'root-cause' 검색 결과

Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective actions after an LLM failure. Produces a structured postmortem with trace reconstruction, a root-cause layer analysis, and corrective actions including a permanent regression case. For non-AI production incidents use incident-postmortem.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when SLCI code inspection has failed due to compatibility issues and you need to diagnose the incompatibilities. Traces inspection failures back to root-cause incompatibility settings or known limitations by matching failed code lines against known incorrect code generation patterns and documented limitation scenarios. Hands off to slci-compatibility-analysis for fixes. Trigger keywords: inspect, inspection failed, trace inspection errors, why did inspection fail, SLCI verification failures, limitation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Debug systematically with root-cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues, CI failures, or system investigation.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use this skill for Amazon e-commerce research, market validation, competitor analysis, traffic diagnosis, keyword strategy, advertising review, launch evaluation, and growth optimization using the Sif MCP server and Sif's real marketplace, traffic, keyword, sales, and ad data. Trigger when users mention Sif, Sif MCP, ASIN research, Amazon product opportunity research, keyword opportunity, competitor teardown, traffic drop/root-cause diagnosis, advertising structure review, or whether a product/market is worth entering, launching, scaling, optimizing, or abandoning.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

CAPA system management for medical device QMS, covering root cause analysis, corrective action planning, and effectiveness verification. Use for CAPA investigations, 5-Why and fishbone analysis, and corrective action tracking.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Systematic root-cause debugging. Iron Law: no fixes without root cause investigation first. Four phases: Root Cause Investigation, Pattern Analysis (6 known patterns), Hypothesis Testing (3-strike rule), Implementation. Structured debug report output.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Autonomous cloud-cost analyst across Neon, Vercel, Railway and GitHub Actions - pulls per-object usage, attributes it to the biggest drivers, root-causes each, and emits recommendations ranked by real signal (idle %, over-allowance, failure rate) with dollar figures only where the billing API returns real ones (and, armed, applies safe cost levers).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when marketing numbers look bad and the user needs to know WHY — layered root-cause diagnosis across tracking, delivery, creative, landing page, offer, and audience quality, 5-Whys, regional benchmarks for US, EU, SEA, and LATAM, and a 48-hour action plan. Covers dropshipping ROAS and BE-ROAS. Trigger on 'why is CPA so high', 'my ads are not converting', 'ROAS dropped', 'we are burning budget', 'performance is bad this month', 'diagnose the funnel'. Also use when the user pastes a screenshot of numbers with no question attached. Not for — auditing account configuration and scoring health, see `21-ads-audit-global`; writing a report someone else reads, see `07-marketing-report-global`; turning a raw export into insight, see `13-data-analysis-global`.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Quarantines an intermittently failing test behind a ticket with an owner and expiry, assigns a root-cause bucket from isolated reruns, and defines when the test leaves quarantine. Use when a test is a QUARANTINE_CANDIDATE or fails without a code change; not for deterministic failures.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional native DeepSeek Harness subagents only when useful.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional native OpenCode subagents only when useful.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence; Codex subagents are optional.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Investigate Elixir/Phoenix bugs root-cause first. Reproduce failures, cite evidence, and use optional Amp subagents only when useful.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Performs root-cause analysis of a bug — from a GitHub issue, an issue URL, or a free-text description — before any reproduction or fix is written. TRIGGER when: triaging or diagnosing a bug, investigating why something misbehaves, an issue number/URL handed over for analysis, needing the root cause before touching code. DO NOT TRIGGER when: a failing reproduction test already exists and you are ready to fix → opsmill-dev-fixing-bugs; writing that reproduction test → opsmill-dev-test-driving-bugs; capturing a new bug as a ticket → opsmill-dev-creating-issues.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Implements and validates the fix for a bug once a failing reproduction test exists. TRIGGER when: a bug has a failing reproduction test and you are ready to make it pass, implementing the root-cause fix, the final step of the bug-fixing pipeline. DO NOT TRIGGER when: no reproduction test exists yet → opsmill-dev-test-driving-bugs; still diagnosing, or asked to fix a bug with no analysis or reproduction test yet → opsmill-dev-analyzing-bugs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Systematic investigation of metric changes and anomalies. Use when a metric unexpectedly changes, investigating business metric drops, explaining performance variations, or drilling into aggregated metric drivers.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

PL (Project Lead) role sub-skill for incident analysis and process evaluation. Loaded through the pl core routing table, or when the owner explicitly asks for a retrospective or root-cause write-up; NEVER auto-load from ambient context.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a framed and root-caused problem needs its assumptions made explicit before design or planning begins — explicit Assumptions, Unknowns, and a Validation plan. This should trigger when an issue's Assumption Analysis point of view needs evaluation, or when a maintainer directly asks to surface hidden assumptions and unknowns before committing to an approach. Part of Plinth Toolkit

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when a problem or issue needs explicit framing before deeper analysis begins — establishing the Problem statement, Current state, Desired state, Stakeholders, and Success criteria. This should trigger when an issue's Problem Framing point of view needs evaluation, or when a maintainer directly asks to frame a problem before root-cause analysis, design, or planning begins. Part of Plinth Toolkit

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

【Bug 诊断专用】当遇到程序错误、异常行为、性能问题、功能故障时必须使用本技能。触发关键词：报错、Bug、问题、异常、故障、不工作、诊断、排查、修复。本技能提供系统性根因分析，输出详细诊断报告和可执行修复方案，包含代码位置引用、步骤指导、注意事项。仅提供分析和方案，不直接修改代码。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Read from a UModel object-graph semantic layer with the `umctl` CLI (MCP alternative noted). Three kinds of read: (1) entities & relationships / topology (`.entity`, `.topo`) and (2) the model itself (`.umodel`, and `.entity_set` methods, including entity-linked `list_skills`) return real rows; (3) metrics & logs (`get_metrics` / `get_logs`) return an executable *plan* — PromQL / Elasticsearch DSL with the entity id pre-substituted — that you run against the backend. Against a PaaS endpoint the same calls return data rows instead of a plan. Use to query or read UModel entities, relations, topology, or model metadata; to read a service's metrics or logs; to look up services and dependencies; or to discover what objects, datasets, and methods exist. For root-cause analysis on top of these reads, see the `umodel-rca` skill. Triggers: UModel, object graph, .entity / .topo / .umodel / .entity_set, query entities, read topology, read metrics / logs, get_metrics / get_logs, list services / dependencies / datasets / skills, 实体查询, 关系/拓扑查询, 读模型, 读指标, 读日志, 查指标, 查日志, 查服务依赖.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Model-guided autonomous root-cause analysis over a UModel object-graph semantic layer. Use with `umodel-query` when diagnosing service degradation, SLO breach, latency/error spikes, incidents, outages, or questions like why a service is slow, degraded, erroring, or timing out. The skill guides evidence collection across object graph, metrics, logs, topology, runbooks, deployments, config changes, business traffic, and runtime capacity; it is especially useful for ruling out red herrings such as recent but unrelated deployments. Triggers: root cause, RCA, incident, SLO breach, outage, postmortem, latency spike, error spike, timeout, 根因分析, 故障排查, 告警定位, 为什么慢, SLO 击穿.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Produces a progressive-disclosure overview of unfamiliar code or a pull request's changes with code-overview and publishes the resulting overview to a user-specified Confluence location. Use when the user wants code or a PR explained, oriented, or made sense of AND the overview posted to a Confluence space or page. Requires a configured Atlassian MCP server. Does not produce the overview to a local file only — use code-overview. Does not publish an arbitrary existing markdown file — use markdown-to-confluence. Does not document an already-understood feature to Confluence — use project-documentation-to-confluence. Does not root-cause a bug to Confluence — use investigate-to-confluence. Does not plan or specify a new feature to Confluence — use plan-a-feature-to-confluence. Does not publish to Jira — use work-items-to-jira.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Runs an evidence-based investigation of a bug, failure, or unexpected behavior with investigate and publishes the resulting investigation report to a user-specified Confluence location. Use when the user wants something debugged, diagnosed, or root-caused AND the findings posted to a Confluence space or page. Requires a configured Atlassian MCP server. Does not investigate to a local file only — use investigate. Does not publish an arbitrary existing markdown file — use markdown-to-confluence. Does not document an already-understood feature to Confluence — use project-documentation-to-confluence. Does not plan or specify a new feature to Confluence — use plan-a-feature-to-confluence. Does not publish to Jira — use work-items-to-jira.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.