Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook.

MITAuto-check passedDevOps & Cloud

Install CI

skills CLI
$ npx skills add aiblueprinthq/ai-blueprint --skill ci -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install aiblueprinthq/ai-blueprint ci --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/aiblueprinthq/ai-blueprint.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ci .claude/skills/ci && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ci
GitHub stars
463
Token cost
~2.2k tokens
SKILL.md length
1,286 words
Files
1
Skills in repo
20
Repo updated
First seen
Licence
MIT

At a glance

Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook.

  • Works in 5 steps: inspect without changing files → define one Verify command → create or align the workflow → …
  • GitHub Actions setup
  • SKILL.md covers Input, Step 1 - inspect without…, Step 2 - define one Verify… and Step 3 - create or align the…, plus 6 more sections
  • Calls git

What it does

CI is an agent skill from aiblueprinthq/ai-blueprint. Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook. Use for /ci, GitHub Actions setup, pull-request checks, automatic checks, pre-push hooks, or aligning typecheck, test, and build verification.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering CI/CD and Pull requests. It works with GitHub Actions and GitHub. The repository describes itself as: A file-backed, spec-driven AI coding workflow framework for building real software while staying in control. The licence is MIT.

When your agent uses it

  • GitHub Actions setup
  • Pull-request checks
  • Automatic checks
  • Aligning typecheck

Example prompts

  • “/ci”

Requirements

  • Node.js

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. inspect without changing files
  2. define one Verify command
  3. create or align the workflow
  4. prove the setup locally
  5. report

What it can do on your machine

Read from SKILL.md and the folder at commit 96222b7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

CI loads about 2.2k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 1,286 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aiblueprinthq/ai-blueprint at commit 96222b7, republished under its MIT licence (© aiblueprinthq). 1,286 words, ~2,232 tokens.

Download SKILL.mdSave it as .claude/skills/ci/SKILL.md (or your agent's skills folder).
name
ci
description
Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook. Use for /ci, GitHub Actions setup, pull-request checks, automatic checks, pre-push hooks, or aligning typecheck, test, and build verification.

ci - set up automatic GitHub checks

Context reuse: Reuse any required file already loaded in project instructions or the current session. Read it again only if absent, changed, or exact current bytes or line references are needed.

First action: Before project inspection, preflight, or any other tool call, publish running to blueprint/.state/run.json using the dashboard activity contract in AGENTS.md.

Where this sits in the workflow:

/onboard or /adopt  ->  [ci]  ->  Verify locally  ->  GitHub runs Verify
(project commands)     (setup)    (same recipe)      (pull requests)

This skill gives local work and GitHub one shared automated command. It is an optional setup task, not a requirement for using the Blueprint.

Keep the beginner explanation simple:

  • Verify is the recipe. It runs checks the project already has.
  • GitHub Actions is the worker. It runs the same recipe automatically.
  • A GitHub ruleset is the lock. That optional remote setting can require the worker to report green before merge.
  • A pre-push hook is the early warning. That optional local setting runs the recipe before a push leaves the machine. It is a convenience, not the lock: git push --no-verify skips it.

This skill configures the recipe and worker, and adds the hook only when the user opts in. It never changes the remote ruleset, pushes, publishes, or deploys.

Input

No argument is required. A named provider or workflow preference is a request to review, not permission to replace existing CI. This skill's default provider is GitHub Actions because it creates GitHub pull-request checks.

Step 1 - inspect without changing files

Read enough to identify the real project setup:

  • AGENTS.md, especially Commands and any documented Verify command
  • package or language manifests and task-runner files
  • lockfiles and the package manager they imply
  • existing typecheck, test, build, lint, and other quality commands
  • test configuration and actual test files
  • runtime version files such as .nvmrc, .node-version, .python-version, go.mod, or rust-toolchain.toml
  • .github/workflows/ and any documented external CI
  • git's current branch, configured default branch, and remotes when available

Do not assume npm, Node.js, main, or GitHub from the Blueprint template. Do not run installs or edit files during inspection.

If an existing workflow already provides equivalent pull-request checks, explain what it runs. If it is healthy and aligned with a documented Verify command, report that no setup is needed. If normalization would change existing CI, show the proposed change and get explicit approval before editing it.

Step 2 - define one Verify command

Build one command from meaningful checks that actually exist, in this order:

  1. typecheck
  2. tests, only when a runner and real test command are configured
  3. build

Omit missing checks. Do not install a test runner, invent an empty test suite, or add a placeholder command. Lint, formatting, coverage, browser tests, security scans, dependency audits, and version matrices are not part of the beginner default. Preserve them when existing CI already requires them, and discuss any normalization before changing that behavior.

For JavaScript and TypeScript, add or reuse a package script named verify and invoke it with the detected package manager. For other stacks, use the existing native task runner or the smallest clear combined command. Document the exact invocation as Verify in the Commands section of AGENTS.md.

Examples are explanatory only. Never copy them without detecting the project:

text
Verify: npm run verify
Verify: make verify
Verify: cargo test && cargo build --locked

If no meaningful check exists, stop and explain what is missing. Do not create a workflow that always passes.

Step 3 - create or align the workflow

Create .github/workflows/verify.yml only when that path is free. If it already exists, never overwrite it silently. Show the exact proposed diff and ask before changing it.

The workflow should contain only what the detected project needs:

  • a clear workflow name such as Verify
  • pull_request
  • pushes to the detected default branch
  • permissions: contents: read
  • the real runtime version
  • checkout and the appropriate runtime setup action
  • the lockfile-safe dependency install command
  • one final step that runs the exact Verify command from AGENTS.md

If the default branch cannot be identified from git or project context, ask before writing the push trigger instead of guessing. Preserve all other workflow files. When another workflow overlaps, report the overlap and ask whether to reuse, align, or leave it alone.

Show full SKILL.md (587 more words)Show less

Step 3b - offer a local pre-push hook (opt-in)

After the workflow exists, ask one question and default to no:

Also add a local pre-push hook that runs Verify before every push? [y/N]

Skip the question when the request already answered it (for example "/ci with hook" or "no hook"). When the answer is no, write nothing and move on. When it is yes:

  1. Write .githooks/pre-push (mode 755) that announces itself and then runs the exact Verify command from AGENTS.md with exec, so the command's exit code is the hook's exit code.
  2. Point git at the folder: git config core.hooksPath .githooks.
  3. For JavaScript and TypeScript projects, add a prepare script, git config core.hooksPath .githooks 2>/dev/null || true, so a fresh install wires the hook without a manual step. The || true keeps installs working where no git checkout exists, such as a deploy build. For other stacks, document the git config line in the README instead.
  4. Run the hook once (.githooks/pre-push). If it fails, remove what this step added and report the failing subcommand. Never leave a hook the project cannot pass.

The hook and the workflow run the same Verify command; if one changes, the other changes with it. Say in the report that --no-verify bypasses the hook, so the GitHub ruleset remains the lock.

Step 4 - prove the setup locally

Run the exact documented Verify command locally. The individual build, test, or typecheck commands may still be run separately for diagnosis, but the final proof must use Verify because that is what GitHub will run.

A passing local run proves the recipe against the current working copy. It does not prove dependency installation or command behavior from a fresh checkout. Until the workflow is pushed and reports green on GitHub, describe the setup as prepared locally, not CI verified. The first successful GitHub run is the authoritative clean-checkout proof.

If Verify fails, report the failing subcommand and stop. Do not weaken the command, remove a legitimate check, or describe CI as ready.

Do not push the workflow. A local workflow file does nothing on GitHub until the user later approves a push.

Step 5 - report

Finish with a concise setup report:

  • existing CI found and whether it was preserved or changed
  • exact Verify command
  • checks included and checks omitted
  • test gate status
  • workflow path and triggers
  • whether a pre-push hook was added, and that --no-verify bypasses it
  • local Verify result and whether CI is only prepared locally or confirmed by a successful GitHub run
  • files changed
  • any overlap, uncertainty, or follow-up

Explain that making the GitHub check required is a separate remote ruleset choice after the workflow is pushed. Do not change repository settings or treat that as part of this skill.

Interaction with other skills

  • /tests adds the real test command to an existing Verify command, but never creates CI by itself.
  • /implement, /complete, and /autopilot run Verify when it is documented, with their existing fallback behavior when it is absent.
  • /doctor diagnoses drift between AGENTS.md, the project command, and the workflow. Missing CI remains informational.

Rules

  • Preserve existing CI and custom checks.
  • Never invent tests or install a runner as part of CI setup.
  • Never add coverage, browser tests, security scans, or matrices by default.
  • Add a git hook only through the Step 3b opt-in, never silently.
  • Never push or change a remote ruleset without separate explicit approval.
  • Keep one exact Verify command shared by local work and GitHub.

Formatting

Format the output to match the project's conventions in blueprint/context/ai-interaction.md: concise, scannable markdown, with lists for enumerations and tables for matrices rather than dense paragraphs.

© aiblueprinthq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/ci of aiblueprinthq/ai-blueprint.

Open the folder on GitHubat commit 96222b7

Compare with similar skills

CI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

CI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CI this skillaiblueprinthq/ai-blueprint463—~2.2kAutomated safety check: PassMIT
Michel Monitor Pull Request GitHub ActionsPackmindHub/packmind318—~2.6kAutomated safety check: PassApache-2.0
CIopenJiuwen-ai/sciencediscovery159—~2.2kAutomated safety check: PassApache-2.0
Diy Netlifyswyxio/skills176—~1.1kAutomated safety check: PassMIT
ONNX Runtime CI Managementmicrosoft/onnxruntime22k—~4.1kAutomated safety check: PassMIT
Renovate Actions PR Reviewbacknotprop/plannotator9.3k—~640Automated safety check: PassApache-2.0

Similar skills

  • Diagnose a failed, stuck, or never-triggered CI run on a GitHub PR, apply a local fix if possible, push it, and document the result in a single running PR comment.

    318 GitHub stars~2.6k tokensUpdated yesterday
    DevOps & CloudAuto-check passed
  • CI

    openJiuwen-ai/sciencediscovery

    Read, diagnose, and change the CI pipeline: GitHub Actions on pull requests, the nightly schedule and the release tag.

    159 GitHub stars~2.2k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Diy Netlify

    swyxio/skills

    Build or audit an isolated Netlify/Vercel-style pull-request preview workflow using GitHub Actions and the project's existing hosting provider.

    176 GitHub stars~1.1k tokensUpdated 5 days ago
    DevOps & CloudAuto-check passed
  • ONNX Runtime CI Management

    microsoft/onnxruntime

    Official

    Triggers, re-runs and unblocks the CI checks on an ONNX Runtime pull request, after diagnosing whether a failure is transient or needs a code change.

    22k GitHub stars~4.1k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Renovate Actions PR Review

    backnotprop/plannotator

    Reviews Renovate pull requests that bump GitHub Actions by checking pinned SHAs against upstream tags, scanning changelogs and confirming workflows stay compatible.

    9.3k GitHub stars~640 tokensUpdated today
    DevelopmentAuto-check passed
  • Generates and optimizes GitHub Actions workflows with swarm coordination, using named modes for PR management, issue tracking, releases and repository structure.

    818 GitHub starsUsed in 6 repos~6k tokens
    DevOps & CloudAuto-check passed

More from aiblueprinthq/ai-blueprint

All 20 skills in this repo
  • Adopt

    aiblueprinthq/ai-blueprint

    Adopt Blueprint into an existing brownfield codebase by surveying shipped behavior and generating plans, standards, commands, adapter choices, and visibility setup.

    463 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed
  • Doctor

    aiblueprinthq/ai-blueprint

    Run a Blueprint health and context check covering setup, adapters, commands, visibility, plans, overview freshness, configuration, dashboard state, and workflow drift.

    463 GitHub stars~4.5k tokensUpdated yesterday
    Auto-check: notes
  • Feature

    aiblueprinthq/ai-blueprint

    Turn the next, named, or numbered build-plan feature into a buildable current-feature.md spec with small steps and done-when criteria.

    463 GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed
  • Onboard

    aiblueprinthq/ai-blueprint

    Onboard a fresh or early scaffold after Blueprint is overlaid by tuning commands, standards, adapters, visibility, and context loading.

    463 GitHub stars~4.5k tokensUpdated yesterday
    Auto-check passed
  • Overview

    aiblueprinthq/ai-blueprint

    Validate and normalize project-plan.md and build-plan.md, then generate the durable project-overview.md used by agents.

    463 GitHub stars~3.8k tokensUpdated yesterday
    Auto-check passed
  • Brief

    aiblueprinthq/ai-blueprint

    Brief an upcoming build-plan feature without writing files. An agent skill from aiblueprinthq/ai-blueprint.

    463 GitHub stars~1.3k tokensUpdated yesterday
    Auto-check passed

Questions about CI

What does CI do?

Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook. CI is an agent skill from aiblueprinthq/ai-blueprint. Set up or normalize one project Verify command and matching GitHub Actions checks while preserving existing CI, with an optional local pre-push hook.

When should I use CI?

CI fits situations like: GitHub Actions setup; pull-request checks; automatic checks; aligning typecheck.

How do I install CI in Claude Code?

Run `npx skills add aiblueprinthq/ai-blueprint --skill ci -a claude-code`. Or copy the skill folder (.agents/skills/ci in aiblueprinthq/ai-blueprint) into .claude/skills/ci in your project. Claude Code loads it when a task matches its description.

How do I install CI in Codex?

Run `npx skills add aiblueprinthq/ai-blueprint --skill ci -a codex`. Or copy the skill folder (.agents/skills/ci in aiblueprinthq/ai-blueprint) into .agents/skills/ci in your project. Codex loads it when a task matches its description.

Can I use CI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add aiblueprinthq/ai-blueprint --skill ci -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ci, .gemini/skills/ci, .github/skills/ci and .opencode/skills/ci in your project.

What does CI need to run?

Going by SKILL.md and its folder, CI needs the command-line tools its instructions call (git). Our summary lists: Node.js.

Does CI access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is CI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does CI use?

CI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does CI use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to CI?

Skills that share tags, products or a category with CI: Michel Monitor Pull Request GitHub Actions (PackmindHub/packmind, 318 stars), CI (openJiuwen-ai/sciencediscovery, 159 stars), Diy Netlify (swyxio/skills, 176 stars) and ONNX Runtime CI Management (microsoft/onnxruntime, 22k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CI?

aiblueprinthq (a GitHub organization) maintains it in aiblueprinthq/ai-blueprint, which has 463 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 8, 2026.

Source: aiblueprinthq/ai-blueprint on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.