Not in the top 1,000 by GitHub stars
vercel-labs/autoship
CLI tool to automate changeset-based releases
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/autoship/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeadbaa1d8c8
No earlier version was observed for comparison.
View on GitHubAdd to my skills
Verified commit aeadbaa1d8c8209e3de508c7e6999b843cd274d8
git clone --filter=blob:none --no-checkout https://github.com/vercel-labs/autoship.git .hotskills/vercel-labs-autoship && git -C .hotskills/vercel-labs-autoship checkout --detach aeadbaa1d8c8209e3de508c7e6999b843cd274d8
# Copy each selected skill directory from .hotskills/vercel-labs-autoship into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/vercel-labs/autoship.git .hotskills/vercel-labs-autoship && git -C .hotskills/vercel-labs-autoship checkout --detach aeadbaa1d8c8209e3de508c7e6999b843cd274d8
# Copy each selected skill directory from .hotskills/vercel-labs-autoship into .cursor/skills/<skill-name>/163GitHub stars
2stars in 7 days
1skill in this repository
1commit in 30 days
Heat
3.3- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- autoship
skills/autoship
How it works
autoship
When your agent uses it
CLI tool for automated changeset-based releases with AI-generated descriptions. Use when the user needs to release a package, create changesets, bump versions, or automate npm publishing workflows. Triggers include requests to "release a package", "create a changeset", "publish to npm", "bump the version", "automate releases", or any task involving version management and package publishing for repositories using the changesets workflow.
What it loads into context
Frontmatter
108 tokensAlways available to the agent
SKILL.md
1,285 tokensWhen the skill is activated
Reference documents
2,530 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core Workflow
- Requirements
- Essential Commands
- Command Options
- Common Patterns
- What autoship Does (10 Steps)
- Output Format
- Configuration
- Deep-Dive Documentation
- Ready-to-Use Templates
- Troubleshooting
Scripts executed separately
templates/automated-release.shtemplates/setup-repo.sh
Files
SKILL.mdcore5,245 bytesSKILL.mdcore5,245 bytesSKILL.mdcore5,245 bytesSKILL.mdcore5,245 bytesSKILL.mdcore5,245 bytesSKILL.mdcore5,245 bytesSKILL.mdcore5,245 bytesSKILL.mdcore5,245 bytesSKILL.mdcore5,245 bytesreferences/ci-integration.mddoc4,813 bytesreferences/commands.mddoc2,327 bytesreferences/configuration.mddoc2,622 bytestemplates/automated-release.shruns1,238 bytestemplates/setup-repo.shruns1,803 bytes
Read SKILL.md
# Automated Releases with autoship
## Core Workflow
Every release follows this pattern:
1. **Configure**: `autoship add <name>` (one-time setup)
2. **Release**: `autoship <name>` (interactive) or `autoship <name> -t patch -y` (automated)
The tool handles the complete release cycle:
- Clone repository
- Analyze changes and suggest release type (patch/minor/major)
- Generate AI-powered changeset description
- Create and merge changeset PRSkills included
- autoship
Repository facts
- License
- Apache-2.0
- Created
- Jan 26, 2026
- Last pushed
- Nov 3, 2026
- Forks
- 10
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 8 notes
skills/autoship/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/autoship/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/autoship/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/autoship/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/autoship/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/autoship/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/autoship/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/autoship/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- 1 broad permissionin 1 file: autoship/SKILL.md:1
- 4 dangerous shell commandsin 1 file: autoship/references/ci-integration.md:190
- 30 network referencesin 6 files: autoship/templates/setup-repo.sh:32 autoship/references/ci-integration.md:174 autoship/references/configuration.md:38 and 3 more
- No hidden or obfuscated text
- No instruction overrides
- 2 executable scriptsin 2 files: autoship/templates/automated-release.sh:1 autoship/templates/setup-repo.sh:1
- 11 references to secretsin 4 files: autoship/references/ci-integration.md:55 autoship/SKILL.md:33 autoship/templates/automated-release.sh:36 and 1 more
- No requests to vote in Hot
Show all 48 signals by file
skills/autoship/SKILL.md
- Broad permissionsline 1
Bash(autoship:*), Bash(npx autoship:*) - Access to secretsline 33
[Credential-related source omitted] - Access to secretsline 98
[Credential-related source omitted] - Network accessline 145
"repo": "myproject", "baseBranch": "main", "cloneUrl": "https://github.com/vercel-labs/myproject.git" - Network accessline 146
"baseBranch": "main", "cloneUrl": "https://github.com/vercel-labs/myproject.git" } - Network accessline 147
"cloneUrl": "https://github.com/vercel-labs/myproject.git" - Access to secretsline 189
[Credential-related source omitted]
skills/autoship/references/ci-integration.md
- Access to secretsline 55
[Credential-related source omitted] - Access to secretsline 102
[Credential-related source omitted] - Access to secretsline 117
[Credential-related source omitted] - Network accessline 174
if: success() run: | curl -X POST "${{ secrets.SLACK_WEBHOOK }}" \ - Network accessline 175
run: | curl -X POST "${{ secrets.SLACK_WEBHOOK }}" \ -H "Content-Type: application/json" \ - Network accessline 176
curl -X POST "${{ secrets.SLACK_WEBHOOK }}" \ - Network accessline 188
- name: Install GitHub CLI run: | curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | sudo dd of=/usr/share/keyrings/githubcli-archive-keyring.gpg - Network accessline 189
run: | curl -fsSL https://cli.github.com/packages/githubcli-archive-keyring.gpg | sudo dd of=/usr/share/keyrings/githubcli-archive-keyring.gpg echo "deb [arch=$(dpkg --print-architecture) signed-by=/usr/share/keyrings/githubcli-arch - Dangerous shell operationline 190
[Credential-related source omitted] - Network accessline 190
[Credential-related source omitted] - Access to secretsline 190
[Credential-related source omitted] - Dangerous shell operationline 191
[Credential-related source omitted] - Network accessline 191
[Credential-related source omitted] - Access to secretsline 191
[Credential-related source omitted] - Dangerous shell operationline 192
sudo apt update - Dangerous shell operationline 193
sudo apt install gh
skills/autoship/references/commands.md
skills/autoship/references/configuration.md
- Network accessline 38
"repo": "ai", "baseBranch": "main", "cloneUrl": "https://github.com/vercel/ai.git" - Network accessline 39
"baseBranch": "main", "cloneUrl": "https://github.com/vercel/ai.git" }, - Network accessline 40
"cloneUrl": "https://github.com/vercel/ai.git" - Network accessline 44
"repo": "agent-browser", "baseBranch": "main", "cloneUrl": "https://github.com/vercel-labs/agent-browser.git" - Network accessline 45
"baseBranch": "main", "cloneUrl": "https://github.com/vercel-labs/agent-browser.git" } - Network accessline 46
"cloneUrl": "https://github.com/vercel-labs/agent-browser.git" - Network accessline 84
autoship works with repositories that use the [changesets](https://github.com/changesets/changesets) workflow:
skills/autoship/templates/automated-release.sh
- Executable scriptline 1
#!/bin/bash - Network accessline 24
if ! command -v gh &> /dev/null; then echo "Error: GitHub CLI (gh) is required" echo "Install: https://cli.github.com" - Network accessline 25
echo "Error: GitHub CLI (gh) is required" echo "Install: https://cli.github.com" exit 1 - Network accessline 26
echo "Install: https://cli.github.com" - Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 37
[Credential-related source omitted]
skills/autoship/templates/setup-repo.sh
- Executable scriptline 1
#!/bin/bash - Network accessline 32
CLONE_URL="https://github.com/$OWNER/$REPO.git" - Network accessline 34
jq --arg name "$NAME" --arg owner "$OWNER" --arg repo "$REPO" --arg branch "$BASE_BRANCH" --arg url "$CLONE_URL" - Network accessline 36
--arg repo "$REPO" \ --arg branch "$BASE_BRANCH" \ --arg url "$CLONE_URL" \ - Network accessline 37
--arg branch "$BASE_BRANCH" \ --arg url "$CLONE_URL" \ '.repos[$name] = {owner: $owner, repo: $repo, baseBranch: $branch, cloneUrl: $url}' \ - Network accessline 38
--arg url "$CLONE_URL" \ - Network accessline 44
echo " Repo: $REPO" echo " Branch: $BASE_BRANCH" echo " Clone URL: $CLONE_URL" - Network accessline 45
echo " Branch: $BASE_BRANCH" echo " Clone URL: $CLONE_URL" else - Network accessline 46
echo " Clone URL: $CLONE_URL"
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Signal confidence: 48 facts
- Broad permissions in the frontmatter of the SKILL.mdautoship/SKILL.md:1High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueautoship/SKILL.md:33Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueautoship/SKILL.md:98Low confidence
- Network access in code of the SKILL.mdautoship/SKILL.md:145High confidence
- Network access in code of the SKILL.mdautoship/SKILL.md:146High confidence
- Network access in code of the SKILL.mdautoship/SKILL.md:147High confidence
- Access to secrets in prose of the SKILL.mdautoship/SKILL.md:189Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueautoship/references/ci-integration.md:55Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueautoship/references/ci-integration.md:102Low confidence
- Access to secrets in prose of documentationautoship/references/ci-integration.md:117Low confidence
- Network access in code of documentationautoship/references/ci-integration.md:174Low confidence
- Network access in code of documentationautoship/references/ci-integration.md:175Low confidence
- Network access in code of documentationautoship/references/ci-integration.md:176Low confidence
- Network access in code of documentationautoship/references/ci-integration.md:188Low confidence
- Network access in code of documentationautoship/references/ci-integration.md:189Low confidence
- Dangerous shell operation in code of documentationautoship/references/ci-integration.md:190Low confidence
- Network access in code of documentationautoship/references/ci-integration.md:190Low confidence
- Access to secrets in code of documentationautoship/references/ci-integration.md:190Low confidence
- Dangerous shell operation in code of documentationautoship/references/ci-integration.md:191Low confidence
- Network access in code of documentationautoship/references/ci-integration.md:191Low confidence
- Access to secrets in code of documentationautoship/references/ci-integration.md:191Low confidence
- Dangerous shell operation in code of documentationautoship/references/ci-integration.md:192Low confidence
- Dangerous shell operation in code of documentationautoship/references/ci-integration.md:193Low confidence
- Network access in code of documentationautoship/references/commands.md:65Low confidence
- Network access in code of documentationautoship/references/commands.md:67Low confidence
- Access to secrets in prose of documentationautoship/references/commands.md:90Low confidence
- Network access in code of documentationautoship/references/configuration.md:38Low confidence
- Network access in code of documentationautoship/references/configuration.md:39Low confidence
- Network access in code of documentationautoship/references/configuration.md:40Low confidence
- Network access in code of documentationautoship/references/configuration.md:44Low confidence
- Network access in code of documentationautoship/references/configuration.md:45Low confidence
- Network access in code of documentationautoship/references/configuration.md:46Low confidence
- Network access in prose of documentationautoship/references/configuration.md:84Low confidence
- Executable script in code of a file that runsautoship/templates/automated-release.sh:1High confidence
- Network access in code of a file that runsautoship/templates/automated-release.sh:24High confidence
- Network access in code of a file that runsautoship/templates/automated-release.sh:25High confidence
- Network access in code of a file that runsautoship/templates/automated-release.sh:26High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valueautoship/templates/automated-release.sh:36Low confidence
- Access to secrets in code of a file that runsautoship/templates/automated-release.sh:37High confidence
- Executable script in code of a file that runsautoship/templates/setup-repo.sh:1High confidence
- Network access in code of a file that runsautoship/templates/setup-repo.sh:32High confidence
- Network access in code of a file that runsautoship/templates/setup-repo.sh:34High confidence
- Network access in code of a file that runsautoship/templates/setup-repo.sh:36High confidence
- Network access in code of a file that runsautoship/templates/setup-repo.sh:37High confidence
- Network access in code of a file that runsautoship/templates/setup-repo.sh:38High confidence
- Network access in code of a file that runsautoship/templates/setup-repo.sh:44High confidence
- Network access in code of a file that runsautoship/templates/setup-repo.sh:45High confidence
- Network access in code of a file that runsautoship/templates/setup-repo.sh:46High confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md skills/autoship/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Native | Path .cursor/skills/ai-sdk | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/autoship/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/autoship/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/autoship/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.
