Agent skill

Apple Flow Ops

by dkyazzentwatwa in dkyazzentwatwa/apple-flow

A skill your agent uses when working on Apple Flow in the apple-flow repository.

MITAuto-check: notesDevelopment

Install Apple Flow Ops

skills CLI
$ npx skills add dkyazzentwatwa/apple-flow --skill apple-flow-ops -a claude-code

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

GitHub CLI
$ gh skill install dkyazzentwatwa/apple-flow apple-flow-ops --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/dkyazzentwatwa/apple-flow.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/codex-flow-ops .claude/skills/apple-flow-ops && 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
apple-flow-ops
GitHub stars
105
Token cost
~1k tokens
SKILL.md length
445 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when working on Apple Flow in the apple-flow repository.

  • Works in 5 steps: Reproduce First → Identify Root Cause → Keep Config Hygiene → …
  • Working on Apple Flow in the apple-flow repository
  • SKILL.md covers Overview, When to Use, Non-Negotiable Safety Defaults and Primary Workflow, plus 2 more sections
  • Calls pytest and codex

What it does

Apple Flow Ops is an agent skill from dkyazzentwatwa/apple-flow. Use when working on Apple Flow in the apple-flow repository. Enforces safe defaults, beginner-first startup, focused debugging, config hygiene, and required verification.

Its SKILL.md is about 1k 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 Development. The repository describes itself as: Your Apple-Native AI Agent. The licence is MIT.

When your agent uses it

  • Working on Apple Flow in the apple-flow repository

Example prompts

  • “/apple-flow-ops”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Reproduce First
  2. Identify Root Cause
  3. Keep Config Hygiene
  4. Preserve Logging Quality
  5. Verify Before Completion

What it can do on your machine

Read from SKILL.md and the folder at commit 4b9cf4f. 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:

    • pytest
    • codex

    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

Apple Flow Ops loads about 1k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 445 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:92
    2. Fix reported safety stop in `.env` (senders, DB path, placeholders)

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 dkyazzentwatwa/apple-flow at commit 4b9cf4f, republished under its MIT licence (© dkyazzentwatwa). 445 words, ~1,029 tokens.

Download SKILL.mdSave it as .claude/skills/apple-flow-ops/SKILL.md (or your agent's skills folder).
name
apple-flow-ops
description
Use when working on Apple Flow in the apple-flow repository. Enforces safe defaults, beginner-first startup, focused debugging, config hygiene, and required verification.

Codex Flow Ops

Overview

Use this skill for changes, debugging, and operations in the apple-flow repository.

Apple Flow is a local-first macOS daemon bridging iMessage, Mail, Reminders, Notes, and Calendar to Claude/Codex CLI. This skill keeps workflow safe-by-default and beginner-friendly while giving concrete operator steps.

When to Use

Use this skill when the task involves any of:

  • Starting or troubleshooting the relay daemon
  • Editing relay behavior in src/apple_flow/*
  • Updating runtime config fields or .env.example
  • Improving ingress/egress/orchestration/logging behavior
  • Verifying safety gates around sender allowlist, chat prefix, or approvals

Non-Negotiable Safety Defaults

Keep these defaults unless the user explicitly asks otherwise:

  • apple_flow_only_poll_allowed_senders=true
  • apple_flow_require_chat_prefix=true
  • apple_flow_chat_prefix=relay:
  • apple_flow_process_historical_on_first_start=false
  • apple_flow_notify_blocked_senders=false
  • apple_flow_notify_rate_limited_senders=false
  • Keep mutating workflows behind approval (task: and project:)

Do not remove duplicate/echo suppression without explicit request:

  • apple_flow_suppress_duplicate_outbound_seconds
  • IMessageEgress.was_recent_outbound(...)

Primary Workflow

1) Reproduce First

Use beginner path before changing code:

bash
cd <path-to-apple-flow>
./scripts/start_beginner.sh

If startup appears idle, verify:

  • Full Disk Access for terminal host app
  • apple_flow_messages_db_path points to a real chat.db
  • codex login is completed
2) Identify Root Cause

Inspect the right layer first:

  • Runtime settings: src/apple_flow/config.py
  • Polling/loop/logs: src/apple_flow/daemon.py
  • Messages DB reads: src/apple_flow/ingress.py
  • iMessage send and suppression: src/apple_flow/egress.py
  • command routing and approvals: src/apple_flow/orchestrator.py

Prefer minimal, focused patches once the cause is clear.

3) Keep Config Hygiene

For every new config field:

  1. Add sensible default in src/apple_flow/config.py
  2. Document in README.md
  3. Add sample in .env.example

If runtime behavior changes, update beginner-facing guidance:

  • BEGINNER_SETUP_10_MIN.md
4) Preserve Logging Quality

Terminal logs should stay concise and actionable:

  • Inbound row processed or ignored
  • Explicit ignore reason (echo, missing prefix, empty, blocked, rate-limited)
  • Handled command kind + duration

Avoid noisy repeated logs; keep throttled warnings for recurring failures.

Show full SKILL.md (181 more words)Show less
5) Verify Before Completion

Run from repo root:

bash
source .venv/bin/activate
pytest -q

Expected result:

  • All tests passing

If tests fail, report failing tests and root cause before claiming completion.

Common Task Playbooks

A) Startup Failures
  1. Run ./scripts/start_beginner.sh
  2. Fix reported safety stop in .env (senders, DB path, placeholders)
  3. Confirm Messages DB readability and Full Disk Access
  4. Re-run script and confirm daemon foreground readiness
B) No Replies in iMessage
  1. Confirm sender matches apple_flow_allowed_senders
  2. Confirm message uses relay: prefix (or explicit command prefix)
  3. Confirm sender allowlist polling is on and non-empty
  4. Check logs for ignore reason (ignored_missing_chat_prefix, echo suppression, rate limit)
C) Approval Flow Confusion (task: / project:)
  1. Confirm plan is produced first
  2. Confirm approval request id issued
  3. Confirm only original sender can approve/deny
  4. Confirm expiration handling and status transitions are preserved

Acceptance Checklist

Before finishing a apple-flow task, confirm:

  • Safety defaults preserved (unless explicitly changed by request)
  • Patch is minimal and scoped to root cause
  • Config/docs/examples are in sync if config changed
  • pytest -q passes
  • Final summary includes what changed, why, and how it was verified

© dkyazzentwatwa, 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 skills/codex-flow-ops of dkyazzentwatwa/apple-flow.

Open the folder on GitHubat commit 4b9cf4f

Compare with similar skills

Apple Flow Ops 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.

Apple Flow Ops compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Apple Flow Ops this skilldkyazzentwatwa/apple-flow105—~1kAutomated safety check: NotesMIT
Vercel Composition Patternssupabase/supabase111k58 repos~726Automated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Typescript Advanced Typesrolling-scopes/rsschool-app10k25 repos~4.2kAutomated safety check: PassMPL-2.0
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Code Review ChecklistshareAI-lab/learn-claude-code78k4 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Official

    React composition patterns that scale. An agent skill from supabase/supabase.

    111k GitHub starsUsed in 58 repos~726 tokens
    DevelopmentAuto-check passed
  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Typescript Advanced Types

    rolling-scopes/rsschool-app

    Master TypeScript's advanced type system including generics, conditional types, mapped types, template literals, and utility types for building type-safe applications.

    10k GitHub starsUsed in 25 repos~4.2k tokens
    DevelopmentAuto-check passed
  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Code Review Checklist

    shareAI-lab/learn-claude-code

    Reviews code against a five-part checklist covering security, correctness, performance, maintainability and testing, and reports findings in a fixed format.

    78k GitHub starsUsed in 4 repos~1.1k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed

More from dkyazzentwatwa/apple-flow

  • Apple Flow Mail

    dkyazzentwatwa/apple-flow

    Deep workflow skill for Apple Flow Mail operations. An agent skill from dkyazzentwatwa/apple-flow.

    105 GitHub stars~718 tokensUpdated 6 mo ago
    Auto-check passed
  • Apple Flow Numbers

    dkyazzentwatwa/apple-flow

    General Apple Numbers automation for Apple Flow. An agent skill from dkyazzentwatwa/apple-flow.

    105 GitHub stars~1.5k tokensUpdated 6 mo ago
    Auto-check passed
  • Apple Flow Pages

    dkyazzentwatwa/apple-flow

    Universal Markdown-to-Apple-Pages formatting skill for Apple Flow.

    105 GitHub stars~1k tokensUpdated 6 mo ago
    Auto-check passed
  • Apple Flow Gateways

    dkyazzentwatwa/apple-flow

    Core routing and troubleshooting skill for Apple Flow gateways (Mail, Reminders, Notes, Calendar).

    105 GitHub stars~766 tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Apple Flow Ops

What does Apple Flow Ops do?

A skill your agent uses when working on Apple Flow in the apple-flow repository. Apple Flow Ops is an agent skill from dkyazzentwatwa/apple-flow. Use when working on Apple Flow in the apple-flow repository.

When should I use Apple Flow Ops?

Apple Flow Ops fits situations like: working on Apple Flow in the apple-flow repository.

How do I install Apple Flow Ops in Claude Code?

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

How do I install Apple Flow Ops in Codex?

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

Can I use Apple Flow Ops 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 dkyazzentwatwa/apple-flow --skill apple-flow-ops -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/apple-flow-ops, .gemini/skills/apple-flow-ops, .github/skills/apple-flow-ops and .opencode/skills/apple-flow-ops in your project.

What does Apple Flow Ops need to run?

Going by SKILL.md and its folder, Apple Flow Ops needs the command-line tools its instructions call (pytest and codex).

Does Apple Flow Ops 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 Apple Flow Ops safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Apple Flow Ops use?

Apple Flow Ops 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 Apple Flow Ops use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Apple Flow Ops?

Skills that share tags, products or a category with Apple Flow Ops: Vercel Composition Patterns (supabase/supabase, 111k stars), Finishing a Development Branch (obra/superpowers, 297k stars), Typescript Advanced Types (rolling-scopes/rsschool-app, 10k stars) and PR Babysitter (openinterpreter/openinterpreter, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Apple Flow Ops?

dkyazzentwatwa (a GitHub user) maintains it in dkyazzentwatwa/apple-flow, which has 105 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on March 30, 2026.

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