Agent skill

Logs Stop

Stop whichever VivaDicta log capture is active, then summarize it.

MITAuto-check: notesMobile

Install Logs Stop

skills CLI

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

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

GitHub CLI

$ gh skill install n0an/VivaDicta logs-stop --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-stop .claude/skills/logs-stop && 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-stop" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-stop into .claude/skills/logs-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-stop", 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-stop

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-stop -a codex

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

GitHub CLI

$ gh skill install n0an/VivaDicta logs-stop --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-stop .agents/skills/logs-stop && 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-stop" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-stop into .agents/skills/logs-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-stop", 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-stop -a cursor

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

GitHub CLI

$ gh skill install n0an/VivaDicta logs-stop --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-stop .cursor/skills/logs-stop && 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-stop" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-stop into .cursor/skills/logs-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-stop", 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-stop

--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-stop -a gemini-cli

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

GitHub CLI

$ gh skill install n0an/VivaDicta logs-stop --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-stop .gemini/skills/logs-stop && 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-stop" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-stop into .gemini/skills/logs-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-stop", 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-stop

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-stop -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-stop .github/skills/logs-stop && 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-stop" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-stop into .github/skills/logs-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-stop", 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-stop -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-stop --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-stop .opencode/skills/logs-stop && 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-stop" agent skill from https://github.com/n0an/VivaDicta/tree/main/.agents/skills/logs-stop into .opencode/skills/logs-stop/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "logs-stop", 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-stop
GitHub stars: 131
Token cost: ~1.6k tokens
SKILL.md length: 764 words
Files: 2
Skills in repo: 20
Repo updated: Oct 5, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Stop whichever VivaDicta log capture is active, then summarize it.

Works in 3 steps: detect → stop and summarize each active tier → report
Mobile work in your project
SKILL.md covers Step 1: detect, Step 2: stop and summarize…, Step 3: report and Read levels skeptically, plus 2 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Logs Stop is an agent skill from n0an/VivaDicta. Stop whichever VivaDicta log capture is active, then summarize it. Detects the tier itself; takes an optional filter.

Its SKILL.md is about 1.6k 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-stop”

Workflow steps

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

detect
stop and summarize each active tier
report

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
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
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 Stop loads about 1.6k tokens when it runs. Until then it costs about 32 tokens; SKILL.md has 764 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~32
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

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:126

sudo is needed - that reads as "go and do this in a terminal somewhere", and 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). 764 words, ~1,604 tokens.

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

name: logs-stop
description: Stop whichever VivaDicta log capture is active, then summarize it. Detects the tier itself; takes an optional filter.
disable-model-invocation: true

logs-stop

Stop the active capture(s) started by logs-start and summarize the result. Never ask the user which tier is running - detect it.

Step 1: detect

logs-start writes a marker per live tier naming the process that streams: logs/.sim-capture.pid and logs/.device-capture.pid. Read those - do not go looking for processes.

bash

for tier in sim device; do
  PIDFILE="logs/.${tier}-capture.pid"
  [ -f "$PIDFILE" ] || continue
  PID=$(cat "$PIDFILE" 2>/dev/null)
  if [ -n "$PID" ] && kill -0 "$PID" 2>/dev/null; then
    echo "$tier ACTIVE (pid $PID)"
  else
    echo "$tier marker stale (pid ${PID:-none} gone), removing"
    rm -f "$PIDFILE"
  fi
done
[ -f llmtemp/.device-log-start-time ] && echo "structured PENDING: $(cat llmtemp/.device-log-start-time)"

structured has no process - a marker file is the only evidence. If nothing is found, say so plainly and stop; do not summarize a stale file as if it were fresh.

Never detect or stop a capture by process pattern

The obvious-looking check is wrong and it is destructive:

bash

pgrep -f "simctl spawn.*log stream"     # matches ANY simulator log stream on the machine

That pattern is not specific to this repo, this app, or this capture. It matches an unrelated log stream any other session has running, reports sim ACTIVE when no VivaDicta capture exists, and the matching pkill then kills that session's stream. A capture the user never started must never be stopped, so the marker is the only handle.

Two related traps, if you ever debug this by hand:

pgrep -a is not a macOS flag. pgrep here accepts only [-Lfilnoqvx], yet -a exits 0 and prints a bogus pid rather than erroring. Use plain -f.
grep for a pattern matches your own pipeline. ps -A | grep "log stream" counts the greps themselves, because both carry the string in their own argv. Add | grep -v grep, or check the marker instead.

Step 2: stop and summarize each active tier

Kill the streaming process the marker names. Do not kill the wrapper script: launch_*.sh is the parent of the stream, and killing the parent reparents the stream to PID 1, where it keeps appending to the log file with nothing left to stop it. Killing the stream is enough - the script's tee then reaches EOF and the script exits, clearing its own marker.

sim

bash

PID=$(cat logs/.sim-capture.pid)
ps -p "$PID" -o command= | grep -q "log stream" || echo "refusing: pid $PID is not a log stream"
kill "$PID"
LOGFILE=$(ls -t logs/sim-*.log 2>/dev/null | head -1)

device

bash

PID=$(cat logs/.device-capture.pid)
ps -p "$PID" -o command= | grep -q "devicectl device process launch" || echo "refusing: pid $PID is not a device capture"
kill "$PID"
LOGFILE=$(ls -t logs/device-*.log 2>/dev/null | head -1)

The ps check is there because a pid can be reused. If the command line does not match, say so and stop rather than killing an unrelated process.

The capture ends with App terminated due to signal 15 - that is this skill's kill, not a crash. Say so rather than reporting it as a failure.

Show full SKILL.md (409 more words)Show less

structured

Check staleness first. If llmtemp/.device-log-start-time is more than a few hours old, show its timestamp and ask before collecting - the marker may be left over from an abandoned session, and collecting is expensive.

The script needs interactive sudo, so the user must run it themselves. Root is a hard requirement inside /usr/bin/log, not a choice this script makes - verified 2026-09-05, running it unprivileged fails outright and writes nothing:

$ /usr/bin/log collect --device-udid <udid> --start <time> --output out.logarchive
log: Must be root to collect logs from attached device

There is no flag or output-path that avoids it, so do not try to drop the sudo. (Local-only log collect, with no --device-udid, is the case that can run unprivileged - the device path talks to attached hardware.)

Note also that log is a shell builtin in Anton's zsh, so a bare log show ... typed interactively fails with too many arguments. Use /usr/bin/log. The script is unaffected: it runs under #!/bin/bash.

Hand them a line they can paste, not a description of one. In Claude Code, a prompt starting with ! runs in the session and its output lands back in the conversation, so the whole handoff is one copy-paste. Print exactly this, on its own line, as the last thing before you stop:

! ./scripts/collect_device_logs.sh

Do not write it as a bare ./scripts/collect_device_logs.sh and explain that sudo is needed - that reads as "go and do this in a terminal somewhere", and the result then has to be pasted back by hand. The ! prefix is the part that makes it work in place, and it is not obvious unless it is shown.

Then wait for confirmation and read the newest export:

bash

LOGFILE=$(ls -t logs/device_*.txt 2>/dev/null | head -1)

It also writes logs/vivadicta_device_*.logarchive, reopenable in Console.app. Do not claim the logs exist before the user confirms the script finished. Remove the marker files once collection succeeds so the next logs-stop does not re-trigger it.

Step 3: report

Per file: path, size, modified time, line count, and level counts.

bash

wc -l "$LOGFILE"
grep -oE '\[(INFO|DEBUG|ERROR|WARNING|NOTICE)\]' "$LOGFILE" | sort | uniq -c | sort -rn

Then apply $ARGUMENTS:

`$ARGUMENTS`	Show
(empty)	Last 20 lines, plus any error/fault lines
`errors`	Error and fault lines
`warnings`	Warning lines
`all`	The whole file
anything else	Treat as a search term; show matching lines

Read levels skeptically

Several call sites log success messages at [ERROR] - for example AudioPrewarmManager.swift:490 ("Input tap installed") and the AppGroupCoordinator state-update lines, where all 30 "errors" in one capture were routine status changes. Report what a line says, not what its level claims. A raw error count is misleading on its own.

Notes

Logs are never deleted here; this only stops streams and summarizes.
logs/ is gitignored.

logs-start

Files

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

SKILL.md
agents/openai.yaml

Open the folder on GitHubat commit b141304

Compare with similar skills

Logs Stop 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 Stop compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Logs Stop this skilln0an/VivaDicta	131	—	~1.6k	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 Stop

What does Logs Stop do?

Stop whichever VivaDicta log capture is active, then summarize it. Logs Stop is an agent skill from n0an/VivaDicta. Stop whichever VivaDicta log capture is active, then summarize it.

When should I use Logs Stop?

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

How do I install Logs Stop in Claude Code?

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

How do I install Logs Stop in Codex?

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

Can I use Logs Stop 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-stop -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-stop, .gemini/skills/logs-stop, .github/skills/logs-stop and .opencode/skills/logs-stop in your project.

What does Logs Stop need to run?

SKILL.md names no scripts, command-line tools or credentials: Logs Stop is instructions for the agent only.

Does Logs Stop 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 Stop 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 Stop use?

Logs Stop 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 Stop use?

About 1.6k tokens (SKILL.md is roughly 6.4k 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 Stop?

Skills that share tags, products or a category with Logs Stop: 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 Stop?

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 Stop

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-stop

Step 1: detect

Never detect or stop a capture by process pattern

Step 2: stop and summarize each active tier

sim

device

structured

Step 3: report

Read levels skeptically

Notes

Related

Files

Compare with similar skills

Similar skills

More from n0an/VivaDicta

Related

Questions about Logs Stop