186 skills · sorted by relevance
Investigate data incidents and find root causes using Monte Carlo's observability data. Guides the agent through systematic investigation: alert lookup, lineage tracing, ETL checks, query analysis, and data profiling. Activates when a user asks about data issues, incidents, alerts, or why data looks wrong.
The English summary is being prepared. Showing the original description.
Diagnose and fix mini-program failures through reproducible, evidence-driven root-cause analysis across source, state, asynchronous timing, caches, mock data, build versions, platform behavior, devices, cloud calls, and external services. Use when users report white screens, crashes, stale or jumping values, missing data, intermittent behavior, permission failures, performance stalls, device-only defects, API or cloud-function errors, source-versus-build mismatches, or regressions whose cause is not yet established. Freezes the observation environment, ranks competing hypotheses, runs discriminating checks, creates a failing regression test before repair, covers analogous states, and never hides a known failure with longer waits, swallowed errors, forced success, or cosmetic patches.
The English summary is being prepared. Showing the original description.
Implement bounded features and fixes in existing or new mini-program codebases while preserving repository rules, user-owned changes, approved behavior, assets, framework conventions, and evidence boundaries. Use when users ask to write or modify mini-program code, implement a confirmed specification or architecture, add a scoped feature, remove behavior semantically, update internal documentation required by a change, or carry out a well-defined small fix that does not require root-cause investigation. Establishes a baseline and change boundary, applies test-driven small steps, distinguishes source from generators and build artifacts, verifies the affected contract, and never reports source completion as device validation, formal acceptance, upload, or release.
The English summary is being prepared. Showing the original description.
A harness that makes Opus (or any Claude model) behave like Fable — it enforces seeing a task through to the end, with evidence and verification, as procedure. Use when starting a multi-step task (2+ sequential stories), long autonomous work, debugging or root-cause investigation, building render/executable artifacts (HTML, SVG, games, charts), or when the user says "fablize", "see it through", "verify as you go", "split into goals".
The English summary is being prepared. Showing the original description.
Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than guessing.
The English summary is being prepared. Showing the original description.
Structured incident response. Use when user reports an outage, production error, or says 'incident', 'something is down', 'users are affected'. Triage severity, contain blast radius, root-cause, document timeline, generate postmortem.
The English summary is being prepared. Showing the original description.
Systematic debugging method: 5-step root-cause analysis (capture, isolate, hypothesize, investigate, fix & verify) plus common bug-pattern reference. Use when errors, exceptions, test failures, or unexpected behavior appear. Loaded automatically by the debugger agent.
The English summary is being prepared. Showing the original description.
Trace bugs, CI failures, and unexpected behavior from reproduced evidence to a causal mechanism and governing contract. Distinguish product, architecture, test-oracle, and harness defects; investigate intermittent failures with controlled experiments and report unresolved evidence explicitly.
The English summary is being prepared. Showing the original description.
Five-Whys Root-Cause Analysis.
The English summary is being prepared. Showing the original description.
Use when EZ_math_model coder or packaging fails repeatedly with the same error and needs root-cause analysis instead of another blind retry.
The English summary is being prepared. Showing the original description.
用户面对多个相互关联的问题, 不知道先解决哪个时; 当需要区分根本原因 与表面症状时; 当问题有先后因果链需要追溯源头时。 不适用于: 只有一个简单问题的场景、问题之间没有因果关系的场景。
The English summary is being prepared. Showing the original description.
Use when a human says "overhaul", "rebuild this subsystem", or "rewrite it from scratch". Not for thin-slice features: use incremental-implementation. Not for root-cause repair: use strike-the-root.
The English summary is being prepared. Showing the original description.
分布式训练梯度尖刺 (Gradient Spike) 根因定位。基于梯度监控数据 (trend.db/CSV)、 msprobe dump 统计数据，三阶段渐进式从异常坐标定位逐层深入到算子级根因。 当用户明确指明分析梯度尖刺问题时使用此 skill。 即便用户提供以上数据，但未指明分析梯度尖刺问题时，不可使用此skill。
The English summary is being prepared. Showing the original description.
Deep root cause analysis using the 5 Whys and Fishbone techniques. Use when systematic debugging hasn't found the cause, or for complex systemic issues. Keywords: root cause, why, underlying, fundamental, systemic, deep, origin
The English summary is being prepared. Showing the original description.
Use when diagnosing or fixing user-reported application bugs. Guides evidence-backed root-cause analysis from symptoms, screenshots, logs, provider failures, background tasks, storage, or desktop lifecycle behavior through a scoped patch and regression tests.
The English summary is being prepared. Showing the original description.
Conduct structured root cause analysis using Ishikawa (Fishbone), 5 Whys, and Pareto methods. Suitable for production incidents, quality defects, customer complaints, and recurring operational problems. Use when problems recur or when initial fixes do not resolve the issue. Do not use for one-time, obvious fixes or strategic decision-making.
The English summary is being prepared. Showing the original description.
Define a Lean Six Sigma improvement project using DMAIC, problem framing, baseline measures, root-cause hypotheses, CTQs, and control planning. Use when an existing process is underperforming and the team needs a charter, SIPOC, baseline, and improvement path. Do not use for brand-new process design or vague complaints with no process boundary.
The English summary is being prepared. Showing the original description.
Provides data-retrieval best practices, tool selection guidance, and performant SQL query syntax for BigQuery telemetry across INFORMATION_SCHEMA, Cloud Monitoring, and the REST API. Use when the telemetry to fetch is already known, selecting telemetry tools, writing performant INFORMATION_SCHEMA queries, retrieving telemetry for diagnosing single-job performance bottlenecks, investigating slot contention, job concurrency and queue latency, analyzing reservation capacity, utilization and autoscaling saturation, or auditing capacity-based and on-demand compute and storage resource billable usage. Don't use for root-cause diagnosis or symptom troubleshooting when the cause is unknown (use bigquery-troubleshooting first), or for writing or optimizing business logic SQL (use bigquery-optimization).
The English summary is being prepared. Showing the original description.
Find the root cause of a problem, not just symptoms. Use when the user says "root cause", "why does this keep happening", "5 whys", "fishbone diagram", "cause analysis", "problem investigation", "defect analysis", "incident analysis", "A3 problem solving", "what's causing this", "ishikawa" - even if they don't explicitly say "root cause analysis".
The English summary is being prepared. Showing the original description.
Audit financial reconciliation workflows -- evaluate automated transaction matching engines, intercompany balance reconciliation, suspense and clearing account health, variance root-cause investigation, and close calendar integration.
The English summary is being prepared. Showing the original description.
Enter explore mode for technical work — a thinking partner for {{engine_name}} code, architecture, and implementation decisions before you write any code. Use it to investigate a technical solution, design the architecture of a feature, choose between frameworks or libraries, compare implementation approaches, analyze how existing code or a system works, or deeply root-cause a complex bug without fixing it yet. The ultra mode adds adaptive artifacts (a C4 view, ADRs, a dependency graph) to the research folder — run it on "ultra research", "ultra explore" or "ultraresearch"; otherwise run the default. Trigger on "let's explore this technical solution", "how should we architect this feature", "which framework should we use", "run an ultra research on the save system", "investigate this error deeply". Research and analysis only — it never writes code. This is the CODE / engineering explorer — for GAME-DESIGN, GDD, mechanics, or balance research (no code) use /unikit-gd-explore.
The English summary is being prepared. Showing the original description.
Analyze a set of related tickets to identify the underlying root cause.
The English summary is being prepared. Showing the original description.
Bug-fixing workflow that coordinates diagnosis, test-driven reproduction, root-cause analysis, and targeted fixes. Use when the user wants to fix a bug with thorough investigation and regression testing.
The English summary is being prepared. Showing the original description.
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
The English summary is being prepared. Showing the original description.