菜单
Report Sentry release health (adoption, crash-free sessions and users, new vs resolved issues, regressions) for a release and flag bad releases. Read-only. Use when user asks "how healthy is this release", "is the latest deploy crashing", or "check release health".
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Atlas architect: boot the workspace. Verify claude-mem and context-mode, scan the project, recommend tooling (confirm first), wire hooks, seed the docs/ SSOT.
Measure atlas's own run health, audit context/asset waste, and mine session transcripts. Three lenses: RUN HEALTH reads the observability DB for metrics (wall-clock, dispatches, verifier coverage) and baseline->target goals; ASSET AUDIT scores each context-loaded skill/agent/plugin by token cost and relevance to flag disable/relocate; SESSION FORENSICS mines transcripts for unused tools and unverified claims into rules. No args reports trends.
Use to map a codebase into feature-grouped flowcharts, find architectural duplication across features, and propose the simplest unified architecture - discovery-first and zero-arg. Runs as a Workflow that fans out one explorer per feature, hunts duplication, and synthesizes a unification proposal with file:line evidence. Use before a refactor, to "find the ideal path," or to unify duplicated systems.
Generate or improve a company-specific data analysis skill by extracting tribal knowledge from analysts. BOOTSTRAP MODE - Triggers: "Create a data context skill", "Set up data analysis for our warehouse", "Help me create a skill for our database", "Generate a data skill for [company]" -> Discovers schemas, asks key questions, generates initial skill with reference files ITERATION MODE - Triggers: "Add context about [domain]", "The skill needs more info about [topic]", "Update the data skill with [metrics/tables/terminology]", "Improve the [domain] reference" -> Loads existing skill, asks targeted questions, appends/updates reference files Use when data analysts want Claude to understand their company's specific data warehouse, terminology, metrics definitions, and common query patterns.
QA an analysis before sharing with stakeholders - methodology checks, accuracy verification, and bias detection. Use when reviewing an analysis for errors, checking for survivorship bias, validating aggregation logic, or preparing documentation for reproducibility.
Build self-contained interactive HTML dashboards with Chart.js, dropdown filters, and professional styling. Use when creating dashboards, building interactive reports, or generating shareable HTML files with charts and filters that work without a server.
| name | sentry-release-health |
| description | Report Sentry release health (adoption, crash-free sessions and users, new vs resolved issues, regressions) for a release and flag bad releases. Read-only. Use when user asks "how healthy is this release", "is the latest deploy crashing", or "check release health". |
Assess whether a release is healthy or should be rolled back. Pulls adoption, crash-free sessions and users, the new-vs-resolved issue balance, and regressions tied to the release, then renders a clear healthy/degraded/bad verdict. Read-only.
find_organizations then find_projects to fix the org and project slug.get_sentry_resource (releases resource) and confirm the target release with the user.search_events and get_sentry_resource scoped to the release: session count, crash-free session rate, crash-free user rate, and adoption (share of sessions on this release vs the prior baseline).search_issues filtered to the release: new issues introduced by the release (firstRelease:<version>), regressions (is:regression), and issues resolved in the release.A release health brief containing:
update_issue. update_issue is VISIBLE-TO-OTHERS and mutates team-visible state; rollback or resolve decisions are proposed here, applied by a human.