Agent skill

CI CD

by WrongStack in WrongStack/WrongStack

Build and repair reproducible CI and deployment workflows with explicit artifacts, permissions and release gates.

MITAuto-check passedDevOps & Cloud

Install CI CD

skills CLI
$ npx skills add WrongStack/WrongStack --skill ci-cd -a claude-code

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

GitHub CLI
$ gh skill install WrongStack/WrongStack ci-cd --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/WrongStack/WrongStack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/core/skills/ci-cd .claude/skills/ci-cd && 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-cd
GitHub stars
371
Token cost
~830 tokens
SKILL.md length
340 words
Files
1
Skills in repo
100
Repo updated
First seen
Licence
MIT

At a glance

Build and repair reproducible CI and deployment workflows with explicit artifacts, permissions and release gates.

  • Works in 6 steps: Reproduce the failing authoritative… → Use the latest stable toolchain target… → Give jobs minimal permissions. Pin… → …
  • Working on GitHub Actions
  • SKILL.md covers Selection card, Overview, Rules and Workflow, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

CI CD is an agent skill from WrongStack/WrongStack. Build and repair reproducible CI and deployment workflows with explicit artifacts, permissions and release gates. Use when working on GitHub Actions or other pipelines, caches, matrices, packaging or deployment evidence; preserve the authoritative checks and never hide failures.

Its SKILL.md is about 830 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 Deployment. It works with GitHub Actions. The repository describes itself as: An AI coding agent that reads your code, edits files, runs commands, and reasons through bugs — across a terminal REPL, a full-screen TUI, and a browser UI, while you keep your… The licence is MIT.

When your agent uses it

  • Working on GitHub Actions
  • Other pipelines
  • Deployment evidence
  • Preserve the authoritative checks and never hide failures

Example prompts

  • “/ci-cd”

Requirements

  • Docker

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Reproduce the failing authoritative command before editing a pipeline.
  2. Use the latest stable toolchain target when updating it; verify runner image,
  3. Give jobs minimal permissions. Pin third-party actions to reviewed commit SHAs
  4. Keep untrusted PR data out of shell code. Pass it as data through environment
  5. Cache dependencies/build inputs with keys that cover the lockfile, runtime
  6. Serialize release/shared artifact writers. Failures and skipped jobs remain

What it can do on your machine

Read from SKILL.md and the folder at commit a744bdc. 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

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    Links to these hosts (documentation or services it may open):

    • docs.github.com

    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 CD loads about 830 tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 340 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~830

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 WrongStack/WrongStack at commit a744bdc, republished under its MIT licence (© WrongStack). 340 words, ~830 tokens.

Download SKILL.mdSave it as .claude/skills/ci-cd/SKILL.md (or your agent's skills folder).
name
ci-cd
description
Build and repair reproducible CI and deployment workflows with explicit artifacts, permissions and release gates. Use when working on GitHub Actions or other pipelines, caches, matrices, packaging or deployment evidence; preserve the authoritative checks and never hide failures.
version
1.0.1
trigger
working on GitHub Actions or other pipelines, caches, matrices, packaging or deployment evidence; preserve the authoritative checks and never hide failures.
required-capabilities
filesystem.read, filesystem.write
optional-capabilities
verification.run, web.research
metadata.routing-group
operations

CI/CD

Selection card

  • Task: Build automated CI checks and delivery pipelines. / TR: Otomatik CI kontrolleri ve teslim pipeline kur.
  • Start: Identify the authorized target, current health and rollback boundary.
  • Finish: apply the acceptance checks below; report observed results and unresolved constraints.

Overview

Make the pipeline validate the exact source and artifact being shipped. Distinguish a local check, hosted CI result, published artifact and deployed service. They are separate evidence boundaries.

Rules

  1. Reproduce the failing authoritative command before editing a pipeline. Inspect trigger, job dependencies, working directory, runtime and lockfile.
  2. Use the latest stable toolchain target when updating it; verify runner image, action version, engine/peer constraints and official migration notes.
  3. Give jobs minimal permissions. Pin third-party actions to reviewed commit SHAs with identifiable release comments where repository policy calls for it.
  4. Keep untrusted PR data out of shell code. Pass it as data through environment variables or structured arguments; never run untrusted code with release secrets.
  5. Cache dependencies/build inputs with keys that cover the lockfile, runtime and platform. A cache hit is not evidence that today's tests ran.
  6. Serialize release/shared artifact writers. Failures and skipped jobs remain visible; do not add continue-on-error to make a required gate appear green.

Workflow

  1. Map trigger → checks → build → artifact → deployment and who may run each.
  2. Fix the narrow source/config cause. Preserve unrelated baselines and required branch rules.
  3. Run focused local checks and workflow validation available in the repo.
  4. If remote execution is authorized, inspect jobs for the exact commit, read failed logs and verify required checks rather than an old successful run.
  5. Before release, inspect artifact contents, version identity and install/startup.
  6. Report commands, hosted run/commit when applicable, artifact/deployment status and remaining environment-specific gaps.

Sources

GitHub secure workflow use, reviewed 2026-10-09. Follow the selected CI platform's own current contracts.

Acceptance checks

  • Validate the workflow syntax, least-privilege credentials, matrix conditions and the actual job results.

Skills in scope

  • tech-stack — current compatible runtimes/dependencies.
  • docker-deploy — image build/startup.
  • verify-before-done — completion evidence.
  • git-flow — exact reviewed changes and publication authorization.

© WrongStack, 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 packages/core/skills/ci-cd of WrongStack/WrongStack.

Open the folder on GitHubat commit a744bdc

Compare with similar skills

CI CD 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 CD compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
CI CD this skillWrongStack/WrongStack371—~830Automated safety check: PassMIT
Senior DevOps Toolkitmaslennikov-ig/claude-code-orchestrator-kit2606 repos~1.1kAutomated safety check: NotesCustom licence
AI News RadarLearnPrompt/ai-news-radar1.8k—~2.5kAutomated safety check: NotesMIT
Use Vercel Actionamondnet/vercel-action764—~2.7kAutomated safety check: PassMIT
Prepare Cloudflare Production DeploymentLubomirGeorgiev/cloudflare-workers-nextjs-saas-template786—~5.9kAutomated safety check: NotesMIT
Deployments Cicdvercel/vercel-plugin3011 repos~3kAutomated safety check: PassCustom licence

Similar skills

  • Senior DevOps Toolkit

    maslennikov-ig/claude-code-orchestrator-kit

    Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup…

    260 GitHub starsUsed in 6 repos~1.1k tokens
    DevOps & CloudAuto-check: notes
  • AI News Radar

    LearnPrompt/ai-news-radar

    A skill your agent uses when working on AI News Radar, 24 小时 AI 更新雷达, AI 更新雷达, 伯乐Skill, or Scout Skill: finding high-signal AI/tech sources, adding RSS/OPML/GitHub feeds, checking source health…

    1.8k GitHub stars~2.5k tokensUpdated today
    DevOps & CloudAuto-check: notes
  • Use Vercel Action

    amondnet/vercel-action

    Wire amondnet/vercel-action into a GitHub Actions workflow to deploy Vercel projects from CI.

    764 GitHub stars~2.7k tokensUpdated 2 mo ago
    DevOps & CloudAuto-check passed
  • Prepare Cloudflare Production Deployment

    LubomirGeorgiev/cloudflare-workers-nextjs-saas-template

    Source-of-truth runbook for preparing this Vinext Cloudflare Workers SaaS template for production deployment.

    786 GitHub stars~5.9k tokensUpdated yesterday
    DevOps & CloudAuto-check: notes
  • Deployments Cicd

    vercel/vercel-plugin

    Official

    Vercel deployment and CI/CD expert guidance. An agent skill from vercel/vercel-plugin.

    301 GitHub starsUsed in 1 repo~3k tokens
    DevOps & CloudAuto-check passed
  • Azure Bicep Skill

    timothywarner-org/claude-code

    A skill your agent uses when authoring, reviewing, or refactoring Azure Bicep code.

    224 GitHub stars~2.9k tokensUpdated 2 mo ago
    DevOps & CloudAuto-check passed

More from WrongStack/WrongStack

All 100 skills in this repo
  • Tech Stack

    WrongStack/WrongStack

    Validate and upgrade dependencies against live registries and official migration guides in any ecosystem.

    371 GitHub stars~1.5k tokensUpdated today
    Auto-check passed
  • Skill Creator

    WrongStack/WrongStack

    Create, improve and validate WrongStack SKILL.md bundles with precise discovery, progressive resources and current runtime contracts.

    371 GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Bug Hunter

    WrongStack/WrongStack

    A skill your agent uses when scanning source code for bugs, anti-patterns, code smells, or quality issues in a codebase, or when running a proof-driven bug hunt that must find, prove, fix, and…

    371 GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Design Craft

    WrongStack/WrongStack

    Design or substantially improve user-facing interfaces with a product-specific visual direction, content hierarchy, and rendered critique.

    371 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Design Critique

    WrongStack/WrongStack

    A skill your agent uses to audit an interface that already exists and say precisely why it looks generated, templated, or unfinished — a scored rubric across composition, typography, color, states…

    371 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Mailbox Bridge

    WrongStack/WrongStack

    A skill your agent uses when external coding agents (Claude Code, Aider, custom scripts) need to participate in the project's shared WrongStack mailbox, or when a user asks to "expose the mailbox"…

    371 GitHub stars~2.6k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about CI CD

What does CI CD do?

Build and repair reproducible CI and deployment workflows with explicit artifacts, permissions and release gates. CI CD is an agent skill from WrongStack/WrongStack. Build and repair reproducible CI and deployment workflows with explicit artifacts, permissions and release gates.

When should I use CI CD?

CI CD fits situations like: working on GitHub Actions; other pipelines; deployment evidence; preserve the authoritative checks and never hide failures.

How do I install CI CD in Claude Code?

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

How do I install CI CD in Codex?

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

Can I use CI CD 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 WrongStack/WrongStack --skill ci-cd -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-cd, .gemini/skills/ci-cd, .github/skills/ci-cd and .opencode/skills/ci-cd in your project.

What does CI CD need to run?

SKILL.md names no scripts, command-line tools or credentials: CI CD is instructions for the agent only. Our summary lists: Docker.

Does CI CD access the network?

SKILL.md names 1 domain. As links in the text: docs.github.com. This is read from the text; nothing was executed.

Is CI CD 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 CD use?

CI CD 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 CD use?

About 830 tokens (SKILL.md is roughly 3.3k 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 CD?

Skills that share tags, products or a category with CI CD: Senior DevOps Toolkit (maslennikov-ig/claude-code-orchestrator-kit, 260 stars), AI News Radar (LearnPrompt/ai-news-radar, 1.8k stars), Use Vercel Action (amondnet/vercel-action, 764 stars) and Prepare Cloudflare Production Deployment (LubomirGeorgiev/cloudflare-workers-nextjs-saas-template, 786 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains CI CD?

WrongStack (a GitHub organization) maintains it in WrongStack/WrongStack, which has 371 GitHub stars. The repository holds 100 skills in this directory. The repository was last updated on October 10, 2026.

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