Official agent skill

Cali

by callstackincubator in callstackincubator/cali

A skill your agent uses when working in the Cali repository or when you need to run, extend, or debug the Cali CLI for mobile React Native and Expo workflows.

OfficialMITAuto-check passedMobile

Install Cali

skills CLI
$ npx skills add callstackincubator/cali --skill cali -a claude-code

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

GitHub CLI
$ gh skill install callstackincubator/cali cali --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/callstackincubator/cali.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/cali .claude/skills/cali && 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
cali
GitHub stars
991
Token cost
~731 tokens
SKILL.md length
296 words
Files
4 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when working in the Cali repository or when you need to run, extend, or debug the Cali CLI for mobile React Native and Expo workflows.

  • Works in 4 steps: Load references/running-cali.md. → If the task changes implementation or… → Confirm which command is actually in… → …
  • Working in the Cali repository
  • SKILL.md covers Default operating rules, Default flow, Command surface and Runtime modes, plus 2 more sections
  • Calls eas

What it does

Cali is an agent skill from callstackincubator/cali, published by the product's own GitHub organization. Use when working in the Cali repository or when you need to run, extend, or debug the Cali CLI for mobile React Native and Expo workflows. Covers Cali commands (qa, review, perf-review, dev), the shared cali-context.json contract, local mode selection, required local CLIs, provider setup, and CI integration patterns.

Its SKILL.md is about 730 tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `agents/openai.yaml`, `references/extending-cali.md` and `references/running-cali.md`).

It sits in Mobile, covering Cross-platform mobile apps and Third-party API integration. It works with React Native and Expo. The repository describes itself as: AI agent for building React Native apps. The licence is MIT.

When your agent uses it

  • Working in the Cali repository
  • You need to run
  • Debug the Cali CLI for mobile React Native and Expo workflows

Example prompts

  • “/cali”

Workflow steps

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

  1. Load references/running-cali.md.
  2. If the task changes implementation or runtime behavior, then load references/extending-cali.md.
  3. Confirm which command is actually in scope before changing code or docs.
  4. Keep the task aligned to the current runtime model: command + local/CI mode + shared context + tool packs + publishers.

What it can do on your machine

Read from SKILL.md and the folder at commit 3bdc4da. 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:

    • eas

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

  • Network

    No URLs in SKILL.md.

    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

Cali loads about 731 tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 296 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~83
When it runs · the whole SKILL.md, loaded when a task matches
~731
With references · SKILL.md plus every file in references/, read only if the agent opens them
~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 callstackincubator/cali at commit 3bdc4da, republished under its MIT licence (© callstackincubator). 296 words, ~731 tokens.

Download SKILL.mdSave it as .claude/skills/cali/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
cali
description
Use when working in the Cali repository or when you need to run, extend, or debug the Cali CLI for mobile React Native and Expo workflows. Covers Cali commands (`qa`, `review`, `perf-review`, `dev`), the shared `cali-context.json` contract, local mode selection, required local CLIs, provider setup, and CI integration patterns.

Cali

Use this skill as a router with mandatory defaults. Read this file first. For normal Cali tasks, always load references/running-cali.md before acting. If the task changes Cali itself, also load references/extending-cali.md.

Default operating rules

  • Start with the shipped command surface and docs. Do not invent new Cali commands, envs, or config shapes.
  • Treat qa as the stable command. Treat review, perf-review, and dev as experimental unless the task explicitly expands them.
  • Prefer the shared cali-context.json contract over workflow-specific runtime scraping.
  • Keep setup and CI instructions copy-pasteable when editing docs.
  • If the task is about running Cali, verify the required local CLIs and model credentials before assuming the environment is ready.
  • Required role skills are Cali-managed; local CLIs are not.
  • If the task is about changing Cali, prefer small explicit runtime contracts over broad abstraction.

Default flow

  1. Load references/running-cali.md.
  2. If the task changes implementation or runtime behavior, then load references/extending-cali.md.
  3. Confirm which command is actually in scope before changing code or docs.
  4. Keep the task aligned to the current runtime model: command + local/CI mode + shared context + tool packs + publishers.

Command surface

  • cali qa
    • ship-ready mobile QA with agent-device
  • cali review
    • experimental findings-first repository review
  • cali perf-review
    • experimental runtime performance review with agent-device and agent-react-devtools
  • cali dev
    • experimental repository-backed implementation flow

Runtime modes

  • local mobile: --local android|ios
  • CI: implicit provider detection in GitHub Actions and EAS, with optional --ci github-actions|eas override

Required references

  • For every normal Cali task, after reading this file, load references/running-cali.md first.
  • If the task changes code, runtime behavior, or extension points, also load references/extending-cali.md.
  • Load additional repo files only after you identify the owning command, role, or runtime module.

Additional references

  • Public CLI, provider setup, required CLIs, and copy-pasteable CI examples: packages/cali/README.md
  • Repo implementation guidance and validation expectations: AGENTS.md

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

Files

SKILL.md and 3 other files (references) in skills/cali of callstackincubator/cali.

  • SKILL.md
  • agents/openai.yaml
  • references/extending-cali.md
  • references/running-cali.md

Open the folder on GitHubat commit 3bdc4da

Compare with similar skills

Cali 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.

Cali compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cali this skillcallstackincubator/cali991—~731Automated safety check: PassMIT
Adynato Mobile APImajiayu000/claude-skill-registry6661 repos~2.5kAutomated safety check: PassMIT
React Native Best Practicesvercel-labs/openreview1.7k17 repos~1.1kAutomated safety check: PassMIT
Appllama App Design SkillAppllama/appllama-skills2.5k1 repos~5kAutomated safety check: PassMIT
Appllama UsageAppllama/appllama-skills2.5k1 repos~1.6kAutomated safety check: PassMIT
Release Sample SweepAtmosphere/atmosphere3.8k—~4.2kAutomated safety check: PassApache-2.0

Similar skills

  • Adynato Mobile API

    majiayu000/claude-skill-registry

    API integration patterns for Adynato mobile apps. An agent skill from majiayu000/claude-skill-registry.

    666 GitHub starsUsed in 1 repo~2.5k tokens
    MobileAuto-check passed
  • React Native Best Practices

    vercel-labs/openreview

    Official

    A prioritized rule set for React Native and Expo apps covering list performance, animation, navigation, UI patterns, state, rendering, monorepos and configuration.

    1.7k GitHub starsUsed in 17 repos~1.1k tokens
    MobileAuto-check passed
  • Appllama App Design Skill

    Appllama/appllama-skills

    Build native-feeling, benchmark-quality mobile app screens (Expo / React Native).

    2.5k GitHub starsUsed in 1 repo~5k tokens
    MobileAuto-check passed
  • Appllama Usage

    Appllama/appllama-skills

    Use the Appllama MCP (mcp.appllama.io) well — research real top-grossing mobile apps, their screens, flows, and UI elements, then build from what you learn.

    2.5k GitHub starsUsed in 1 repo~1.6k tokens
    MobileAuto-check passed
  • Release Sample Sweep

    Atmosphere/atmosphere

    Run the pre-release end-to-end sweep of every user-facing surface — the 33 samples under samples/ (booted from their packaged artifacts and driven in a real browser via chrome-devtools MCP), the…

    3.8k GitHub stars~4.2k tokensUpdated yesterday
    MobileAuto-check passed
  • App Store Review

    safaiyeh/app-store-review-skill

    Evaluates code against Apple's App Store Review Guidelines. An agent skill from safaiyeh/app-store-review-skill.

    362 GitHub starsUsed in 1 repo~3.4k tokens
    MobileAuto-check passed

Categories

Questions about Cali

What does Cali do?

A skill your agent uses when working in the Cali repository or when you need to run, extend, or debug the Cali CLI for mobile React Native and Expo workflows. Cali is an agent skill from callstackincubator/cali, published by the product's own GitHub organization. Use when working in the Cali repository or when you need to run, extend, or debug the Cali CLI for mobile React Native and Expo workflows.

When should I use Cali?

Cali fits situations like: working in the Cali repository; you need to run; debug the Cali CLI for mobile React Native and Expo workflows.

How do I install Cali in Claude Code?

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

How do I install Cali in Codex?

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

Can I use Cali 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 callstackincubator/cali --skill cali -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cali, .gemini/skills/cali, .github/skills/cali and .opencode/skills/cali in your project.

What does Cali need to run?

Going by SKILL.md and its folder, Cali needs the command-line tools its instructions call (eas).

Does Cali access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cali 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 Cali use?

Cali 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 Cali use?

About 731 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 1.3k tokens, read only when the agent opens those files.

What are the alternatives to Cali?

Skills that share tags, products or a category with Cali: Adynato Mobile API (majiayu000/claude-skill-registry, 666 stars), React Native Best Practices (vercel-labs/openreview, 1.7k stars), Appllama App Design Skill (Appllama/appllama-skills, 2.5k stars) and Appllama Usage (Appllama/appllama-skills, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cali?

callstackincubator (a GitHub organization, an official publisher) maintains it in callstackincubator/cali, which has 991 GitHub stars. The repository was last updated on July 1, 2026.

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