В каталоге 183 730 навыков в 14 категориях.
複雑なバグの並列仮説調査。Subagent/Agent Teams両モード対応。「原因調査」「investigate」「diagnose」で起動。
Use when a test fails and you need to diagnose the root cause. Run the test, read errors, trace through generated and so...
Run safe diagnostic commands on the remote memory server. Use for checking logs, container status, disk usage, memory, a...
Evidence-based debugging discipline for measurable systems. Trigger on:- diagnose, debug, why is X failing, what's causi...
Evidence-led diagnosis for hard bugs and performance regressions, using the full reproduce → minimise → hypothesise → in...
Analyze Claude Code session bloat — shows token count, context usage %, and bloat breakdown. Use when the user asks abou...
Runs a systematic debugging workflow for bugs, regressions, flaky behavior, and performance surprises. Use when somethin...
Trace from a reproduced symptom to the source code that causes it. Identify the specific file and approximate line, then...
Диагностика ступени мастерства (Диагност R28, FORM.089 §6.1 v5.0) прямо в VS Code / claude.ai. До 6 вопросов, ~3 мин. Со...
When something feels off, type /diagnose and describe the symptom. The skill walks the seven-layer stack (kernel, skills...
Use when behavior fails, flakes, or slows down, and nobody knows the cause yet. Also use it when the user says "why does...
Diagnose failures before creating a Prime Agent plan. MUST USE for bugs, CI failures, test failures, regressions, incide...
Use when a judged benchmark or acceptance scenario fails and you need the cause before editing. Reads the judge's render...
Fetch CI logs for a failing branch, classify the failure type, and write a structured
Diagnose a failing CI workflow run (lint, markdown lint, build, or unit tests) — identify which job failed, the cause, a...
Diagnose ClickHouse cluster health and provide concrete remediation.
Diagnose ClickHouse query failures when the user provides a numeric error code, symbolic error name such as UNKNOWN_SETT...
Work out why a 3x-ui client cannot connect, in the order that finds the cause fastest — scope the outage, check the core...
Finds the root cause of a defect and fixes it at the cause, proven by a test that failed first. Use when something is br...
Surfaces PAC CLI upload errors and Dataverse async operation errors, pattern-matches against a known failure catalog, an...
Diagnose drill problems - fuel shortages, blocked outputs, depleted resources. Use when drills aren't working or showing...
Determine the TRUE cause of a failed retort run before attributing it. Ground-truth every failure (run its tests, read i...
Deep autonomous diagnosis of a failed flow run. Provide environment, flow, and run IDs. Use when the user asks to diagno...
Diagnose Gateway, config, secrets, channels, and port failures with read-only one-liners.
When SDK generation fails, determine the root cause and fix strategy.
Diagnose a failing TMDb integration-test run — summarise the failure, rank the likely cause, and suggest a concrete fix
Workflow for diagnosing project issues
Debug and verify the three-layer defense against internal content leaking into user-visible messages.
Verify a native LLM voting advisor before trusting advisor-sensitive evaluations.
Diagnoses failed Maestro cluster deployments by analyzing Helm releases, pod status, and resource conflicts
Diagnose network connectivity issues for pods. Checks DNS resolution, service connectivity, and network policies. Use wh...
Use when the user asks why performance changed or what's going on with an account: ROAS dropped, CPA spiked, spend jumpe...
Diagnose picking bottlenecks from productivity, travel, replenishment, congestion, errors, labor, equipment, and order m...
Diagnose receiving bottlenecks from inbound volume, dock capacity, labor, equipment, documents, queues, and exceptions.
诊断 renderer OOM（内存耗尽崩溃）。当用户交来 renderer OOM 诊断包（zip 或 logs 目录）、报告编辑器窗口变黑/自动关闭、或提到 renderer OOM / Automatic resume is paus...
This is a repository related to my course at DTU, and the exam project on course 38113: Containing drafts for Anthropic...
Load this skill when a Claude Code session went wrong and the cause should be found from its transcript, every finding c...
Use only when the user asks why an agent run went wrong and wants evidence from the transcripts - "why did that take so...
Diagnose a failed or suspicious Runx skill execution from receipts and harness evidence, then propose the smallest bound...
Use when identifying the likely cause and type of a sleep problem to guide appropriate intervention or referral
Read state.json and diagnose PR statuses, errors, stuck entries, and anomalies.
Diagnose storage and persistent volume issues. Checks PVC binding, storage class configuration, and volume mount status....
Use when classifying a stuck, failed, empty, or zero-scoring evaluation as infrastructure or policy failure.
Diagnose logistics throughput loss from throughput gaps, queues, downtime, labor, equipment, process, and source evidenc...
Diagnose why a specific Google Ads or Meta Ads campaign / ad set / ad is underperforming and prescribe the next concrete...
Compatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run f...
Collect and analyze OADP diagnostic data using oadp-must-gather to troubleshoot backup, restore, and deployment issues.
Diagnose WMS inventory issues by reconciling balances, transaction history, physical evidence, master data, and source-s...
Disciplined diagnosis loop for hard bugs, regressions, flaky failures, and performance problems with unclear cause. Use...
Reproduction signals, chronology, and hypothesis testing for hard, elusive, or intermittent bugs. Use when a diagnosis n...
针对棘手 bug 和性能回归的诊断循环。当用户说"诊断"/"调试这个"，或报告某处崩溃/报错/不正常/缓慢时使用。
Diagnosis loop for hard bugs and performance regressions. Use for "diagnose", "debug this", or a reported crash/hang/slo...
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports som...
This skill should be used when diagnosing a reported bug, intermittent failure, stuck operation, or performance regressi...
Diagnosis loop for hard bugs and performance regressions. Use when diagnosing a hard-to-reproduce bug or performance reg...
针对硬 bug 和 performance regression 的诊断循环。当用户说"诊断"/"调试这个"，或报告有东西坏了/抛异常/失败/慢时使用。
Use this skill to diagnose Jetpack Compose stability problems by enabling and reading the Compose Compiler Reports (clas...
Use this skill when troubleshooting OpenStudio or EnergyPlus energy models that fail to simulate, have geometry errors (...
Isolate the root cause of ML performance drops, inconsistent evaluations, prediction errors, and training-serving mismat...
Diagnoses runtime bugs, crashes, regressions, failing CI/CD pipelines, and underspecified user reports through read-only...
Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumb...
当一次 superpowers 会话出了问题、你的人类伙伴想知道原因时使用——重复劳动、无视计划、磕磕绊绊、结果质量差、某个技能没触发、"太慢了"、"为什么这么贵"、"它到底在干什么"——或者想给 superpowers 维护者整理一份 b...
Analyze TypeScript errors and provide detailed diagnostics with root cause analysis and specific fix recommendations
An important skill, to help agents assist doctors with diagnosising patients.
Run the multi-year campaign of being chronically ill with no diagnosis — track patterns across specialists so nothing re...
Structured diagnostic-then-fix workflow using GitNexus knowledge graph and Ariya-4 problem framing. Gathers symptoms, is...
Tool usage patterns for non-prompting file operations - use Glob, Read, Grep instead of Bash commands to avoid user inte...
Agent-only procedure for diagnosing reported bugs. Use before scoping a reported bug and before acting on a diagnostic r...
Executa diagnosticos de saude do banco PostgreSQL: indices nao usados, duplicados, queries lentas, cache hit rate, conex...
Se invoca SOLO de forma explicita (/diagnosticar-repo); NO se carga por contexto y nada del ciclo de desarrollo la dispa...
Use when something in iclone os does not work. Diagnose and self-repair the app, the runtime, the gateway, ACP, the wall...
Use for structured technical SEO audits, incident response, and validation.
Generate DiagnosticReport resources (lab, radiology, pathology, cardiology) and DocumentReference resources (discharge s...
Run comprehensive system diagnostics including dependency checks, test suite execution, git status, and pipeline health...
"RAN fault detection and automated troubleshooting with cognitive consciousness, predictive failure analysis, and autono...
Diagonal Adaptive Non-local Observables (ANO) methodology for quantum neural networks — reduces observable parameter com...
Generate a specific diagram — architecture, flow, db, sequence, deps Arguments: <type> [scope] — types: architecture, fl...
Generate architecture diagrams using Python diagrams library
Architecture diagram of a monorepo's packages: shared foundations, the hosts built on them, runtime dependencies versus...
Generate publication-quality technical diagrams using Nano Banana Pro (Gemini 3 Pro Image) with AI-powered quality revie...
Produce diagrams two ways: Mermaid DSL copied to the clipboard for mermaid.live or excalidraw (default; also ERD, class,...
Generate architecture diagrams for a codebase subsystem or module. Explores source files and produces Mermaid diagrams i...
Turn an English description (or mermaid source) into a diagram triplet: the source, an editable .excalidraw file you can...
Use the smallest visual when prose must carry structure—control flow, call depth, module ownership, or change shape: pse...
Use when a reader needs an editorial architecture, flowchart, sequence, state, ER, swimlane, loop, layer-stack, data-flo...
Generate diagrams from descriptions with Mermaid, PlantUML, or ASCII。Use when 需要项目管理、任务规划、进度跟踪、团队协作时使用。不适用于实际人员绩效评估。适用于独...
Generate Mermaid architecture diagrams from your codebase. Produces C4 context and container diagrams, sequence diagrams...
Use when a diagram is going into a document: pick the tool, write the text source, render it, and embed it with an acces...
Create or update architecture, infrastructure, deployment, swimlane, and request sequence diagrams as generated HTML pag...
Create professional diagrams using Mermaid, PlantUML, and other text-based diagram tools. Generate flowcharts, sequence...
Create process and architecture diagrams using Mermaid.js syntax
Create technical diagrams using diagramming languages like Mermaid, PlantUML, GraphViz, and others. Use when users reque...
Create branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swimlane, qu...
Create generic branded architecture, IT current-state, flowchart, sequence, state machine, ER/data model, timeline, swim...
Create branded architecture, architecture delta, IT current-state, flowchart, sequence, state machine, ER/data model, ti...
에디토리얼 품질 다이어그램 표현 계층. 파이프라인 .mmd(flowchart/sequence/state/ER) 또는 자연어 설명을 브랜드 토큰 기반 self-contained HTML + inline SVG로 렌더링...
Create technical and product diagrams — architecture, IT current-state, flowchart, sequence, state machine, ER / data mo...
以來源證據繪製自足 HTML／SVG 的 SSDLC 圖，包括使用案例、UML 類別與順序圖、操作流程、ER、架構、測試與部署圖；依各階段產物分類並核對圖文一致。
MUST USE when creating, choosing, or improving any diagram or visual explanation - mermaid flowchart/sequence/state/ER d...