How do I install the Local CI Simulation skill?

Run npx skillmds@latest add tomevault-io/local-ci-simulation in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Local CI Simulation safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Local CI Simulation?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Local CI Simulation free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Local CI Simulation?

tomevault-io (@tomevault-io) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Local CI Simulation by tomevault-io

Name: Local CI Simulation
Author: tomevault-io

Local CI Simulation

Simulate GitHub Actions CI locally for this repository by mapping workflow jobs to terminal commands, running phases step-by-step, isolating failing stages, and reporting exact root causes with fix suggestions. Use when CI is red, when validating a fix before push, or when user asks for phased local CI verification. Always propose full simulation first and run it only after explicit user confirmation because it is resource-intensive. Use when this capability is needed.

tomevault-io 5c896c8 2 files · 2.8 KB Updated Sep 17, 2026

File contents

Local Ci Simulation

Core Policy

Offer full local CI simulation before running it.
Start full simulation only after explicit user confirmation.
Prefer lightweight targeted checks first when user has not requested full run.
Preserve command order from workflow files and report exact failing phase.

Workflow

Inspect .github/workflows/tests.yml and .github/workflows/release.yml.
Build a phase list that mirrors CI jobs and step order.
Ask whether to run:
- focused mode: failing phase only;
- full mode: all heavy phases sequentially.
Run selected phases and stop at first failing command unless user asks to continue.
Distinguish non-fatal warnings from fatal errors.
Report:
- failing phase name;
- command;
- key error lines;
- minimal fix;
- post-fix recheck commands.

Repo Command Map

Use these commands as default simulation phases for this repository:

make .yarnrc.yml
yarn install
yarn workspaces foreach -A --topological-dev run build
yarn eslint
yarn test
yarn test:coverage
yarn vitest run -c packages/v1-contexts/vitest.config.ts --typecheck.only --typecheck.checker tsc --typecheck.tsconfig packages/v1-contexts/tsconfig.json
yarn workspace @retailcrm/embed-ui-v1-components run storybook:build

Practical Notes

Re-run the exact failing command after applying a fix.
Run dependent follow-up checks for confidence (eslint, test, relevant build/storybook step).
Mention when output is truncated and provide the most diagnostic lines.

Converted and distributed by TomeVault — claim your Tome and manage your conversions.

---name: local-ci-simulationdescription: Simulate GitHub Actions CI locally for this repository by mapping workflow jobs to terminal commands, running phases step-by-step, isolating failing stages, and reporting exact root causes with fix suggestions. Use when CI is red, when validating a fix before push, or when user asks for phased local CI verification. Always propose full simulation first and run it only after explicit user confirmation because it is resource-intensive. Use when this capability is needed.---# Local Ci Simulation## Core Policy- Offer full local CI simulation before running it.- Start full simulation only after explicit user confirmation.- Prefer lightweight targeted checks first when user has not requested full run.- Preserve command order from workflow files and report exact failing phase.## Workflow1. Inspect `.github/workflows/tests.yml` and `.github/workflows/release.yml`.2. Build a phase list that mirrors CI jobs and step order.3. Ask whether to run: - focused mode: failing phase only; - full mode: all heavy phases sequentially.4. Run selected phases and stop at first failing command unless user asks to continue.5. Distinguish non-fatal warnings from fatal errors.6. Report: - failing phase name; - command; - key error lines; - minimal fix; - post-fix recheck commands.## Repo Command MapUse these commands as default simulation phases for this repository:```bashmake .yarnrc.ymlyarn installyarn workspaces foreach -A --topological-dev run buildyarn eslintyarn testyarn test:coverageyarn vitest run -c packages/v1-contexts/vitest.config.ts --typecheck.only --typecheck.checker tsc --typecheck.tsconfig packages/v1-contexts/tsconfig.jsonyarn workspace @retailcrm/embed-ui-v1-components run storybook:build```## Practical Notes- Re-run the exact failing command after applying a fix.- Run dependent follow-up checks for confidence (`eslint`, `test`, relevant build/storybook step).- Mention when output is truncated and provide the most diagnostic lines.---> Converted and distributed by [TomeVault](https://tomevault.io/claim/retailcrm) — claim your Tome and manage your conversions.

Frequently asked questions