New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Sentry Monitor

by different-ai-studio in different-ai-studio/teamclu

A skill your agent uses when the user wants to check Sentry issues, run a Sentry daily report, or monitor error trends.

MITAuto-check passedMobile

Install Sentry Monitor

skills CLI
$ npx skills add different-ai-studio/teamclu --skill sentry-monitor -a claude-code

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

GitHub CLI
$ gh skill install different-ai-studio/teamclu sentry-monitor --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/different-ai-studio/teamclu.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/sentry-monitor .claude/skills/sentry-monitor && 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
sentry-monitor
GitHub stars
167
Token cost
~1.7k tokens
SKILL.md length
773 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the user wants to check Sentry issues, run a Sentry daily report, or monitor error trends.

  • Works in 5 steps: Quota gate — do this FIRST → Scan Issues → Analyze Root Causes (Local) → …
  • The user wants to check Sentry issues
  • SKILL.md covers Projects, Execution Steps, Usage and Constraints
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Sentry Monitor is an agent skill from different-ai-studio/teamclu. Use when the user wants to check Sentry issues, run a Sentry daily report, or monitor error trends. Triggers on "sentry 监控", "sentry 日报", "查看 sentry", "sentry report", "sentry monitor".

Its SKILL.md is about 1.7k 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 Mobile. It works with Sentry, Rust and iOS. The repository describes itself as: TeamClu, AI Agent Desktop Workspace. The licence is MIT.

When your agent uses it

  • The user wants to check Sentry issues
  • Run a Sentry daily report
  • Monitor error trends

Example prompts

  • “sentry 监控”
  • “sentry 日报”
  • “查看 sentry”
  • “/sentry-monitor”

Workflow steps

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

  1. Quota gate — do this FIRST
  2. Scan Issues
  3. Analyze Root Causes (Local)
  4. Format Report
  5. Report Out

What it can do on your machine

Read from SKILL.md and the folder at commit 8f754b3. 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

Sentry Monitor loads about 1.7k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 773 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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 passed

The automated check found no risky patterns in SKILL.md.

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 different-ai-studio/teamclu at commit 8f754b3, republished under its MIT licence (© different-ai-studio). 773 words, ~1,668 tokens.

Download SKILL.mdSave it as .claude/skills/sentry-monitor/SKILL.md (or your agent's skills folder).
name
sentry-monitor
description
Use when the user wants to check Sentry issues, run a Sentry daily report, or monitor error trends. Triggers on "sentry 监控", "sentry 日报", "查看 sentry", "sentry report", "sentry monitor".

Sentry Monitor — Daily Issue Report

Scan the TeamClu Sentry projects for unresolved fatal/high issues, analyze root causes, and report.

Projects

ProjectSentry SlugPlatform
Web / desktop frontenducar-inc/teamclu-reactJavaScript React
Desktop Rust processucar-inc/teamclu-rustRust
iOSucar-inc/teamclu-iosapple-ios
Expoucar-inc/teamclu-exporeact-native

ucar-inc/teamclu (the old Rust slug) does not exist — it was deleted, and sentry issue list 404s on it. teamclu-rust replaced it on 2026-09-04, so that project has no history before then; an empty result there is expected for a while rather than a signal. Re-verify with sentry project list ucar-inc/ --json if a scan errors on an unknown project.

Execution Steps

0. Quota gate — do this FIRST

The org is on Sentry's free tier: 5,000 errors/month, onDemandMaxSpend = 0, billing period resetting on the 19th. When the quota runs out Sentry drops every incoming event silently — from the issue list that looks identical to "no new errors." This has already happened twice (2026-08-17 and 2026-09-02), and the second time the projects sat blind for over two weeks.

Never report "全部正常" without clearing this check.

bash
sentry api "/organizations/ucar-inc/stats_v2/?field=sum(quantity)&groupBy=outcome&category=error&statsPeriod=7d&interval=1d"

Read the accepted and rate_limited series:

  • accepted non-zero for the most recent day → ingestion is healthy, continue.
  • accepted at 0 with rate_limited climbing → quota exhausted. Stop the normal report. Lead with this instead, get the exact numbers from sentry api "/customers/ucar-inc/" (categories.errors: usage / reserved / usageExceeded, plus billingPeriodEnd), and say plainly that the issue list below is stale as of the last accepted event.
1. Scan Issues

Run these in parallel, one per project:

bash
sentry issue list ucar-inc/teamclu-react --query "is:unresolved" --period 48h --json --fields shortId,title,priority,level,status --limit 30
sentry issue list ucar-inc/teamclu-rust  --query "is:unresolved" --period 48h --json --fields shortId,title,priority,level,status --limit 30
sentry issue list ucar-inc/teamclu-ios   --query "is:unresolved" --period 48h --json --fields shortId,title,priority,level,status --limit 30
sentry issue list ucar-inc/teamclu-expo  --query "is:unresolved" --period 48h --json --fields shortId,title,priority,level,status --limit 30

Use --period for the time window (24h / 48h / 14d), not a lastSeen: clause. Default is 90 days, which is far wider than a daily report wants.

Filter results: keep only issues where level is fatal OR priority is high.

--fields gotcha (CLI 0.26.1): count, userCount, firstSeen and lastSeen are listed in --help but are silently dropped from issue list output — you get the key omitted, not an error. Volume and recency have to come from sentry issue view <shortId> --json, which does return them. Do not report event counts sourced from issue list.

If no issues match and step 0 was clean, skip to step 4 with the "全部正常" message. If step 0 was not clean, say so instead — an empty list under an exhausted quota means nothing.

Show full SKILL.md (398 more words)Show less
2. Analyze Root Causes (Local)

For each filtered issue (max 10 total), perform local root cause analysis:

  1. Fetch issue details with stack trace, which also carries the volume numbers:
bash
sentry issue view <shortId> --json

  1. From the stack trace / error message, identify the relevant source files and functions in the codebase.

  2. Read those source files to understand the code context around the error site.

  3. Produce a one-sentence root cause summary based on the stack trace + source.

Two things worth checking before writing the summary:

  • Group splits. The same defect often appears as several issues — a sourcemapped build and a minified one group separately. Compare metadata.value across the filtered set and treat identical values as one root cause rather than reporting the same bug three times.
  • Prefer a sourcemapped frame. When several groups share a value, analyze the one whose culprit is a repo path (/src/...) rather than a bundle (assets/index-*.js) — it names the file directly.

When there are more than ~4 issues to analyze, run them as parallel subagents via the Agent tool; each runs sentry issue view, reads the relevant sources, and returns one sentence. For fewer than that, just do it inline — spawning agents costs more than it saves.

If analysis cannot determine a root cause, use the error title as-is and say the root cause is undetermined. Do not guess.

3. Format Report
Sentry 日报 <YYYY-MM-DD>

【Web / 桌面】N 个高优 issue
• <shortId> [<level>] <title> — 根因：<root cause summary>
• ...

【桌面 Rust】N 个高优 issue
• ...

【iOS】N 个高优 issue
• ...

【Expo】N 个高优 issue
• ...

修复命令：/sentry-fix <top-issue-id>

Omit any project section with zero matching issues. When step 0 found the quota exhausted, put that first, above every section:

⚠️ Sentry 配额已耗尽（<usage>/<reserved>），<date> 起事件全部被丢弃，<billingPeriodEnd> 重置。
以下列表停留在最后一条被接收的事件，不代表当前状态。
4. Report Out

Present the report in the conversation.

Pushing to WeCom is a separate step that needs the user's go-ahead, unless this run is the scheduled daily report (/loop 24h /sentry-monitor), where pushing is the whole point. When the user asked for an analysis rather than a daily report, show the report and offer to push — do not push unasked, since it posts to a group chat.

bash
wecom-cli msg send_message '{"chat_type": 2, "chatid": "wrOOClYgAA5gMJijxEUfWC6M0RAjwlWQ", "msgtype": "text", "text": {"content": "<report text>"}}'

If no fatal/high issues exist anywhere and the quota gate was clean:

Sentry 日报 <YYYY-MM-DD> — 全部正常，无高优 issue

Usage

  • One-time: /sentry-monitor
  • Recurring: /loop 24h /sentry-monitor

Constraints

  • This skill is READ-ONLY. Never modify any code files.
  • Do not attempt to fix issues. Only report them.
  • If sentry CLI is not authenticated, prompt the user to run sentry auth login.
  • Never pipe a sentry command through tail/head when you care about success — the pipeline's exit code is the pager's, so a failed call reads as exit 0. Redirect to a file and check $?.

© different-ai-studio, 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 .claude/skills/sentry-monitor of different-ai-studio/teamclu.

Open the folder on GitHubat commit 8f754b3

Compare with similar skills

Sentry Monitor 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.

Sentry Monitor compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sentry Monitor this skilldifferent-ai-studio/teamclu167—~1.7kAutomated safety check: PassMIT
Mobile Nativeleepokai/Codync2691 repos~4.2kAutomated safety check: PassApache-2.0
Ccapwysaid/CameraCapture191—~1.4kAutomated safety check: PassMIT
iOS Log DiagnoseUniClipboard/UniClipboard1.9k—~1.1kAutomated safety check: PassAGPL-3.0
Add Error Trackinggotempsh/temps833—~4.2kAutomated safety check: NotesApache-2.0
Frb Dev Envfzyzcjy/flutter_rust_bridge5.4k—~5.5kAutomated safety check: PassMIT

Similar skills

  • Mobile Native

    leepokai/Codync

    Make a web app feel native on a phone — the small CSS and meta-tag fixes that separate "a website in a browser" from something that feels installed.

    269 GitHub starsUsed in 1 repo~4.2k tokens
    MobileAuto-check passed

  • Ccap

    wysaid/CameraCapture

    Install or use the ccap CLI for camera capture, webcam inspection, device listing, frame capture, and video metadata.

    191 GitHub stars~1.4k tokensUpdated 3 mo ago
    MobileAuto-check passed

  • iOS Log Diagnose

    UniClipboard/UniClipboard

    Drive the UniClipboard iOS app in a simulator and read its OSLog yourself to diagnose a mobile-sync bug, instead of asking the user to paste logs.

    1.9k GitHub stars~1.1k tokensUpdated today
    MobileAuto-check passed

  • Add Error Tracking

    gotempsh/temps

    Add Temps error tracking to applications using the Sentry-compatible SDK.

    833 GitHub stars~4.2k tokensUpdated today
    MobileAuto-check: notes

  • Frb Dev Env

    fzyzcjy/flutter_rust_bridge

    A skill your agent uses when the user wants Docker-based FRB development or Tart-based iOS Simulator validation.

    5.4k GitHub stars~5.5k tokensUpdated yesterday
    MobileAuto-check passed

  • Sentry Cocoa SDK

    getsentry/sentry-for-ai

    Official

    Full Sentry SDK setup for Apple platforms (iOS, macOS, tvOS, watchOS, visionOS).

    268 GitHub stars~5.4k tokensUpdated yesterday
    MobileAuto-check passed

More from different-ai-studio/teamclu

All 8 skills in this repo

  • App Auth

    different-ai-studio/teamclu

    A skill your agent uses when implementing TeamClu platform sign-in, organization-role access, employee pages or protected data endpoints in an app, or changing its login permissions.

    167 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Create Role

    different-ai-studio/teamclu

    Create a workspace role that follows the ROLE.md specification.

    167 GitHub stars~1.5k tokensUpdated today
    Auto-check passed

  • Image Gen

    different-ai-studio/teamclu

    生成图片：配图、插图、海报、头像、示意图、Logo 草稿、封面、banner。触发词：画一张、画个、生成图片、生成一张图、做张图、做个图、配图、出图、生图、AI 绘图、image、draw、illustration、poster。仅从零生成，不做已有图片的编辑或修改。

    167 GitHub stars~430 tokensUpdated today
    Auto-check passed

  • macOS Control

    different-ai-studio/teamclu

    Control macOS desktop applications: open/operate apps, click buttons, type text, scroll, keyboard shortcuts, window management, toggle options, dropdown selections, etc.

    167 GitHub stars~4.2k tokensUpdated today
    Auto-check passed

  • Sentry Fix

    different-ai-studio/teamclu

    A skill your agent uses when the user wants to fix a Sentry issue, auto-repair a bug from Sentry, or create a fix PR for a Sentry error.

    167 GitHub stars~2.2k tokensUpdated today
    Auto-check passed

  • Windows Control

    different-ai-studio/teamclu

    Control Windows desktop applications: open/operate apps, click controls, type text, scroll, keyboard shortcuts, window management, toggle options, lists and combos, etc.

    167 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Sentry Monitor

What does Sentry Monitor do?

A skill your agent uses when the user wants to check Sentry issues, run a Sentry daily report, or monitor error trends. Sentry Monitor is an agent skill from different-ai-studio/teamclu. Use when the user wants to check Sentry issues, run a Sentry daily report, or monitor error trends.

When should I use Sentry Monitor?

Sentry Monitor fits situations like: the user wants to check Sentry issues; run a Sentry daily report; monitor error trends.

How do I install Sentry Monitor in Claude Code?

Run `npx skills add different-ai-studio/teamclu --skill sentry-monitor -a claude-code`. Or copy the skill folder (.claude/skills/sentry-monitor in different-ai-studio/teamclu) into .claude/skills/sentry-monitor in your project. Claude Code loads it when a task matches its description.

How do I install Sentry Monitor in Codex?

Run `npx skills add different-ai-studio/teamclu --skill sentry-monitor -a codex`. Or copy the skill folder (.claude/skills/sentry-monitor in different-ai-studio/teamclu) into .agents/skills/sentry-monitor in your project. Codex loads it when a task matches its description.

Can I use Sentry Monitor 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 different-ai-studio/teamclu --skill sentry-monitor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sentry-monitor, .gemini/skills/sentry-monitor, .github/skills/sentry-monitor and .opencode/skills/sentry-monitor in your project.

What does Sentry Monitor need to run?

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

Does Sentry Monitor 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 Sentry Monitor safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Sentry Monitor use?

Sentry Monitor 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 Sentry Monitor use?

About 1.7k tokens (SKILL.md is roughly 6.7k 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 Sentry Monitor?

Skills that share tags, products or a category with Sentry Monitor: Mobile Native (leepokai/Codync, 269 stars), Ccap (wysaid/CameraCapture, 191 stars), iOS Log Diagnose (UniClipboard/UniClipboard, 1.9k stars) and Add Error Tracking (gotempsh/temps, 833 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sentry Monitor?

different-ai-studio (a GitHub organization) maintains it in different-ai-studio/teamclu, which has 167 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 11, 2026.

Source: different-ai-studio/teamclu on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.