Asc Shots Pipeline logo

Asc Shots Pipeline

OrganizationPopular
rorkai
asc-shots-pipeline

Orchestrate iOS screenshot automation with xcodebuild/simctl for build-run, AXe for UI actions, JSON settings and plan files, Koubou-based framing (`asc screenshots frame`), and screenshot upload (`asc screenshots upload`). Use when users ask for automated screenshot capture, AXe-driven simulator flows, frame composition, or screenshot-to-upload pipelines.

Overview

Publisherrorkai
Repositoryapp-store-connect-cli-skills
Skill nameasc-shots-pipeline
Stars
1K
Forks
63
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by rorkai on GitHub. Read the source before you install it.

Installation

Install the Asc Shots Pipeline AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/rorkai/app-store-connect-cli-skills/tree/main/skills/asc-shots-pipeline
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/rorkai/app-store-connect-cli-skills.git /tmp/app-store-connect-cli-skills
mkdir -p .claude/skills
cp -r /tmp/app-store-connect-cli-skills/skills/asc-shots-pipeline .claude/skills/asc-shots-pipeline
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Asc Shots Pipeline in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Asc Shots Pipeline on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Asc Shots Pipeline is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

asc screenshots pipeline (xcodebuild -> AXe -> frame -> asc)

Use this skill for agent-driven screenshot workflows where the app is built and launched with Xcode CLI tools, UI is driven with AXe, and screenshots are uploaded with asc.

Current scope

  • Implemented now: build/run, AXe plan capture, frame composition, and upload.
  • Device discovery is built-in via asc screenshots list-frame-devices.
  • Local screenshot automation commands are experimental in asc cli.
  • Framing is pinned to Koubou 0.18.1 for deterministic output.
  • Feedback/issues: https://github.com/rorkai/App-Store-Connect-CLI/issues/new/choose

Defaults

  • Settings file: .asc/shots.settings.json
  • Capture plan: .asc/screenshots.json
  • Raw screenshots dir: ./screenshots/raw
  • Framed screenshots dir: ./screenshots/framed
  • Default frame device: iphone-air

1) Create settings JSON first

Create or update .asc/shots.settings.json:

json
{
  "version": 1,
  "app": {
    "bundle_id": "com.example.app",
    "project": "MyApp.xcodeproj",
    "scheme": "MyApp",
    "simulator_udid": "booted"
  },
  "paths": {
    "plan": ".asc/screenshots.json",
    "raw_dir": "./screenshots/raw",
    "framed_dir": "./screenshots/framed"
  },
  "pipeline": {
    "frame_enabled": true,
    "upload_enabled": false
  },
  "upload": {
    "version_localization_id": "",
    "device_type": "IPHONE_65",
    "source_dir": "./screenshots/framed"
  }
}

If you intentionally skip framing, set:

  • "frame_enabled": false
  • "upload.source_dir": "./screenshots/raw"

2) Build and run app on simulator

Use Xcode CLI for build/install/launch:

bash
xcrun simctl boot "$UDID" || true

xcodebuild \
  -project "MyApp.xcodeproj" \
  -scheme "MyApp" \
  -configuration Debug \
  -destination "platform=iOS Simulator,id=$UDID" \
  -derivedDataPath ".build/DerivedData" \
  build

xcrun simctl install "$UDID" ".build/DerivedData/Build/Products/Debug-iphonesimulator/MyApp.app"
xcrun simctl launch "$UDID" "com.example.app"

Use xcodebuild -showBuildSettings if the app bundle path differs from the default location.

3) Capture screenshots with AXe (or asc screenshots run)

Prefer plan-driven capture:

bash
asc screenshots run --plan ".asc/screenshots.json" --udid "$UDID" --output json

Useful AXe primitives during plan authoring:

bash
axe describe-ui --udid "$UDID"
axe tap --id "search_field" --udid "$UDID"
axe type "wwdc" --udid "$UDID"
axe screenshot --output "./screenshots/raw/home.png" --udid "$UDID"

Minimal .asc/screenshots.json example:

json
{
  "version": 1,
  "app": {
    "bundle_id": "com.example.app",
    "udid": "booted",
    "output_dir": "./screenshots/raw"
  },
  "steps": [
    { "action": "launch" },
    { "action": "wait", "duration_ms": 800 },
    { "action": "screenshot", "name": "home" }
  ]
}

4) Frame screenshots with asc screenshots frame

The asc CLI pins framing to Koubou 0.18.1. Install and verify before running framing steps:

bash
pip install koubou==0.18.1
kou --version  # expect 0.18.1
# If Koubou reports missing device frames, run once with network access:
kou setup-frames

List supported frame device values first:

bash
asc screenshots list-frame-devices --output json

Frame one screenshot (defaults to iphone-air):

bash
asc screenshots frame \
  --input "./screenshots/raw/home.png" \
  --output-dir "./screenshots/framed" \
  --device "iphone-air" \
  --output json

Supported --device values:

  • iphone-air (default)
  • iphone-17-pro
  • iphone-17-pro-max
  • iphone-16e
  • iphone-17
  • mac

5) Upload screenshots with asc

Generate and review artifacts before upload:

bash
asc screenshots review-generate --framed-dir "./screenshots/framed" --output-dir "./screenshots/review"
asc screenshots review-open --output-dir "./screenshots/review"
asc screenshots review-approve --all-ready --output-dir "./screenshots/review"

For reviewed multi-locale sets, prefer the plan/apply flow so existing remote screenshot counts are included before upload:

bash
asc screenshots plan --app "APP_ID" --version "1.2.3" --review-output-dir "./screenshots/review" --output json
asc screenshots apply --app "APP_ID" --version "1.2.3" --review-output-dir "./screenshots/review" --confirm --output json

Upload from the configured source directory (default ./screenshots/framed when framing is enabled):

bash
asc screenshots upload \
  --version-localization "LOC_ID" \
  --path "./screenshots/framed" \
  --device-type "IPHONE_65" \
  --output json

List or validate before upload when needed:

bash
asc screenshots sizes --output table
asc screenshots list --version-localization "LOC_ID" --output table

Agent behavior

  • Always confirm exact flags with --help before running commands.
  • Re-check command paths with asc screenshots --help because screenshot commands are evolving quickly.
  • Keep outputs deterministic: default to JSON for machine steps.
  • Prefer asc screenshots list-frame-devices --output json before selecting a frame device.
  • Ensure screenshot files exist before upload.
  • Use explicit long flags (--app, --output, --version-localization, etc.).
  • Treat screenshot-local automation as experimental and call it out in user-facing handoff notes.
  • Use asc screenshots plan / asc screenshots apply for reviewed batches when you need append-limit guardrails across existing remote screenshots.
  • If framing fails with a version error, re-install pinned Koubou: pip install koubou==0.18.1.
  • If framing fails because device frames are missing, run kou setup-frames once with network access.

6) Multi-locale capture (optional)

Do not use xcrun simctl launch ... -e AppleLanguages for localization. -e is an environment variable pattern and does not reliably switch app language.

For this pipeline, use simulator-wide locale defaults per UDID. This works with asc screenshots capture, which relaunches the app internally.

bash
# Map each locale to a dedicated simulator UDID.
# (Create these simulators once with `xcrun simctl create`.)
declare -A LOCALE_UDID=(
  ["en-US"]="UDID_EN_US"
  ["de-DE"]="UDID_DE_DE"
  ["fr-FR"]="UDID_FR_FR"
  ["ja-JP"]="UDID_JA_JP"
)

set_simulator_locale() {
  local UDID="$1"
  local LOCALE="$2"            # e.g. de-DE
  local LANG="${LOCALE%%-*}"   # de
  local APPLE_LOCALE="${LOCALE/-/_}" # de_DE

  xcrun simctl boot "$UDID" || true
  xcrun simctl spawn "$UDID" defaults write NSGlobalDomain AppleLanguages -array "$LANG"
  xcrun simctl spawn "$UDID" defaults write NSGlobalDomain AppleLocale -string "$APPLE_LOCALE"
}

for LOCALE in "${!LOCALE_UDID[@]}"; do
  UDID="${LOCALE_UDID[$LOCALE]}"
  echo "Capturing $LOCALE on $UDID..."
  set_simulator_locale "$UDID" "$LOCALE"

  xcrun simctl terminate "$UDID" "com.example.app" || true
  asc screenshots capture \
    --bundle-id "com.example.app" \
    --name "home" \
    --udid "$UDID" \
    --output-dir "./screenshots/raw/$LOCALE" \
    --output json
done

If you launch manually (outside asc screenshots capture), use app launch arguments:

bash
xcrun simctl launch "$UDID" "com.example.app" -AppleLanguages "(de)" -AppleLocale "de_DE"

7) Parallel execution for speed

Run one locale per simulator UDID in parallel:

bash
#!/bin/bash
# parallel-capture.sh

declare -A LOCALE_UDID=(
  ["en-US"]="UDID_EN_US"
  ["de-DE"]="UDID_DE_DE"
  ["fr-FR"]="UDID_FR_FR"
  ["ja-JP"]="UDID_JA_JP"
)

capture_locale() {
  local LOCALE="$1"
  local UDID="$2"
  local LANG="${LOCALE%%-*}"
  local APPLE_LOCALE="${LOCALE/-/_}"

  echo "Starting $LOCALE on $UDID"
  xcrun simctl boot "$UDID" || true
  xcrun simctl spawn "$UDID" defaults write NSGlobalDomain AppleLanguages -array "$LANG"
  xcrun simctl spawn "$UDID" defaults write NSGlobalDomain AppleLocale -string "$APPLE_LOCALE"
  xcrun simctl terminate "$UDID" "com.example.app" || true

  asc screenshots capture \
    --bundle-id "com.example.app" \
    --name "home" \
    --udid "$UDID" \
    --output-dir "./screenshots/raw/$LOCALE" \
    --output json

  echo "Completed $LOCALE"
}

for LOCALE in "${!LOCALE_UDID[@]}"; do
  capture_locale "$LOCALE" "${LOCALE_UDID[$LOCALE]}" &
done

wait
echo "All captures done. Now framing..."

Or use xargs with locale:udid pairs:

bash
printf "%s\n" \
  "en-US:UDID_EN_US" \
  "de-DE:UDID_DE_DE" \
  "fr-FR:UDID_FR_FR" \
  "ja-JP:UDID_JA_JP" | xargs -P 4 -I {} bash -c '
    PAIR="{}"
    LOCALE="${PAIR%%:*}"
    UDID="${PAIR##*:}"
    LANG="${LOCALE%%-*}"
    APPLE_LOCALE="${LOCALE/-/_}"
    xcrun simctl boot "$UDID" || true
    xcrun simctl spawn "$UDID" defaults write NSGlobalDomain AppleLanguages -array "$LANG"
    xcrun simctl spawn "$UDID" defaults write NSGlobalDomain AppleLocale -string "$APPLE_LOCALE"
    xcrun simctl terminate "$UDID" "com.example.app" || true
    asc screenshots capture --bundle-id "com.example.app" --name "home" --udid "$UDID" --output-dir "./screenshots/raw/$LOCALE" --output json
  '

8) Full multi-locale pipeline example

bash
#!/bin/bash
# full-pipeline-multi-locale.sh

declare -A LOCALE_UDID=(
  ["en-US"]="UDID_EN_US"
  ["de-DE"]="UDID_DE_DE"
  ["fr-FR"]="UDID_FR_FR"
  ["es-ES"]="UDID_ES_ES"
  ["ja-JP"]="UDID_JA_JP"
)

DEVICE="iphone-air"
RAW_DIR="./screenshots/raw"
FRAMED_DIR="./screenshots/framed"

# Step 1: Parallel capture with per-simulator locale defaults
for LOCALE in "${!LOCALE_UDID[@]}"; do
  (
    UDID="${LOCALE_UDID[$LOCALE]}"
    LANG="${LOCALE%%-*}"
    APPLE_LOCALE="${LOCALE/-/_}"

    xcrun simctl boot "$UDID" || true
    xcrun simctl spawn "$UDID" defaults write NSGlobalDomain AppleLanguages -array "$LANG"
    xcrun simctl spawn "$UDID" defaults write NSGlobalDomain AppleLocale -string "$APPLE_LOCALE"
    xcrun simctl terminate "$UDID" "com.example.app" || true

    asc screenshots capture \
      --bundle-id "com.example.app" \
      --name "home" \
      --udid "$UDID" \
      --output-dir "$RAW_DIR/$LOCALE" \
      --output json
    echo "Captured $LOCALE"
  ) &
done
wait

# Step 2: Parallel framing
for LOCALE in "${!LOCALE_UDID[@]}"; do
  (
    asc screenshots frame \
      --input "$RAW_DIR/$LOCALE/home.png" \
      --output-dir "$FRAMED_DIR/$LOCALE" \
      --device "$DEVICE" \
      --output json
    echo "Framed $LOCALE"
  ) &
done
wait

# Step 3: Generate review (single run, aggregates all locales)
asc screenshots review-generate \
  --framed-dir "$FRAMED_DIR" \
  --output-dir "./screenshots/review"

# Step 4: Upload (run per locale if needed)
for LOCALE in "${!LOCALE_UDID[@]}"; do
  asc screenshots upload \
    --version-localization "LOC_ID_FOR_$LOCALE" \
    --path "$FRAMED_DIR/$LOCALE" \
    --device-type "IPHONE_65" \
    --output json
done

Frequently asked questions

What does the Asc Shots Pipeline AI skill do?

Orchestrate iOS screenshot automation with xcodebuild/simctl for build-run, AXe for UI actions, JSON settings and plan files, Koubou-based framing (`asc screenshots frame`), and screenshot upload (`asc screenshots upload`). Use when users ask for automated screenshot capture, AXe-driven simulator flows, frame composition, or screenshot-to-upload pipelines.

Why use Asc Shots Pipeline on TypingMind?

Because you install it once and use it with any model. Asc Shots Pipeline is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Asc Shots Pipeline in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rorkai/app-store-connect-cli-skills/tree/main/skills/asc-shots-pipeline. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Asc Shots Pipeline?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Asc Shots Pipeline?

As many as you like. As long as a model supports skills, you can use Asc Shots Pipeline with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Asc Shots Pipeline AI skill free?

Yes. It is published on GitHub by rorkai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇