Asc Workflow logo

Asc Workflow

OrganizationPopular
rorkai
asc-workflow

Define, validate, run, resume, and audit repo-local multi-step automations with current `asc workflow` and `.asc/workflow.json`, including step outputs and safe release/TestFlight workflows.

Overview

Publisherrorkai
Repositoryapp-store-connect-cli-skills
Skill nameasc-workflow
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 Workflow 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-workflow
  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-workflow .claude/skills/asc-workflow
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Asc Workflow 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 Workflow 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 Workflow 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 workflow

Use this skill when you need lane-style automation inside the CLI using:

  • asc workflow validate
  • asc workflow list
  • asc workflow run

Workflows are repo-local automation files. They run trusted shell commands, stream step output to stderr, and keep stdout as machine-readable JSON.

Command discovery

Always verify flags with:

bash
asc workflow --help
asc workflow validate --help
asc workflow list --help
asc workflow run --help

End-to-end flow

  1. Author .asc/workflow.json.
  2. Validate structure and references:
bash
asc workflow validate
  1. Discover public workflows:
bash
asc workflow list
asc workflow list --all
  1. Preview execution:
bash
asc workflow run --dry-run beta BUILD_ID:123456789 GROUP_ID:abcdef
  1. Execute:
bash
asc workflow run beta BUILD_ID:123456789 GROUP_ID:abcdef
  1. If a recoverable run fails, resume with the run ID from the JSON result:
bash
asc workflow run release --resume "release-20260312T120000Z-deadbeef"

Do not pass extra KEY:VALUE params with --resume; the saved workflow file, params, and persisted outputs are reused.

File location and format

  • Default path: .asc/workflow.json
  • Override path: asc workflow run --file ./path/to/workflow.json <name>
  • JSONC comments are supported.
  • Top-level hooks: before_all, after_all, error
  • Workflow keys: description, private, env, steps
  • Step forms:
    • string shorthand: "echo hello"
    • run shell command
    • workflow sub-workflow call
    • name label
    • if conditional var name
    • with env overrides for workflow-call steps
    • outputs map for JSON stdout extraction from named run steps
    • retry fixed-delay retry policy for a run step
    • timeout positive per-attempt duration for a run step

Outputs

Run steps can declare outputs. The command must emit JSON on stdout, so pass --output json for asc commands that produce outputs.

Output references use:

text
${steps.step_name.OUTPUT_NAME}

Rules:

  • A step that declares outputs must have a reference-safe name.
  • Outputs are allowed on run steps, not workflow-call steps.
  • Output-producing names must be unique across workflows that can execute together in the same run graph.
  • Persisted outputs are stored in workflow run state, so do not map secrets into outputs.

Bounded retry and timeout

Add retry only to commands you have determined are safe to repeat. The runner does not classify commands or retry mutations on its own.

json
{
  "name": "resolve_build",
  "run": "asc builds info --app $APP_ID --latest --platform IOS --output json",
  "retry": {
    "max_attempts": 3,
    "delay": "5s"
  },
  "timeout": "2m"
}

retry.max_attempts counts the first attempt and must be between 2 and 100. Retry delays and timeouts must be positive durations no longer than 24 hours. Both fields work only on run steps, not workflow calls or lifecycle hooks.

A timeout without retry is terminal because the command may have completed remotely. Pairing retry and timeout is the explicit signal that another attempt is safe. Resume requires either a successful checkpoint or a retry-enabled failed step; output-extraction failures cannot be resumed.

Runtime params

asc workflow run <name> [KEY:VALUE ...] supports both separators:

bash
asc workflow run beta VERSION:2.1.0
asc workflow run beta VERSION=2.1.0

Repeated keys are last-write-wins. In shell commands, reference params through shell expansion like $VERSION.

Env precedence

Main workflow run:

text
definition.env < workflow.env < CLI params

Sub-workflow call with with:

text
sub-workflow env < caller env and params < step with

Conditionals

Add "if": "VAR_NAME" to a step. Truthy values are 1, true, yes, y, and on, case-insensitive. Lookup checks merged workflow env/params first, then process environment.

Example workflow

json
{
  "env": {
    "APP_ID": "123456789",
    "VERSION": "1.0.0",
    "GROUP_ID": ""
  },
  "before_all": "asc auth status",
  "after_all": "echo workflow_done",
  "error": "echo workflow_failed",
  "workflows": {
    "beta": {
      "description": "Resolve the latest build and distribute it to TestFlight",
      "steps": [
        {
          "name": "resolve_build",
          "run": "asc builds info --app $APP_ID --latest --platform IOS --output json",
          "outputs": {
            "BUILD_ID": "$.data.id"
          }
        },
        {
          "name": "list_groups",
          "run": "asc testflight groups list --app $APP_ID --limit 20 --output json"
        },
        {
          "name": "add_build_to_group",
          "if": "GROUP_ID",
          "run": "asc builds add-groups --build-id ${steps.resolve_build.BUILD_ID} --group $GROUP_ID"
        }
      ]
    },
    "release": {
      "description": "Validate, stage, and submit an App Store version",
      "steps": [
        {
          "name": "validate",
          "run": "asc validate --app $APP_ID --version $VERSION --platform IOS --output json"
        },
        {
          "name": "stage",
          "run": "asc release stage --app $APP_ID --version $VERSION --build-id $BUILD_ID --metadata-dir ./metadata/version/$VERSION --confirm --output json"
        },
        {
          "name": "submit",
          "if": "SUBMIT_FOR_REVIEW",
          "run": "asc review submit --app $APP_ID --version $VERSION --build-id $BUILD_ID --confirm --output json"
        }
      ]
    },
    "publish-appstore": {
      "description": "High-level upload plus App Store review submission",
      "steps": [
        {
          "name": "publish",
          "run": "asc publish appstore --app $APP_ID --ipa ./build/MyApp.ipa --version $VERSION --wait --submit --confirm --output json"
        }
      ]
    }
  }
}

Useful invocations

bash
asc workflow validate | jq -e '.valid == true'
asc workflow list --pretty
asc workflow list --all --pretty
asc workflow run --dry-run beta BUILD_ID:123 GROUP_ID:grp_abc
asc workflow run beta BUILD_ID:123 GROUP_ID:grp_abc | jq -e '.status == "ok"'
asc workflow run release BUILD_ID:123 SUBMIT_FOR_REVIEW:true
asc workflow run release --resume "release-20260312T120000Z-deadbeef"

Safety rules

  • Treat .asc/workflow.json like code; only run trusted workflow files.
  • Avoid running workflows from untrusted PRs with secrets.
  • Keep workflow files in version control.
  • Validate first, dry-run next, then run.
  • Use explicit IDs and --confirm for mutating steps.
  • Use asc validate, asc release stage, asc review submit, and asc publish appstore; do not use removed submission commands.

Frequently asked questions

What does the Asc Workflow AI skill do?

Define, validate, run, resume, and audit repo-local multi-step automations with current `asc workflow` and `.asc/workflow.json`, including step outputs and safe release/TestFlight workflows.

Why use Asc Workflow on TypingMind?

Because you install it once and use it with any model. Asc Workflow 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 Workflow 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-workflow. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Asc Workflow?

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 Workflow?

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

Is the Asc Workflow 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 👇