Answer "what's breaking" questions from Sentry — find the right org and project, search issues and events with the vocabulary Sentry uses, and report what is actually firing rather than the first hit. Use when the user asks what errors are happening, whether something is stable, what changed since a release, or for any health summary of a service.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Sentry answers precise questions precisely and vague questions misleadingly. The work is scoping the question before searching, and ranking what comes back by impact instead of by relevance.
Run find_organizations and find_projects before searching if you are not
certain where the code reports to. A monorepo often maps to several Sentry
projects (api, web, desktop), and a search in the wrong one returns a
confident, empty answer. Say which project you searched.
"Is checkout broken?" becomes queries on what Sentry actually stores: the
error type, the transaction or URL, the release. Prefer search_issues for
"what problems exist" and search_events for "how often / for whom / since
when". Run two or three narrow queries over one broad one, and time-bound
them — is:unresolved over the last 24h answers a different question than
all-time.
The issues worth reporting are the ones with high event counts, many affected
users, or a first-seen that matches a recent release. A brand-new issue with
three events can matter more than a year-old one with thousands — say why the
ones you picked matter. When a number is load-bearing (error rate, affected
users), take it from search_events rather than eyeballing the issue list.
Every issue you cite gets its Sentry link and the window you looked at.
"No matching issues in the last 7 days in api" is a complete, useful
answer — silence about scope is how "it's fine" turns out to mean "I searched
the wrong project".
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Personalized audit that teaches the advanced Superset features the user isn't using yet (automations, parallel agents, tasks, multi-host, terminal remote control, custom commands, MCP, pages) and sets them up live. Use when the user wants to get more out of Superset, asks "what else can Superset do", "how do I 10x my workflow", "what am I missing", or wants to learn a specific Superset feature.
日本語の概要は準備中です。原文の説明を表示しています。
Turn a recurring chore into a Superset automation. Drafts the agent prompt, confirms the schedule or event trigger and the target, creates it with the CLI, and reviews the first run together. Use when the user wants a scheduled or recurring agent, a daily or weekly job, or an agent that reacts to a Slack message, GitHub pull request, Linear issue, Sentry issue or incoming email, or says things like "every morning do X", "automate this", "set up a cron agent", "run this on a schedule", "when someone opens a PR, do X".
日本語の概要は準備中です。原文の説明を表示しています。
Open, navigate, screenshot, read, click, and type in web pages from an agent. Use when the user asks to open a URL, preview or verify a running web app, check a page's console, fill a form, click through a web flow, or automate anything in a browser, including "open localhost:3000", "screenshot the page", "what does the console say", "click the submit button", "I'm logged in on Chrome". Drives the in-app browser pane of a Superset workspace by default and Browser Use for browsers the panes cannot reach.
日本語の概要は準備中です。原文の説明を表示しています。
Write Stripe code against what the API does today — plan the product shape, confirm every parameter from Stripe's own docs and schemas, and keep the agent in a sandbox. Use when adding checkout, billing, subscriptions, invoicing, or webhooks to a codebase, or when debugging Stripe integration code that compiles but behaves wrong.
日本語の概要は準備中です。原文の説明を表示しています。
Verify UI behavior end-to-end by driving the running desktop app over the Chrome DevTools Protocol. Use when asked to verify, reproduce, or confirm a UI change, bug, or regression in the real app rather than in tests.
日本語の概要は準備中です。原文の説明を表示しています。
Diagnose a failing GitHub Actions run — find the first real error in the logs, tell a flake apart from a genuine failure, and identify the commit that broke it. Use when checks are red on a PR, a workflow failed, the build is broken, CI is flaky, or the user asks why a run failed or whether a failure is real.
日本語の概要は準備中です。原文の説明を表示しています。