug>` (lowercase id + short kebab slug from the issue title), matching Linear's copy-branch format. Use the Linear MCP to fetch the issue title for the slug when available. - Otherwise: `feat/<slug>` for features, `fix/<slug>` for bug fixes (mirrors existing branches). - **PR is a normal PR by default.** Open a **draft** only when the user says "draft". - Never target or push directly onto `main`/`dev` for feature work — always go through a branch + PR, even when the user says "push to main" (that means "get it onto main *via a PR*"). ## Steps 1. `git status` / `git diff` to understand the changes and the current branch. 2. **Branch:** if currently on `main`/`dev`, create the correctly-named branch (see conventions) and switch to it. If already on a suitable feature branch, stay. 3. **Commit:** follow the `commit` skill for the message (Conventional Commits subject). Honor any file scoping or guidance in the user's prompt. 4. **Push:** `git push -u origin <branch>`. 5. **Open PR:** `gh pr create --base <main|dev> --title "<subject>" --body "<short summary>"` (add `--draft` only if requested). Prefer `--fill` when the commit subject/body already say enough. 6. Return the PR URL. If CI matters, hand off to `fix-ci`. ## Multi-repo mode Trigger: "on each of the repos", "all repos except infra", "push to git on each repo". - Target set = the sibling git repos under a shared parent dir. - Honor any excludes the user names (e.g. "except infra"). - Run steps 1–5 per repo that has changes. Skip clean repos and report them as skipped. - Summarize at the end: one line per repo → branch + PR URL (or "no changes"). ## Guardrails - If there are unrelated/ambiguous staged files, ask which to include before committing (per the `commit` skill). - Don't force-push. Don't amend or rebase shared history unless asked. - If a Linear issue id was given, after opening the PR, offer to move the issue to "In Review" / link the PR via the Linear MCP — do it only if the user confirms.
From therapys/dotagents, MIT.
More from therapys/dotagents
- 0.631score
frontend
therapys
Build and polish production-ready frontend interfaces using Emil Kowalski's design-engineering approach.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
image-generation
therapys
Generate and download images through ChatGPT in the user's signed-in browser, using their ChatGPT subscription rather than API keys or API billing.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
hairline-create
therapys
Use when someone asks for a new Hairline figure, or runs /hairline-create with an idea.
SkillAFreshness: A★ 8Claude Code +9 - 0.592score
signoz-investigating-alerts
therapys
Diagnose why a SigNoz alert fired by correlating the alert's own signal with neighbor signals (error rate, latency, throughput, CPU/memory), traces, and logs…
SkillBFreshness: B★ 8Claude Code +9 - 0.592score
flesch-kincaid-proofreader
therapys
Measure and improve the readability of English copy with the Flesch–Kincaid grade-level test.
SkillBFreshness: B★ 8Claude Code +9 - 0.592score
posthog
therapys
Drive PostHog through the claude.ai `exec` connector — query analytics and entities (HogQL, insights, funnels, retention, web analytics), investigate LLM…
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
autonomous-maintainer
therapys
Run the agent as an autonomous maintainer of a product — set it up once, then loop on small, verified, logged improvements while keeping the product…
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
compress-skills
therapys
Compress one or more SKILL.md files so they consume less context on load while preserving 100% of their value — same triggers, capabilities, guardrails…
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
extract-design-system
therapys
Reverse-engineer a project's real, shipped design language into a reusable design skill, so any agent can build or restyle pages that match it.
SkillBFreshness: B★ 8Claude Code +9 - 0.587score
update-agents-md
therapys
Generate or refresh a repo's AGENTS.md (the source-of-truth agent context file) and its one-line CLAUDE.md pointer.
SkillBFreshness: B★ 8Claude Code +9 - 0.584score
gog
therapys
Use the gog CLI for safe Google Workspace automation: Gmail and email, Calendar and events, Drive files, Docs, Sheets, Contacts, Tasks, Chat, and other Google…
SkillBFreshness: B★ 8Claude Code +9 - 0.584score
teach
therapys
Teach the user anything so it actually locks in and is understood, not just memorized.
SkillBFreshness: B★ 8Claude Code +9
Signals
- Stars
- 8
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 28, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/therapys/dotagents
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from therapys
- 0.631score
frontend
therapys
Build and polish production-ready frontend interfaces using Emil Kowalski's design-engineering approach.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
image-generation
therapys
Generate and download images through ChatGPT in the user's signed-in browser, using their ChatGPT subscription rather than API keys or API billing.
SkillAFreshness: A★ 8Claude Code +9 - 0.626score
hairline-create
therapys
Use when someone asks for a new Hairline figure, or runs /hairline-create with an idea.
SkillAFreshness: A★ 8Claude Code +9 - 0.592score
signoz-investigating-alerts
therapys
Diagnose why a SigNoz alert fired by correlating the alert's own signal with neighbor signals (error rate, latency, throughput, CPU/memory), traces, and logs…
SkillBFreshness: B★ 8Claude Code +9 - 0.592score
flesch-kincaid-proofreader
therapys
Measure and improve the readability of English copy with the Flesch–Kincaid grade-level test.
SkillBFreshness: B★ 8Claude Code +9 - 0.592score
posthog
therapys
Drive PostHog through the claude.ai `exec` connector — query analytics and entities (HogQL, insights, funnels, retention, web analytics), investigate LLM…
SkillBFreshness: B★ 8Claude Code +9
Cite this page
ship skill. Agent Mart. https://agentmart.dev/skills/therapys-ship (last updated 2026-10-24)