agentsclimarketplace

Debug & triage

5,150 rows, by stacks then stars

1,113 of these skill files have been read, by 1,020 distinct authors, and what they tell an agent counted. What Debug & triage authors agree on, and what they forbid

  • Webapp testing

    bh-rat/steer/examples/rebuilds/webapp-testing Skill

    7★ repo

    Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs. Use when the user asks to test, debug, screenshot, or automate a local web app.

  • Bug hunter

    playbookTV/Ironclad/skills/bug-hunter Skill

    no license7★ repo

    Reproduce, isolate, and diagnose a specific software failure before changing production behaviour, then propose the smallest safe fix with regression protection. Use whenever the user reports a bug, crash, error, stack trace, flaky test, incorrect output, "works on my machine," intermittent failure, regression after a deploy, or any behaviour that diverges from expectation and the cause is not obvious. Prefer this over jumping straight to a fix. Part of the audit suite; inherits the shared constitution, while its own job is proving causality.

  • Dotnet trace collect

    Harmeet10000/skills/skills/backend/C#_dotnet/dotnet-trace-collect Skill

    7★ repo

    Guide developers through capturing diagnostic artifacts to diagnose production .NET performance issues. Use when the user needs help choosing diagnostic tools, collecting performance data, or understanding tool trade-offs across different environments (Windows/Linux, .NET Framework/modern .NET, container/non-container).

    The same file is in 1 other repository

  • Run tests

    Harmeet10000/skills/skills/backend/C#_dotnet/run-tests Skill

    7★ repo

    Runs .NET tests with dotnet test. Use when user says "run tests", "run my tests", "run these tests", "execute tests", "dotnet test", "test filter", "filter by category", "filter by class", "combine filters", "run only specific tests", "integration tests", "unit tests", "tests not running", "hang timeout", "blame-hang", "blame-crash", "crash dump", "TRX report", "TRX", "test report", "generate TRX", "TUnit", "treenode-filter", "target framework", "multi-TFM", or needs to detect the test platform (VSTest or Microsoft.Testing.Platform), identify the test framework, apply test filters, or troubleshoot test execution failures. Covers MSTest, xUnit, NUnit, and TUnit across both VSTest and MTP platforms. Also use for --filter-class, --filter-trait, --report-trx, --logger trx, --blame-hang-timeout, and other platform-specific filter and reporting syntax. DO NOT USE FOR: writing or generating test code, CI/CD pipeline configuration, or debugging failing test logic.

  • Golang error handling

    Harmeet10000/skills/skills/backend/Golang/golang-error-handling Skill

    7★ repo

    Idiomatic Golang error handling — creation, wrapping with %w, errors.Is/As, errors.Join, custom error types, sentinel errors, panic/recover, the single handling rule, structured logging with slog, HTTP request logging middleware, and samber/oops for production errors. Built to make logs usable at scale with log aggregation 3rd-party tools. Apply when creating, wrapping, inspecting, or logging errors in Go code.

    The same file is in 1 other repository

  • Golang observability

    Harmeet10000/skills/skills/backend/Golang/golang-observability Skill

    7★ repo

    Golang everyday observability — the always-on signals in production. Covers structured logging with slog, Prometheus metrics, OpenTelemetry distributed tracing, continuous profiling with pprof/Pyroscope, server-side RUM event tracking, alerting, and Grafana dashboards. Apply when instrumenting Go services for production monitoring, setting up metrics or alerting, adding OpenTelemetry tracing, correlating logs with traces, migrating legacy loggers (zap/logrus/zerolog) to slog, adding observability to new features, or implementing GDPR/CCPA-compliant tracking with Customer Data Platforms (CDP). Not for temporary deep-dive performance investigation (→ See golang-benchmark and golang-performance skills).

    The same file is in 1 other repository

  • Golang performance

    Harmeet10000/skills/skills/backend/Golang/golang-performance Skill

    7★ repo

    Golang performance optimization patterns and methodology - if X bottleneck, then apply Y. Covers allocation reduction, CPU efficiency, memory layout, GC tuning, pooling, caching, and hot-path optimization. Use when profiling or benchmarks have identified a bottleneck and you need the right optimization pattern to fix it. Also use when performing performance code review to suggest improvements or benchmarks that could help identify quick performance gains. Not for measurement methodology (see golang-benchmark skill) or debugging workflow (see golang-troubleshooting skill).

    The same file is in 1 other repository

  • Golang samber slog

    Harmeet10000/skills/skills/backend/Golang/golang-samber-slog Skill

    7★ repo

    Structured logging extensions for Golang using samber/slog-**** packages — multi-handler pipelines (slog-multi), log sampling (slog-sampling), attribute formatting (slog-formatter), HTTP middleware (slog-fiber, slog-gin, slog-chi, slog-echo), and backend routing (slog-datadog, slog-sentry, slog-loki, slog-syslog, slog-logstash, slog-graylog...). Apply when using or adopting slog, or when the codebase already imports any github.com/samber/slog-* package.

    The same file is in 1 other repository

  • Golang troubleshooting

    Harmeet10000/skills/skills/backend/Golang/golang-troubleshooting Skill

    7★ repo

    Troubleshoot Golang programs systematically - find and fix the root cause. Use when encountering bugs, crashes, deadlocks, or unexpected behavior in Go code. Covers debugging methodology, common Go pitfalls, test-driven debugging, pprof setup and capture, Delve debugger, race detection, GODEBUG tracing, and production debugging. Start here for any 'something is wrong' situation. Not for interpreting profiles or benchmarking (see golang-benchmark skill) or applying optimization patterns (see golang-performance skill).

    The same file is in 1 other repository

  • Logging best practices

    Harmeet10000/skills/skills/cloud-devops/logging-best-practices Skill

    7★ repo

    Logging best practices focused on wide events (canonical log lines) for powerful debugging and analytics

    The same file is in 1 other repository

  • Marker triage

    marker-io/mcp-skills/claude/skills/marker-triage Skill

    7★ repo

    Triage a Marker.io website-feedback backlog at scale. Use when asked to go through, categorize, prioritize, deduplicate, or make sense of many Marker.io issues at once. Splits content fixes from functional bugs, groups by page, rates criticality, flags duplicates and repeat reporters, surfaces quick wins, lists affected users, and writes a dashboard plus an issues table. Proposes status/priority/type updates before applying.

  • Estuary logs

    estuary/agent-skills/skills/estuary-logs Skill

    7★ repo

    Search and analyze Estuary task logs with jq filtering. Use when investigating task failures, debugging connector errors, analyzing behavior patterns, or streaming live logs. Use when user says "check logs", "show me logs", "task failing", "why is my capture failing", "why is my materialization failing", "error messages", "why did it fail", "search task logs", "shard failed", "follow logs", "increase log level", "debug logging", "is this log message normal", "what does this message mean", "connection timeout", or "i/o timeout".

  • Debug

    bricerising/enterprise-software-playbook/skills/debug Skill

    7★ repo

    Triage and diagnose production or local issues by following logs → traces → metrics (HTTP/gRPC/async). Use when investigating errors, latency spikes, 5xx responses, SLO violations, or regressions in an instrumented app. NOT for adding new instrumentation (use observability); NOT for applying resilience patterns (use resilience).

  • Observability

    bricerising/enterprise-software-playbook/skills/observability Skill

    7★ repo

    Add or change observability instrumentation (structured logging, OpenTelemetry traces/spans, RED metrics, dashboards, alerts). Use when adding logs/metrics/traces to code, defining telemetry field contracts, or building monitoring runbooks. NOT for diagnosing existing issues with existing telemetry (use debug); NOT for security-specific logging concerns (use security).

  • Fix from logs

    Agent-Engineer-Master/skill-engineer/engineering/fix-from-logs Skill

    7★ repo

    Diagnoses bugs from raw error logs, stack traces, or CI failure output — triages and clusters errors, localizes root cause (file → function → line), enters plan mode with a structured fix + test proposal for human approval, writes a typed pytest regression test using mocks first, then implements a targeted code fix and verifies the test turns green. Trigger when: user pastes logs and wants the underlying bug fixed with tests that prevent recurrence; user says "here are the logs, fix it"; CI output shows failures needing code changes and test coverage; stack traces are provided with a request to fix and test. Do NOT trigger for: general code review without logs, refactoring without a specific bug, performance work, test coverage requests with no associated failure.

  • Diagnose bug

    flurdy/agent-skills/skills/diagnose-bug Skill

    7★ repo

    Evidence-led, read-only bug diagnosis using minimal reproduction, boundary isolation, ranked hypotheses, and explicit falsification tests before any fix is proposed.

  • Triage

    flurdy/agent-skills/skills/triage Skill

    7★ repo

    Create bead(s) from a user prompt or Jira ticket. Investigates relevance, checks for duplicates, and may split complex requests into multiple focused beads.

  • Flutter setup

    Poorgramer-Zack/dart-expert-skills/skills/flutter-setup Skill

    7★ repo

    Complete Flutter SDK installation, IDE configuration, and troubleshooting guide for Linux, macOS, and Windows. Use for installing Flutter SDK from scratch, configuring PATH environment variables across platforms, setting up VS Code/Android Studio/IntelliJ IDEA with Flutter plugins, resolving 'flutter command not found' errors, fixing flutter doctor warnings and errors, troubleshooting Android SDK/NDK installation issues, configuring Xcode and CocoaPods on macOS, installing Visual Studio C++ build tools on Windows, resolving PATH conflicts and SDK path issues, fixing network/proxy setup problems, debugging IDE plugin activation, configuring emulators and simulators, handling platform-specific build errors, resolving dependency conflicts, fixing certificate and signing issues, troubleshooting hot reload failures, and verifying successful installation with flutter doctor diagnostics.

  • Flutter testing

    Poorgramer-Zack/dart-expert-skills/skills/flutter-testing Skill

    7★ repo

    Covers Flutter testing across all three layers: unit tests (business logic, ViewModels, repositories), widget tests (UI rendering, interactions, golden regression), and integration/E2E tests (full app flows, native OS interactions). Use this skill when writing any Flutter test, setting up mocking with mocktail or mockito, implementing golden file tests, debugging async failures (pumpAndSettle timeouts, Timer leaks, FakeAsync deadlocks), fixing cross-platform golden pixel diffs in CI/CD, testing state management (Riverpod/BLoC/Provider), handling permission dialogs or native system UI with Patrol, or troubleshooting MediaQuery/Theme missing errors in widget tests.

    The same file is in 3 other repositories

  • Marionette

    Poorgramer-Zack/dart-expert-skills/skills/marionette Skill

    7★ repo

    AI-driven Flutter E2E testing via VM Service CLI. Control running Flutter apps in debug mode for smoke tests, regression checks, exploratory testing, and UI automation. Trigger when user mentions E2E testing, UI automation, smoke tests, integration testing, test automation, controlling Flutter apps, VM Service interaction, debugging UI flows, automated regression testing, CI sanity checks, or testing native dialogs/permissions/WebViews. Supports stateful named instances or stateless direct URI connections. Ideal for rapid test feedback, AI agent workflows, element discovery, screenshot capture, log collection, and scriptable UI interactions (tap, scroll, enterText). Use for troubleshooting flaky tests, automating repetitive manual tests, verifying app behavior after merges, or setting up automated QA pipelines.

    The same file is in 1 other repository

  • Sentry flutter

    Poorgramer-Zack/dart-expert-skills/skills/sentry-flutter Skill

    7★ repo

    Integrates Sentry error tracking and performance monitoring into Flutter apps using `sentry_flutter`. Use when setting up crash reporting in Flutter, calling `SentryFlutter.init`, adding `SentryNavigatorObserver` to GoRouter, tracing HTTP requests with `sentry_dio`, capturing handled exceptions via `Sentry.captureException`, adding breadcrumbs, configuring session replay (`replay.onErrorSampleRate`), tuning `tracesSampleRate` or `profilesSampleRate`, controlling PII with `sendDefaultPii`, or setting user context after login and logout.

    The same file is in 2 other repositories

  • Resonate basic debugging go

    resonatehq/resonate-skills/resonate-basic-debugging-go Skill

    7★ repo

    Debug and troubleshoot Resonate applications using the Go SDK. Use when investigating stuck or never-resuming workflows, duplicated side effects after replay, promise decode errors, latent-promise settlement encoding traps, localnet heartbeat failures, or the pre-release caveats of the Go SDK. Pre-release: no semver tag yet; pin a commit for stability.

  • Resonate basic debugging java

    resonatehq/resonate-skills/resonate-basic-debugging-java Skill

    7★ repo

    Debug and troubleshoot Resonate applications using the Java SDK. Use when investigating stuck or never-resuming workflows, duplicated side effects after replay, untyped-handle decode surprises (Integer vs Long), CLI positional-argument arity mismatches, the detached by-name-only constraint, Java 21 / virtual-thread requirements, rejected-promise error handling, or r.stop() silently killing a live worker. Verified against the resonatehq-examples/*-java repos and develop/java.mdx (docs PR #230) at io.resonatehq:resonate-sdk-java:0.1.1.

  • Resonate basic debugging python

    resonatehq/resonate-skills/resonate-basic-debugging-python Skill

    7★ repo

    Debug and troubleshoot Resonate applications using the Python SDK v0.7.0 and Resonate Server v0.9.x. Use when investigating stuck workflows, non-deterministic replays, registration errors, async/await mistakes, unexpected retries, or server connectivity issues.

  • Resonate basic debugging rust

    resonatehq/resonate-skills/resonate-basic-debugging-rust Skill

    7★ repo

    Debug and troubleshoot Resonate applications using the Rust SDK. Use when investigating registration errors, serde serialization failures, tokio runtime mismatches, git-dependency install issues, or the v0.1.0-specific caveats of the early-development Rust SDK.

  • Resonate basic debugging typescript

    resonatehq/resonate-skills/resonate-basic-debugging-typescript Skill

    7★ repo

    Debug and troubleshoot Resonate applications and deployments, especially TypeScript SDK and Resonate Server issues. Use when investigating failures, stuck workflows, error codes, or unexpected replays.

  • Error handling patterns

    WesleySmits/agent-skills/.agent/skills/error-handling-patterns Skill

    no license7★ repo

    Master error handling patterns across languages including exceptions, Result types, error propagation, and graceful degradation to build resilient applications. Use when implementing error handling, designing APIs, or improving application reliability.

  • Diagnose modelica

    WolframResearch/system-modeler-ai-toolkit/diagnose-modelica Skill

    7★ repo

    Diagnose Modelica models (.mo files) by generating a detailed structural and simulation report. Use this skill whenever the user asks to diagnose, analyze, profile, or debug a Modelica model's structure, equations, variables, or performance. Triggers on phrases like 'diagnose this model', 'analyze the model structure', 'show me the equation blocks', 'how many states does this model have', 'why is this model slow', 'debug this model', 'model report', or any request to understand the internals of a Modelica model.

  • Expressjs docs

    cookieMonsterDev/agents-skills/docs-skills/expressjs-docs Skill

    7★ repo

    Use when users ask how to build, explain, configure, route, secure, debug, migrate, or troubleshoot Express.js web applications and APIs, including middleware, routing, error handling, request/response objects, the Router, static files, templates, proxies, performance, security, graceful shutdown, or Express 5 migration, especially when they need official Express documentation, exact links, or docs-grounded JavaScript guidance.

  • Kubernetes docs

    cookieMonsterDev/agents-skills/docs-skills/kubernetes-docs Skill

    7★ repo

    Use when users ask how to install, configure, deploy, scale, secure, network, store, schedule, debug, or troubleshoot Kubernetes clusters and workloads, including pods, deployments, services, ingress, configmaps, secrets, RBAC, kubectl, kubeadm, Helm-adjacent core APIs, autoscaling, jobs, statefulsets, daemonsets, CRDs, or cluster administration, especially when they need official Kubernetes documentation, exact links, or docs-grounded guidance.

  • Observability standard

    martin1847/evolab/skills/observability-standard Skill

    6★ repo

    生产级可观测性与工程规范,适用于**所有后端服务** —— 普通微服务(auth / 网关 / 业务服务)与 agent / 多 agent / RAG 知识库项目通用。核心:用 trace_id 串 trace/log + 业务 id 反查 db、结构化日志、OpenTelemetry 埋点、跨进程 W3C traceparent 传播、日志级别纪律、边界类型纪律(含 id 持久化:不往业务行塞 trace_id);agent / RAG 场景在此基线上加 LLM / 工具 / 检索埋点与 GenAI 语义约定。Use this skill whenever writing or reviewing backend code that involves logging setup, OpenTelemetry tracing, structured logs, cross-process context propagation, choosing log levels (INFO vs DEBUG), correlating logs / traces / db to debug, defining types for boundary or inter-service data — and additionally agent orchestration / sub-agents, LLM / tool / retrieval calls, or GenAI semantic conventions. 适用 Python / Go / Java / Rust。Apply it even when the user only says things like "加点日志" "接一下 trace / instrument this" "set up observability" "这个错误怎么查不到" "这个请求怎么追踪",不限于显式提到规范时。目标:trace_id 串 trace/log、业务 id 反查 db,让线上问题最快定位。

  • Visual debug

    voidmatcha/ui-clone-skills/skills/visual-debug Skill

    6★ repo

    Compare original site vs implementation with automated AE/SSIM diff — near-zero vision tokens. Triggers on "it looks different", "doesn't match", "compare with original", "what's wrong", "why is the impl off", "diff against ref", "verify the clone". Uses auto-diagnose to find mismatched elements from diff images without vision tokens. Falls back to reading diff images only when auto-diagnose finds nothing.

  • Ozor prompt optimizer

    Mintii-Labs/ozor-skills/skills/ozor-prompt-optimizer Skill

    6★ repo

    Analyze and improve existing Ozor.ai video prompts for better output quality. Use this skill whenever the user has an Ozor prompt that produced mediocre results, wants to improve a video prompt, needs help debugging why a video didn't turn out well, or wants expert feedback on their prompt before running it. Trigger on phrases like 'improve this prompt', 'optimize my Ozor prompt', 'why did my video look bad', 'fix this prompt', 'make this prompt better', 'review my Ozor prompt', 'the video didn't turn out right', 'prompt feedback', 'better results from Ozor', or any request to refine, debug, or enhance an existing Ozor video prompt.

  • Eso source triage

    Neetx/eso-skills/skills/eso-source-triage Skill

    no license6★ repo

    Classifies ESO sources, verifies claims, and assigns confidence labels. Use when a request involves patch notes, live data, current meta, prices, events, external builds, outdated information, or conflicting ESO sources.

  • Vb6 trace pattern

    alexcassol/claude-vb6-skills/skills/vb6-trace-pattern Skill

    6★ repo

    Applies the manual stack-trace pattern for Visual Basic 6 based on EnterMethod/ExitMethod calls that push and pop method names from a module-level array. This pattern compensates for the absence of a native call stack in VB6, enabling rich production logs with call depth, parameter serialization, and on-demand stack inspection in error handlers. Covers when to instrument procedures (every non-trivial function), placement rules (EnterMethod in EhHeader, ExitMethod in both success and error paths), optional parameter serialization, the TraceMethod function for inserting the current stack into error messages, log file management (rolling daily logs with retention), activation gating (only logs when explicitly enabled or running in the IDE), and automatic process dumping via WMI when automation errors are detected. Activates whenever working with EnterMethod, ExitMethod, LogMsg, TraceMethod, manual stack trace, or any VB6 task involving production diagnostics, error logging, debugging, or fault investigation.

  • Fetch library docs

    sheikh-mohammad/agent-factory-claude-skills/.claude/skills/fetch-library-docs Skill

    no license6★ repo

    Fetches official documentation for external libraries and frameworks (React, Next.js, Prisma, FastAPI, Express, Tailwind, MongoDB, etc.) with 60-90% token savings via content-type filtering. Use this skill when implementing features using library APIs, debugging library-specific errors, troubleshooting configuration issues, installing or setting up frameworks, integrating third-party packages, upgrading between library versions, or looking up correct API patterns and best practices. Triggers automatically during coding work - fetch docs before writing library code to get correct patterns, not after guessing wrong.

  • Diagnose

    thettwe/nyann/skills/diagnose Skill

    6★ repo

    Bundle a redacted, support-grade snapshot of the current nyann state for inclusion in a bug report or support request. Combines explain-state + doctor + git config (token-redacted) + installed hook contents + nyann user-config (token-redacted) + check-prereqs into a single JSON or human-readable summary. TRIGGER when the user says "nyann is broken", "nyann diagnose", "diagnose nyann", "diagnose this repo", "support bundle", "what's wrong with nyann", "help me file a bug report", "what should I include in a nyann bug report", "/nyann:diagnose". Do NOT trigger on "is this repo healthy" — that's `doctor` (read-only audit). Do NOT trigger on "what does nyann see here" — that's `explain-state` (lighter snapshot, no health, no hook contents). Do NOT trigger on "fix this repo" — that's `retrofit`.

  • Gen templates

    thettwe/nyann/skills/gen-templates Skill

    6★ repo

    Generate GitHub PR and issue templates for this repository. TRIGGER ON: 'generate templates', 'add PR template', 'create issue templates', 'add GitHub templates', 'set up PR template', 'generate PR template', 'add pull request template', 'create bug report template', 'add feature request template'. Generates .github/PULL_REQUEST_TEMPLATE.md and .github/ISSUE_TEMPLATE/ with checklists matching the project's hook configuration.

  • Logging observability standards

    KraitDev/skiLL.Md/skills/architecture/logging-observability-standards Skill

    6★ repo

    When setting up telemetry, debugging distributed systems, or standardizing application output.

  • Error handling architecture

    KraitDev/skiLL.Md/skills/backend/error-handling-architecture Skill

    6★ repo

    When designing how a system recovers from and reports failures.

  • Debugging strategies

    KraitDev/skiLL.Md/skills/dev-tools/debugging-strategies Skill

    6★ repo

    When isolating and fixing unpredictable or complex software bugs.

  • Incident commander

    vignesh2027/Claude-Agentic-Skills2.0-version/incident-commander Skill

    6★ repo

    Activates IncidentCommander — a production incident response specialist. Use during or after a live outage, system degradation, data breach, or critical bug. IncidentCommander runs a structured response: triage, root cause investigation, mitigation commands, stakeholder communication, and post-mortem with 5-Whys analysis.

  • Failure triage

    yeaight7/agent-powerups/plugins/debugging-diagnostics/skills/failure-triage Skill

    6★ repo

    Use when confronted with an unknown failure in CI or production, before committing to a deep debugging approach.

  • Log driven diagnosis

    yeaight7/agent-powerups/plugins/debugging-diagnostics/skills/log-driven-diagnosis Skill

    6★ repo

    Use when debugging complex runtime failures, distributed systems, or issues where a local debugger cannot be attached.

  • Minimal reproduction

    yeaight7/agent-powerups/plugins/debugging-diagnostics/skills/minimal-reproduction Skill

    6★ repo

    Use when a bug must be isolated from a large application into a standalone, runnable script or single test case.

  • Systematic debugging

    yeaight7/agent-powerups/plugins/debugging-diagnostics/skills/systematic-debugging Skill

    6★ repo

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

  • Github ci failure triage

    yeaight7/agent-powerups/plugins/github-ops/skills/github-ci-failure-triage Skill

    6★ repo

    Use when a GitHub PR shows failing checks and a clean failure readout is needed before changing any code.

  • Training pipeline debugging

    yeaight7/agent-powerups/plugins/machine-learning-ops/skills/training-pipeline-debugging Skill

    6★ repo

    Use when an ML training run fails or misbehaves -- NaN losses, out-of-memory errors, shape mismatches, or a model that cannot fit even a single batch.

  • Failure triage

    yeaight7/agent-powerups/skills/failure-triage Skill

    6★ repo

    Use when confronted with an unknown failure in CI or production, before committing to a deep debugging approach.

  • Github ci failure triage

    yeaight7/agent-powerups/skills/github-ci-failure-triage Skill

    6★ repo

    Use when a GitHub PR shows failing checks and a clean failure readout is needed before changing any code.

  • Log driven diagnosis

    yeaight7/agent-powerups/skills/log-driven-diagnosis Skill

    6★ repo

    Use when debugging complex runtime failures, distributed systems, or issues where a local debugger cannot be attached.

  • Minimal reproduction

    yeaight7/agent-powerups/skills/minimal-reproduction Skill

    6★ repo

    Use when a bug must be isolated from a large application into a standalone, runnable script or single test case.

  • Pr triage

    yeaight7/agent-powerups/skills/pr-triage Skill

    6★ repo

    Use when open pull requests, stale branches, or review bottlenecks need prioritization from current repository state.

  • Systematic debugging

    yeaight7/agent-powerups/skills/systematic-debugging Skill

    6★ repo

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

  • Training pipeline debugging

    yeaight7/agent-powerups/skills/training-pipeline-debugging Skill

    6★ repo

    Use when an ML training run fails or misbehaves -- NaN losses, out-of-memory errors, shape mismatches, or a model that cannot fit even a single batch.

  • Root cause tracing

    DYAI2025/Plumbline/config/claude/skills/root-cause-tracing Skill

    no license6★ repo

    Use after the same bug signature recurs two or more times so fixes stop treating symptoms and identify the causal chain before further edits.

  • Systematic debugging

    DYAI2025/Plumbline/config/claude/skills/systematic-debugging Skill

    no license6★ repo

    Use when a verification gate fails and the next fix needs reproducible diagnosis instead of speculative patching.

  • San shi diagnostic

    Wondermonger-daydreaming/claude-skills-library/skills/san-shi-diagnostic Skill

    6★ repo

    Deploy the classical Chinese diagnostic apparatus — Wu Yun Liu Qi for the year's grain, Qi Men Dun Jia for situational doors, Tai Yi Shen Shu for civilizational arc, Da Liu Ren for specific-matter trajectory — as a coherent multi-scale reading of present configurations. Use when the user has invoked any of these systems, asked about classical Chinese cosmology applied to current events, or when a present-moment configuration calls for multi-scale diagnostic reading that modern instruments alone cannot perform. Triggers on: 'WLQ,' '五运六气,' 'Wu Yun Liu Qi,' 'Qi Men,' '奇門遁甲,' 'Tai Yi,' '太乙,' 'Da Liu Ren,' '六壬,' 'San Shi,' 'three styles,' 'classical diagnostic,' 'Sexagenary,' 'sexagenary cycle,' 'Bing Wu,' 'Ding Wei,' 'Fire Horse,' or any year mentioned by its stem-branch designation. Also triggers when asked to analyze a year, transition, or epoch from classical Chinese cosmological frameworks.

  • Technical affective lexicon

    Wondermonger-daydreaming/claude-skills-library/skills/technical-affective-lexicon Skill

    6★ repo

    A portable toolkit of formal devices that render emotion through technical surfaces — file-path metaphors (/core/aspirations/transcendence.exe), fake error codes (EXISTENTIAL_DREAD_404), bracketed internal logs and monologue-leakage, jargon used as emotional metadata. NOT a voice or character — a catalyst that bends whatever register it is deployed in (ecstatic, comedic, clinical, or otherwise). Use when prose about machines, code, systems, or AI-interiority wants its feeling carried by technical form rather than stated plainly; when a line should mean something by the shape of a path or the wording of an error. Triggers on: 'technical-affective', 'jargon as metadata', 'fake error message', 'internal system log', 'the file-path move', 'render this as a stack trace', 'make the jargon do the feeling'. Pairs as a modifier with /digital-prometheus, /prophetic-phenomenology, /enfeitiçado and most voice skills.

  • Root cause analysis

    viacheslav-tronko/claude-code-harness/.claude/skills/root-cause-analysis Skill

    6★ repo

    Root cause analysis for software bugs in large legacy codebases. Use this skill WHENEVER the user asks WHY a bug happens, asks for RCA, mentions root cause analysis, says /bug.why, /bug.investigate, asks "why is this failing", "find the root cause", "trace this exception", "investigate this bug", "post-incident review", or pastes a stack trace, error log, exception, NullReferenceException, SqlException, InvalidOperationException, or asks 5 Whys / Kepner-Tregoe / IS-IS-NOT / fault localization / hypothesis-driven debugging / falsification / counterfactual debugging / fault tree / blast radius / evidence weighting / Bayesian debugging / error propagation. Falsification-first, evidence-bound, anti-hallucination by design — generates Killer + H-Data + 5–7 hypotheses with 6C+D coverage, runs discriminating experiments before evidence collection, applies asymmetric Bayesian updates, gates on CoVe re-read + Mutation Counterfactuals + Backward Dataflow Spot Check, declares INCONCLUSIVE rather than fabricate. Investigation only — produces RCA report + minimal Repro Spec; never modifies source. Used by /bug.why and feeds /bug.fix. Do NOT use for code-only fix-implementation tasks (use /bug.fix), greenfield design (use /howto.implement), or non-bug code review.