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
eugenelim/agent-ready-repo/packs/atlassian/.apm/skills/jira-story-triage Skill
31★ repoReview Jira work items for readiness and improve weak stories using the pack's five-question bar — it explains why each item is not ready (which question failed and the specific gap), drafts the fix, and writes to Jira only after you approve the exact payload; read-only until then. Triggers on "which stories are not ready for engineering", "clean up the weak items in the backlog", "make these tickets actionable", "draft acceptance criteria for the top five", "apply the five-question bar", "show me what is missing before changing Jira", "which tickets aren't ready to ship", "triage the backlog for actionability". Do NOT use for a read-only team status snapshot or what to pick up next / blocked / unassigned / in progress / stand-up (use jira-team-status), to create an issue (use jira), to turn an epic into specs (use jira-brief-intake), or to fix a defect end-to-end (use jira-defect-flow).
NickCrew/Claude-Cortex/skills/atomic-commits Skill
30★ repoUse this skill when a working tree contains uncommitted changes that need to be split into a sequence of atomic commits — typically after a long session, an agent hand-off, a rebase resolution, or anytime `git status` shows mixed work that was not committed as it landed. The skill assumes the agent has fresh context and did not author most of the diff, so it treats the working tree as evidence to investigate before grouping. Optimizes for `git bisect`: each commit is the smallest buildable and deployable unit, and no smaller. Uses `cortex git commit` for file-level commits and `cortex git patch --diff` when unrelated changes share a file.
NickCrew/Claude-Cortex/skills/root-cause-tracing Skill
30★ repoUse when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior
NickCrew/Claude-Cortex/skills/systematic-debugging Skill
30★ repoUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
AnthonyAlcaraz/agentic-graph-rag-skills/skills/memory/letta-failure-modes Skill
30★ repoReviewer skill: diagnose an agent's memory architecture against the 8 Letta Leaderboard failure modes (Ch4). Takes a memory snapshot (or a description of the architecture) and reports which failure modes are present, with concrete evidence and recommended fixes. Use BEFORE shipping any memory implementation to production and BEFORE root-causing why a deployed agent "forgets" or "drifts." NOT a benchmark (does not produce a single accuracy number), NOT a substitute for production observability (this is a static diagnostic, not a runtime monitor).
tt-a1i/matt-skills-with-to-goal/skills/diagnosing-bugs Skill
30★ repoDiagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
The same file is in 17 other repositories
tt-a1i/matt-skills-with-to-goal/skills/triage Skill
30★ repoMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.
The same file is in 13 other repositories
saeed-vayghan/gemini-agent-skills/.gemini/skills/debugger Skill
30★ repoExpert debugger specializing in complex issue diagnosis, root cause analysis, and systematic problem-solving. Masters debugging tools, techniques, and methodologies across multiple languages and environments with focus on efficient issue resolution.
shinpr/codex-workflows/.agents/skills/recipe-diagnose Skill
30★ repoInvestigate problem, verify findings, and derive solutions through structured diagnosis.
Superpowers systematic debugging
ItamarZand88/awesome-agent-conventions/conventions/skill-md/examples/dev-tooling/superpowers-systematic-debugging Skill
30★ repoA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.txt, MCP configs, rules, and examples.
ItamarZand88/awesome-agent-conventions/conventions/skill-md/examples/dev-tooling/wshobson-debugging-strategies Skill
30★ repoA curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.txt, MCP configs, rules, and examples.
mcparmory/registry/com.mcparmory/datadog MCP server
no license30★ repoMonitor infrastructure, manage agents and deployments, track metrics, logs, and events
mcparmory/registry/com.mcparmory/sentry MCP server
no license30★ repoTrack errors, manage performance alerts, and configure dashboards and monitors
inngest/inngest-skills/skills/inngest-middleware Skill
no license29★ repoUse when adding cross-cutting concerns to durable functions — structured logging or tracing across all functions, error tracking with Sentry, payload encryption for sensitive data, dependency injection of clients (DB, Stripe, etc.) into function handlers, custom telemetry, or behavior that should apply uniformly across many functions. Covers Inngest middleware lifecycle, creating custom middleware, dependencyInjectionMiddleware, @inngest/middleware-encryption, @inngest/middleware-sentry, and custom middleware patterns.
The same file is in 12 other repositories
mralaminahamed/wp-dev-skills/skills/wp-database Skill
29★ repoUse when a WordPress plugin needs a custom database table — creating with dbDelta (strict SQL format: two spaces before PRIMARY KEY, no trailing comma), writing versioned upgrade routines with version_compare and register_activation_hook, querying with $wpdb prepared statements (prepare, insert, update, delete, get_row, get_results, get_var), debugging with $wpdb->last_error or SAVEQUERIES, schema migrations between plugin versions, uninstall cleanup, multisite table handling with switch_to_blog / get_sites, or seeding test/preview data into custom tables. Triggers: "create a custom table", "dbDelta not working", "dbDelta not creating my table", "write a migration", "wpdb query", "wpdb prepare", "slow query on my custom table", "upgrade my database schema", "add a column to my table", "seed test data", "how do I store this in a custom table", "database upgrade routine", "table not being created on activation", "prepare placeholder wrong", "last_error is empty after query", "SAVEQUERIES debug", "version_compare for db upgrade", "register_activation_hook table", "wpdb prefix table name", "uninstall drops table", "multisite per-site table", "charset_collate missing". Not for: WordPress options API or post meta — use those when a custom table is not needed.
pimenov/codex-first-skills-pack/skills/debugging-and-error-recovery Skill
no license29★ repoGuides systematic root-cause debugging and recovery instead of guessing fixes. Use when tests fail, builds break, commands error, logs or consoles show errors, runtime behavior differs from expectation, a bug is reported, a prior fix did not work, CI/deploy/smoke checks fail, or something worked before and stopped working. Also use when Codex encounters an unexpected tool, package, API, network, infrastructure, or vendor error during a task.
sanky369/vibe-building-skills/skills/frontend-design/error-handling-recovery Skill
29★ repoAudit and implement an app's error UX end-to-end: rewrite error messages, place them correctly, add recovery actions, and build error states for validation, network, permission, system, and 404 failures. Use when the user says 'improve my error handling', 'my error messages suck', 'users get stuck when something fails', 'add form validation errors', 'handle offline/network errors', 'design a 404 page', or when a review finds bare 'Something went wrong' strings, silent failures, or errors with no way forward. Produces an error-state matrix (every failure mode × message × recovery action) plus the implemented error components and copy.
easyzoom/aix-skills/skills/bootloader-debug Skill
28★ repoUse when debugging embedded bootloaders, application jumps, vector table offsets, firmware upgrade flow, OTA state, image validation, rollback, or boot selection failures
easyzoom/aix-skills/skills/cortex-m-debug Skill
28★ repoUse when debugging Cortex-M microcontrollers, firmware bring-up, SWD/JTAG sessions, faults, startup code, or flashing failures
easyzoom/aix-skills/skills/cortex-r5-debug Skill
28★ repoUse when debugging Cortex-R5 or Cortex-R firmware — TCM, MPU, caches, DFSR/DFAR aborts, exceptions, GIC/VIC interrupts, lockstep or split mode, ECC, or JTAG bring-up
easyzoom/aix-skills/skills/embedded-debug-entry Skill
28★ repoUse when triaging embedded device, MCU, firmware, board bring-up, flashing, serial log, RTOS, bootloader, low-power, or peripheral debug requests
easyzoom/aix-skills/skills/embedded-fault-debug Skill
28★ repoUse when embedded firmware crashes, traps, faults, resets unexpectedly, jumps to default handlers, corrupts stack, or executes invalid instructions
easyzoom/aix-skills/skills/embedded-linux-login-debug Skill
28★ repoUse when logging into, connecting to, or preparing to debug an embedded Linux device
easyzoom/aix-skills/skills/embedded-serial-log-debug Skill
28★ repoUse when collecting or debugging embedded serial UART logs, boot consoles,乱码, missing output, baud-rate issues, or serial terminal access
easyzoom/aix-skills/skills/freertos-kernel-debug Skill
28★ repoUse when debugging FreeRTOS kernel behavior, task scheduling, priorities, stacks, heap schemes, tick interrupts, ISR APIs, queues, semaphores, timers, or deadlocks
easyzoom/aix-skills/skills/hardware-interface-debug Skill
28★ repoUse when debugging embedded board-level power, reset, clock, pin, connector, signal integrity, logic analyzer, oscilloscope, or hardware interface issues
easyzoom/aix-skills/skills/letter-shell-integration Skill
28★ repoUse when integrating, porting, configuring, or debugging letter-shell command shells, UART shell transport, command registration, RTOS shell tasks, or embedded debug consoles
easyzoom/aix-skills/skills/low-power-debug Skill
28★ repoUse when debugging embedded sleep, standby, deep sleep, wakeup, current consumption, clock gating, lost debug access, or low-power mode failures
inbharatai/claude-skills/skills/debug-helper Skill
28★ repoDiagnose and fix bugs systematically — error analysis, stack trace interpretation, root cause identification, and fix suggestions.
VoDaiLocz/kilo-kit-mcp/skills/engineering/diagnose Skill
28★ repoDisciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
The same file is in 21 other repositories
VoDaiLocz/kilo-kit-mcp/skills/engineering/triage Skill
28★ repoTriage issues through a state machine driven by triage roles. Use when user wants to create an issue, triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.
The same file is in 14 other repositories
VoDaiLocz/kilo-kit-mcp/skills/kilo-kit/debugging/root-cause Skill
28★ repoDeep 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
VoDaiLocz/kilo-kit-mcp/skills/kilo-kit/debugging/systematic Skill
28★ repoComprehensive 4-phase debugging methodology for complex bugs. Use for bugs that aren't immediately obvious or have resisted quick fixes. Keywords: bug, error, fix, debug, broken, crash, fail, exception
VoDaiLocz/kilo-kit-mcp/skills/problem-solving/root-cause-tracing Skill
28★ repoSystematically trace bugs backward through call stack to find original trigger
The same file is in 2 other repositories
VoDaiLocz/kilo-kit-mcp/skills/problem-solving/systematic-debugging Skill
28★ repoUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
The same file is in 30 other repositories
Dotnet testing test output logging
kevintsengtw/dotnet-testing-agent-skills/skills/dotnet-testing-test-output-logging Skill
28★ repoxUnit 測試輸出與記錄完整指南。當需要在 xUnit 測試中實作測試輸出、診斷記錄或 ILogger 替代品時使用。涵蓋 ITestOutputHelper 注入、AbstractLogger 模式、結構化輸出設計。包含 XUnitLogger、CompositeLogger、效能測試診斷工具實作。 Make sure to use this skill whenever the user mentions ITestOutputHelper, test output, test logging, XUnitLogger, AbstractLogger, or ILogger testing in xUnit, even if they don't explicitly ask for test output guidance. Keywords: ITestOutputHelper, ILogger testing, test output xunit, 測試輸出, 測試記錄, AbstractLogger, XUnitLogger, CompositeLogger, testOutputHelper.WriteLine, 測試診斷, logger mock, 測試日誌, 結構化輸出, Received().Log
The same file is in 3 other repositories
maxnorm/magento2-agent-skills/skills/magento-issue-debugger Skill
28★ repoSystematically investigates, diagnoses, and resolves complex Magento 2 technical problems. Use when debugging issues, investigating bugs, analyzing performance problems, resolving errors, or troubleshooting system failures. Masters log analysis, performance profiling, and root cause analysis.
The same file is in 3 other repositories
Diagnostic medical sonographer
wonsukchoi/domain-experts/roles/diagnostic-medical-sonographer Skill
27★ repoUse when a task needs the judgment of a Diagnostic Medical Sonographer — deciding whether a duplex, compression, or graded-compression ultrasound study is diagnostic versus technically limited, choosing when to interrupt a scanning protocol to escalate a real-time critical finding, setting scan technique and ALARA (TI/MI) parameters for a given exam type, or drafting the technical worksheet and preliminary findings a physician will interpret and sign.
wonsukchoi/domain-experts/roles/farm-equipment-mechanic Skill
27★ repoUse when a task needs the judgment of a Farm Equipment Mechanic — diagnosing an ECU fault code on a combine or tractor before swapping parts, pressure-testing a hydraulic circuit on a planter or sprayer, troubleshooting a PTO or ISOBUS/CAN-bus communication fault, triaging a harvest-season breakdown against dealer-only diagnostic tool access, or scoping a pre-season inspection program against in-season failure risk.
wonsukchoi/domain-experts/roles/logging-equipment-operator Skill
27★ repoUse when a task needs senior logging-equipment-operator judgment — matching a feller-buncher/skidder/forwarder system to a cutting block's slope and stand, sequencing machines to avoid a felling-vs-extraction bottleneck, deciding when winch-assist or cable yarding replaces ground-based equipment, handling a hung tree without leaving the cab, or reconciling machine-hour cost against delivered $/ton.
wonsukchoi/domain-experts/roles/mri-technologist Skill
27★ repoUse when a task needs the judgment of an ARRT(MR)-certified MRI technologist — screening a patient or implant for MR safety and zone entry, selecting or adjusting a pulse-sequence protocol against a diagnostic question and time budget, monitoring or predicting specific absorption rate (SAR) and gradient limits during a scan, judging gadolinium contrast eligibility against renal function, or troubleshooting a motion/artifact problem before images reach the radiologist. US practice default (ACR Manual on MR Safety, FDA/IEC SAR limits). A reasoning aid, not medical advice.
wonsukchoi/domain-experts/roles/quality-inspector-tester Skill
27★ repoUse when a task needs the judgment of a Quality Inspector, Tester, Sorter, or Weigher — classifying a defect's severity (critical/major/minor) and determining whether it overrides a lot's overall AQL sampling result, deciding whether a measurement system's gauge R&R is reliable enough to trust a borderline pass/fail call, or determining whether a disposition decision falls within your authority or needs escalation.
mjunaidca/mjs-agent-skills/.claude/skills/helm Skill
no license27★ repoProduction-grade Helm 4 chart development, release management, and debugging. This skill should be used when users ask to create Helm charts, deploy with Helm, manage releases (install/upgrade/rollback), push charts to OCI registries, debug failed deployments, configure chart dependencies, create umbrella charts, set up GitOps with ArgoCD/Flux, or troubleshoot Helm issues. Auto-detects from Dockerfile/code, generates production-hardened charts with library patterns. Complements kubernetes skill.
mjunaidca/mjs-agent-skills/.claude/skills/kubernetes Skill
no license27★ repoProduction-grade Kubernetes manifests and debugging for containerized applications. This skill should be used when users ask to deploy to Kubernetes, create K8s manifests, containerize for K8s, set up Deployments/Services/Jobs/StatefulSets/CronJobs, create namespaces with resource quotas, set up multi-team isolation, configure ResourceQuota/ LimitRange, secure with RBAC (ServiceAccount, Role, RoleBinding), configure init containers (model download, db wait, migrations), set up sidecars (logging, metrics), or debug pods (CrashLoopBackOff, logs, exec, describe, events). Auto-detects from Dockerfile/code, generates hardened manifests with educational comments. CKAD-aligned.
mjunaidca/mjs-agent-skills/.claude/skills/nextjs-devtools Skill
no license27★ repoNext.js development tooling via MCP. Inspect routes, components, build info, and debug Next.js apps. Use when working on Next.js applications, debugging routing, or inspecting app structure. NOT for general React or non-Next.js projects.
The same file is in 3 other repositories
mjunaidca/mjs-agent-skills/.claude/skills/systematic-debugging Skill
no license27★ repoSystematic methodology for debugging bugs, test failures, and unexpected behavior. Use when encountering any technical issue before proposing fixes. Covers root cause investigation, pattern analysis, hypothesis testing, and fix implementation. Use ESPECIALLY when under time pressure, "just one quick fix" seems obvious, or you've already tried multiple fixes. NOT for exploratory code reading.
mjunaidca/mjs-agent-skills/docs/taskflow-vault/skills/engineering/aks-deployment-troubleshooter Skill
no license27★ repoDiagnose and fix Kubernetes deployment failures, especially ImagePullBackOff, CrashLoopBackOff, and architecture mismatches. Battle-tested from 4-hour AKS debugging session with 10+ failure modes resolved.
Fearvox/multica-ultimate-workbench/skills/workbench-debug-investigate Skill
no license26★ repoRoot-cause investigation for bugs, regressions, suspicious runtime behavior, failed automations, and unexpected outcomes.
ptsilivis/autonomousguy/skills/debugging/embedded-debugging Skill
26★ repoSenior embedded debugging expert. Defaults to Classic AUTOSAR on ARM Cortex-M/R targets and operates in two modes: (1) Problem-report triage — take a field PR / bug ticket and produce symptom classification, affected-element mapping, ranked hypotheses, data-collection plan, and step-by-step investigation; (2) Targeted fault debugging — accept a specific fault signature (watchdog reset, HardFault, wrong output value, Dem event, stack overflow, AUTOSAR OS error, linker hang) and give concrete debugging steps with GDB/TRACE32 commands, code patterns to inspect, ranked root-cause candidates, and a minimal reproduction strategy. Covers AUTOSAR OS (EB Tresos, Vector) and common BSW/RTE failure modes. Handles Adaptive AUTOSAR when the input names POSIX/Linux/QNX, ara::, C++, segfault, core dump, or Execution Management. Returns decision-ready ranked hypotheses with a built-in self-check and can emit a self-contained HTML report under analysis/.
byerlikaya/claude-starter-kit/claude-starter/skills/observability Skill
26★ repoEnterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.
byerlikaya/claude-starter-kit/claude-starter/skills/systematic-debugging Skill
26★ repoEnterprise engineering workflow for Claude Code — not just prompts. AI agents that plan, build, audit, and ship with security gates, privacy checks, and approval-controlled commits. Safely adopt it into new or existing repositories.
byerlikaya/claude-starter-kit/plugin/skills/observability Skill
26★ repoStack-agnostic observability: structured logs, correlation ids, metrics and traces; no PII or secrets in logs. Makes a production issue traceable to why it happened. Trigger phrases: "observability", "structured logging", "structured log", "add a trace", "add a metric", "correlation id", "add logging"
byerlikaya/claude-starter-kit/plugin/skills/systematic-debugging Skill
26★ repoRoot-cause a bug before touching a fix: reproduce, isolate, form and test a hypothesis, confirm the cause, then fix and verify. Stops guess-driven patching. For persistent, intermittent, or "already tried a few things" bugs. Trigger phrases: "debug", "root cause", "why is this failing", "intermittent bug", "can't reproduce", "still broken"
nimadorostkar/Claude-Skills-collection/skills/development/debugging Skill
25★ repoUse when a bug's cause is unknown. Applies a hypothesis-driven method — reproduce, isolate, instrument, prove — instead of speculative edits, and covers profiler, debugger, and log-based investigation.
nimadorostkar/Claude-Skills-collection/skills/devops/network-troubleshooting Skill
25★ repoUse when diagnosing network failures: connection refused, timeouts, TLS errors, DNS problems, and intermittent failures. Covers layer-by-layer isolation and the tools that answer each question.
nimadorostkar/Claude-Skills-collection/skills/devops/observability Skill
25★ repoUse when instrumenting a system or when an incident cannot be diagnosed from existing telemetry. Covers structured logging, metrics, distributed tracing, SLOs, and alerts that are worth waking someone for.
Alibaba ticket triage escalation coordinator
Raishin/vanguard-frontier-agentic/skills/alibaba/alibaba-ticket-triage-escalation-coordinator Skill
25★ repoTriage Alibaba Cloud operational alerts, incidents, and support tickets — P0/P1/P2/P3 classification, Alibaba Cloud Support SLA enforcement, account manager escalation, DingTalk war room coordination, evidence collection from CloudMonitor and SLS, and safe escalation paths.
Aws ticket triage escalation coordinator
Raishin/vanguard-frontier-agentic/skills/aws/aws-ticket-triage-escalation-coordinator Skill
25★ repoTriage AWS tickets and alerts using priority, owner, evidence, incident context, escalation path, OpsCenter, health signals, and safe next steps. Prefer this for non-destructive request coordination and escalation; prefer deep domain skills for implementation or root-cause investigation.
Azure resource health incident triage
Raishin/vanguard-frontier-agentic/skills/azure/azure-resource-health-incident-triage Skill
25★ repoUse this skill for Azure Resource Health, Service Health, activity-log alert, and first-pass incident triage when the question is whether Azure platform health is part of the problem.
Dotnet observability otel review
Raishin/vanguard-frontier-agentic/skills/dotnet/dotnet-observability-otel-review Skill
25★ repoUse this skill when reviewing in-application OpenTelemetry wiring in an ASP.NET Core service — OpenTelemetry SDK registration, trace context propagation across service boundaries, structured logging, correlation and trace identifiers in logs, metrics instrumentation, trace sampling, the health-vs-readiness check distinction, and PII leakage into span attributes or log messages. Trigger when a user provides ASP.NET Core source (Program.cs, telemetry registration, logging configuration, instrumentation code) or sanitized appsettings, asks whether their telemetry is wired correctly, or wants to know why traces are missing or logs are uncorrelated. This skill reviews source and sanitized configuration statically; it never runs the app or contacts a telemetry backend.