Agent skill

Logs Start

Start a VivaDicta log capture. An agent skill from n0an/VivaDicta.

MITAuto-check: notesMobile

Install Logs Start

skills CLI

$ npx skills add n0an/VivaDicta --skill logs-start -a claude-code

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

GitHub CLI

$ gh skill install n0an/VivaDicta logs-start --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/n0an/VivaDicta.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/logs-start .claude/skills/logs-start && 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/

Paste into Claude Code

Install the "logs-start" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-start into .claude/skills/logs-start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-start", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-start

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add n0an/VivaDicta --skill logs-start -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install n0an/VivaDicta logs-start --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/n0an/VivaDicta.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/logs-start .agents/skills/logs-start && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "logs-start" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-start into .agents/skills/logs-start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-start", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add n0an/VivaDicta --skill logs-start -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install n0an/VivaDicta logs-start --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/n0an/VivaDicta.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/logs-start .cursor/skills/logs-start && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "logs-start" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-start into .cursor/skills/logs-start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-start", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/n0an/VivaDicta.git --path .agents/skills/logs-start

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add n0an/VivaDicta --skill logs-start -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install n0an/VivaDicta logs-start --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/n0an/VivaDicta.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/logs-start .gemini/skills/logs-start && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "logs-start" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-start into .gemini/skills/logs-start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-start", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install n0an/VivaDicta logs-start

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add n0an/VivaDicta --skill logs-start -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/n0an/VivaDicta.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/logs-start .github/skills/logs-start && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "logs-start" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-start into .github/skills/logs-start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-start", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add n0an/VivaDicta --skill logs-start -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install n0an/VivaDicta logs-start --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/n0an/VivaDicta.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/logs-start .opencode/skills/logs-start && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "logs-start" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-start into .opencode/skills/logs-start/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-start", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: logs-start
GitHub stars: 131
Token cost: ~1.5k tokens
SKILL.md length: 667 words
Files: 2
Skills in repo: 20
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Start a VivaDicta log capture. An agent skill from n0an/VivaDicta.

Works in 3 steps: mkdir -p logs → Run ./scripts/launch_simulator.sh in a… → Report the logs/sim-YYYYMMDD-HHMMSS.log…
Mobile work in your project
SKILL.md covers Argument, Choosing a tier, sim and device, plus 4 more sections
Calls xcrun

What it does

Logs Start is an agent skill from n0an/VivaDicta. Start a VivaDicta log capture. Defaults to the simulator; takes sim, device, or structured to pick a tier.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Mobile. The repository describes itself as: iOS & watchOS speech-to-text app with AI voice keyboard, on-device RAG, and chat with your notes - powered by Apple Foundation Models, WhisperKit, NVIDIA Parakeet, and 20+ AI…. The licence is MIT.

When your agent uses it

Mobile work in your project

Example prompts

“/logs-start”

Workflow steps

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

mkdir -p logs
Run ./scripts/launch_simulator.sh in a background/long-lived shell so
Report the logs/sim-YYYYMMDD-HHMMSS.log path the script prints.

What it can do on your machine

Read from SKILL.md and the folder at commit b141304. 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:
- xcrun
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

Logs Start loads about 1.5k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 667 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~29
When it runs · the whole SKILL.md, loaded when a task matches: ~1.5k

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.

NoteRuns commands with sudoSKILL.md:115

Why this tier reaches extensions: `sudo log collect --device-udid` pulls the

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 n0an/VivaDicta at commit b141304, republished under its MIT licence (© n0an). 667 words, ~1,491 tokens.

Download SKILL.mdSave it as .claude/skills/logs-start/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.

name: logs-start
description: Start a VivaDicta log capture. Defaults to the simulator; takes sim, device, or structured to pick a tier.
disable-model-invocation: true

logs-start

Start a log capture. Stop it with logs-stop, which resolves the active tier on its own - you never have to name it again.

Argument

$ARGUMENTS selects the tier. Empty means sim.

Argument	Tier	Reaches extensions?	Cost
(empty) or `sim`	Simulator, live unified log	yes (all sim processes)	none
`device`	Device, live stdout	no, main app only	none
`structured`	Device, unified log archive	yes	interactive `sudo`, large archive

Anything else: say what was passed, list the three, and stop. Do not guess.

When invoked with no argument, start the simulator capture as usual, then close your report with this reminder so the other tiers stay discoverable:

Started the simulator capture (default). Other tiers: /logs-start device for live device stdout (main app only), /logs-start structured for the device unified log (the only tier that sees the keyboard and other extensions).

Do not ask which tier to use instead of starting - the default is the default. Only mention the alternatives after the capture is already running.

Choosing a tier

sim is the default because it is free and the richest: real unified-log metadata, timestamps, levels, categories, threads.
device is for hardware-only bugs. Live and cheap, but see the limitation below - it cannot see the keyboard or any other extension.
structured is the only tier that sees extensions on hardware. Reach for it when the keyboard, share, action, or widget target is involved, or for a post-mortem .logarchive you want to reopen in Console.app.

sim

mkdir -p logs
Run ./scripts/launch_simulator.sh in a background/long-lived shell so log stream keeps running. It also writes logs/.sim-capture.pid naming the streaming process, which is what logs-stop reads to end this capture and nothing else.
Report the logs/sim-YYYYMMDD-HHMMSS.log path the script prints.

Attaches to the already-booted Simulator; it does not relaunch the app, and it fails if none is booted. Captures Logger output filtered to subsystem == "com.antonnovoselov.VivaDicta"; raw print() is not included.

device

./scripts/launch_device.sh --check first - it resolves device and bundle id without launching. Fix whatever it reports before continuing.
mkdir -p logs
Run ./scripts/launch_device.sh in a background/long-lived shell. It writes logs/.device-capture.pid naming the devicectl process, which is what logs-stop reads.
Report the logs/device-YYYYMMDD-HHMMSS.log path.

Uses xcrun devicectl device process launch --console with ENABLE_PRINT_LOGS=1. --terminate-existing restarts the app, so in-progress state is lost.

Limitation: main app only, no extensions

--console pipes the stdout of the single process devicectl launched. Every extension runs in its own system-spawned process, so devicectl never sees it. Their output is absent entirely and nothing says so - you get a complete-looking stream that is silently missing a target.

Measured: a capture during keyboard use carried 213 lines from VivaDicta/ and 0 from VivaDictaKeyboard/, though the keyboard logs from KeyboardViewController, KeyboardTextProcessor and VivaModeManager. Use structured for extensions.

Show full SKILL.md (272 more words)Show less

Timestamps

Lines carry time, level and call site, because LoggerExtension's print mirror stamps them itself:

19:09:40.709 [INFO] VivaDicta/AIService.swift:666 Loaded 1 Viva Modes

That is app-side, so it only appears in builds you install. Bare, unstamped lines mean the installed binary predates the print mirror - rebuild to the device rather than changing the capture. Category and thread are still absent; stdout has no room for unified-log metadata.

structured

Starts nothing - it only records where to collect from. logs-stop does the work.

Find the device:

bash

xcrun xctrace list devices | grep iPhone | grep -v Simulator | head -1

mkdir -p llmtemp

bash

date '+%Y-%m-%d %H:%M:%S' > llmtemp/.device-log-start-time
echo "<UDID>" > llmtemp/.device-log-udid

Report the start time and UDID, and warn that logs-stop will need interactive sudo and will write a large archive.

Why this tier reaches extensions: sudo log collect --device-udid pulls the device's whole unified log, and extension lines survive the subsystem filter because LoggerExtension.swift hardcodes one subsystem across all targets:

swift

private nonisolated let kLoggingSubsystem = "com.antonnovoselov.VivaDicta"

That constant is load-bearing. If a target is ever changed to log under its own bundle id, it disappears from these captures silently.

Concurrent captures

sim and device can run at once; logs-stop handles all active tiers, reading one marker file per tier. Do not start a second capture of the same tier - the marker is overwritten, so the first stream is orphaned and its file stops receiving the lines you expect.

The markers are why logs-stop never has to guess. It ends the tier that was actually started, instead of matching simctl spawn.*log stream against the machine and catching an unrelated log stream someone else is running.

Manual analysis

bash

ls -lt logs/sim-*.log | head -5
grep -i "error\|fault" logs/sim-*.log
grep "\[AppState\]" logs/sim-*.log

log show logs/vivadicta_device_*.logarchive \
  --predicate 'subsystem == "com.antonnovoselov.VivaDicta"'

logs-stop
xcodebuild-testing
axe-simulator-control - drive the simulator before capturing

Files

SKILL.md and 1 other file in .agents/skills/logs-start of n0an/VivaDicta.

SKILL.md
agents/openai.yaml

Open the folder on GitHubat commit b141304

Compare with similar skills

Logs Start 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.

Logs Start compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Logs Start this skilln0an/VivaDicta	131	—	~1.5k	Automated safety check: Notes	MIT	3 days ago
React Native Best Practicesvercel-labs/openreview	1.7k	17 repos	~1.1k	Automated safety check: Pass	MIT	7 mo ago
Swiftui Protwostraws/SwiftUI-Agent-Skill	5.1k	2 repos	~1.5k	Automated safety check: Pass	MIT	yesterday
Kortix Brandkortix-ai/suna	20k	—	~4k	Automated safety check: Pass	Custom licence	today
Ip As LogoKartikLabhshetwar/better-shot	2.4k	1 repos	~4.3k	Automated safety check: Pass	MIT	7 days ago
Compose Multiplatform Patternsmonta-app/ocpp-emulator	180	5 repos	~2k	Automated safety check: Pass	Apache-2.0	7 days ago

Similar skills

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
Swiftui Pro
twostraws/SwiftUI-Agent-Skill
Comprehensively reviews SwiftUI code for best practices on modern APIs, maintainability, and performance.
5.1k GitHub starsUsed in 2 repos~1.5k tokens
MobileAuto-check passed
Kortix Brand
kortix-ai/suna
Load FIRST for anything that carries the Kortix look or voice: product or mobile UI, copy of any kind, decks, social, images, email, CLI output, anything with the logo, and reviews of these.
20k GitHub stars~4k tokensUpdated today
MobileAuto-check passed
Ip As Logo
KartikLabhshetwar/better-shot
Generate extremely simple, cute, personified square character images with rounded heavy forms, two purposeful character colors, one solid background color, and a dominant lower-corner composition.
2.4k GitHub starsUsed in 1 repo~4.3k tokens
MobileAuto-check passed
Compose Multiplatform Patterns
monta-app/ocpp-emulator
Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.
180 GitHub starsUsed in 5 repos~2k tokens
MobileAuto-check passed
Aso Appstore Screenshots
adamlyttleapps/claude-skill-aso-appstore-screenshots
Generate high-converting App Store screenshots by analyzing your app's codebase, discovering core benefits, and creating ASO-optimized screenshot images using Nano Banana Pro.
1.8k GitHub starsUsed in 1 repo~9.6k tokens
MobileAuto-check passed

Questions about Logs Start

What does Logs Start do?

Start a VivaDicta log capture. An agent skill from n0an/VivaDicta. Logs Start is an agent skill from n0an/VivaDicta. Start a VivaDicta log capture.

When should I use Logs Start?

Logs Start fits situations like: mobile work in your project.

How do I install Logs Start in Claude Code?

Run `npx skills add n0an/VivaDicta --skill logs-start -a claude-code`. Or copy the skill folder (.agents/skills/logs-start in n0an/VivaDicta) into .claude/skills/logs-start in your project. Claude Code loads it when a task matches its description.

How do I install Logs Start in Codex?

Run `npx skills add n0an/VivaDicta --skill logs-start -a codex`. Or copy the skill folder (.agents/skills/logs-start in n0an/VivaDicta) into .agents/skills/logs-start in your project. Codex loads it when a task matches its description.

Can I use Logs Start 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 n0an/VivaDicta --skill logs-start -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/logs-start, .gemini/skills/logs-start, .github/skills/logs-start and .opencode/skills/logs-start in your project.

What does Logs Start need to run?

Going by SKILL.md and its folder, Logs Start needs the command-line tools its instructions call (xcrun).

Does Logs Start 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 Logs Start safe to install?

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

What licence does Logs Start use?

Logs Start 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 Logs Start use?

About 1.5k tokens (SKILL.md is roughly 6k 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 Logs Start?

Skills that share tags, products or a category with Logs Start: React Native Best Practices (vercel-labs/openreview, 1.7k stars), Swiftui Pro (twostraws/SwiftUI-Agent-Skill, 5.1k stars), Kortix Brand (kortix-ai/suna, 20k stars) and Ip As Logo (KartikLabhshetwar/better-shot, 2.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Logs Start?

n0an (a GitHub user) maintains it in n0an/VivaDicta, which has 131 GitHub stars. The repository holds 20 skills in this directory. The repository was last updated on October 5, 2026.

Source: n0an/VivaDicta on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Logs Start

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

logs-start

Argument

Choosing a tier

sim

device

Limitation: main app only, no extensions

Timestamps

structured

Concurrent captures

Manual analysis

Related

Files

Compare with similar skills

Similar skills

More from n0an/VivaDicta

Related

Questions about Logs Start