Debug & triage
5,138 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
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/diagnosing-bugs Skill
0★ 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 2 other repositories
Distributed debugging debug trace
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/distributed-debugging-debug-trace Skill
0★ repoYou are a debugging expert specializing in setting up comprehensive debugging environments, distributed tracing, and diagnostic tools. Configure debugging workflows, implement tracing solutions, and establish troubleshooting practices for development and production environments.
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/gdb-cli Skill
0★ repoGDB debugging assistant for AI agents - analyze core dumps, debug live processes, investigate crashes and deadlocks with source code correlation
The same file is in 5 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/inbox-triage Skill
0★ repoRuns a full inbox triage using the knowledge base created by the 'inbox-setup' skill. Light-intake by design (most invocations skip questions and run with KB-default preferences); asks at most 2 grill-me override questions when invocation is outside normal cadence or includes category-skip intent. Searches recent emails, classifies them via the user's taxonomy, researches new senders, generates recommendations, drafts replies (NEVER sends), delivers a report in the user's preferred format, and updates the knowledge base with learnings. Designed to run on a recurring schedule (1-3x daily) or on demand. Use when the user wants their inbox processed, in any variation (e.g., 'triage my inbox', 'inbox triage', 'check my email', 'run email triage', 'process my inbox', 'what's new in my email', 'handle my email', 'email triage'). Requires the inbox-setup skill to have been run first.
The same file is in 2 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/incident-response-smart-fix Skill
0★ repo[Extended thinking: This workflow implements a sophisticated debugging and resolution pipeline that leverages AI-assisted debugging tools and observability platforms to systematically diagnose and res
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Development/ios-debugger-agent Skill
0★ repoDebug the current iOS project on a booted simulator with XcodeBuildMCP.
The same file is in 4 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Marketing/analytics-tracking Skill
0★ repoSet up, audit, and debug analytics tracking implementation — GA4, Google Tag Manager, event taxonomy, conversion tracking, and data quality. Use when building a tracking plan from scratch, auditing existing analytics for gaps or errors, debugging missing events, or setting up GTM. Trigger keywords: GA4 setup, Google Tag Manager, GTM, event tracking, analytics implementation, conversion tracking, tracking plan, event taxonomy, custom dimensions, UTM tracking, analytics audit, missing events, tracking broken. NOT for analyzing marketing campaign data — use campaign-analytics for that. NOT for BI dashboards — use product-analytics for in-product event analysis.
The same file is in 2 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Product/error-debugging-error-trace Skill
0★ repoYou are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up error tracking systems, configure alerts, implement structured logging, and ensure teams can quickly identify and resolve production issues.
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Product/error-diagnostics-error-trace Skill
0★ repoYou are an error tracking and observability expert specializing in implementing comprehensive error monitoring solutions. Set up error tracking systems, configure alerts, implement structured logging,
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Productivity/datadog-automation Skill
0★ repoAutomate Datadog tasks via Rube MCP (Composio): query metrics, search logs, manage monitors/dashboards, create events and downtimes. Always search tools first for current schemas.
The same file is in 7 other repositories
Error debugging error analysis
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Research/error-debugging-error-analysis Skill
0★ repoYou are an expert error analysis specialist with deep expertise in debugging distributed systems, analyzing production incidents, and implementing comprehensive observability solutions.
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Research/error-handling-patterns Skill
0★ repoBuild resilient applications with robust error handling strategies that gracefully handle failures and provide excellent debugging experiences.
The same file is in 6 other repositories
srg-sphynx/MDForge/Sources/MDForge/Resources/SkillLibrary/Research/github-issue-creator Skill
0★ repoTurn error logs, screenshots, voice notes, and rough bug reports into crisp, developer-ready GitHub issues with repro steps, impact, and evidence.
The same file is in 7 other repositories
deessejs/skills/skills/diagnosing-bugs Skill
no license0★ repoDiagnose a GitHub issue to find the root cause, document findings, and prepare the issue for triage. Use when asked to "diagnose #N", "investigate bug #N", or "find the root cause of #N".
deessejs/skills/skills/triage Skill
no license0★ repoTriage a GitHub issue — verify, deduplicate, assess, categorize, prioritize, escalate if needed, post a structured review comment.
nledford/engineering-review-board/skills/observability-engineering Skill
0★ repoObservability, telemetry, and production diagnostics guidance. Use when designing, adding, reviewing, or testing structured logs, metrics, traces, span/context propagation, correlation or request IDs, sampling, labels/cardinality, dashboards, alerts, SLO/SLI/error-budget signals, OpenTelemetry/Prometheus/Grafana/Datadog-style instrumentation, operational runbooks, or incident visibility. Do not use for ordinary language implementation, active debugging without durable instrumentation changes, security review except telemetry leakage or audit controls, BDD/TDD mechanics, or documentation-only edits; load those existing skills instead or alongside this skill when their trigger is primary.
nledford/engineering-review-board/skills/root-cause-analysis Skill
0★ repoStructured root-cause analysis for recurring failures, incidents, regressions, systemic process gaps, and postmortem-style prevention work. Use after the direct cause of a current symptom is understood; use systematic-debugging first for active failing tests, crashes, or unknown immediate causes.
nledford/engineering-review-board/skills/systematic-debugging Skill
0★ repoEvidence-driven debugging for active bugs, failing tests, runtime exceptions, flaky behavior, performance regressions, build/lint/type/compile failures, integration failures, crashes, and unexpected behavior. Use before proposing fixes for a current symptom. Use root-cause-analysis for recurring incidents, systemic failures, and postmortem-style prevention work.
Superpowers systematic debugging
host452b/polish/skills/superpowers-systematic-debugging Skill
no license0★ repoUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
381487190/opengod/skills/real-engineering/engineering/diagnosing-bugs Skill
0★ 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
381487190/opengod/skills/real-engineering/engineering/triage Skill
0★ 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
381487190/opengod/skills/seedance/seedance-troubleshoot Skill
0★ repoThis skill should be used when a Seedance 2.0 output is blurry, jittery, off-prompt, morphing, blocked, visually generic, unstable, desynced, inconsistent, or otherwise fails and needs root-cause diagnosis.
matematicsolutions/awesome-matematic-skills-en/eu-law-sources/skills/authority-triage-en Skill
0★ repoEnglish hub of method-neutral legal AI skills (verification core, content quality, EU law) - bundle model. Polish-jurisdiction skills live in awesome-matematic-skills-pl.
Sarmkadan/dotnet-senior-skills/skills/logging-and-observability Skill
0★ repoReview .NET logging and observability - structured logging discipline, log levels, what not to log, correlation, exception logging, and metrics/tracing hooks. Use when reviewing ILogger usage, log statements, or diagnostics code.
Tsurai7/agentic-playbook/skills/systematic-debugging Skill
0★ repoSystematic root-cause debugging: investigate before fixing, log hypotheses, trace data flow, and stop to reassess after 3 failed fix attempts. Use when debugging a non-obvious failure, when a fix attempt did not work, or when asked to find a root cause. Skip for trivial errors whose cause is stated in the error message.
kalepail/skills/skills/solo-troubleshoot Skill
0★ repoDiagnose Solo project, command, terminal, service, CLI, shell, version-manager, trust, solo.yml sync, working-directory, execution-profile, WSL, restart-loop, output, port, and readiness failures. Use when tooling is missing, commands fail, YAML changes do not apply, status disagrees, or services never become ready. Do not use for routine status views or authorized routine start, stop, and restart.
ballisarium/aiogram-bot-skills/skills/telegram-debugging Skill
0★ repouse when diagnosing or fixing a telegram or aiogram bot bug; баг, не работает, handler missing, filters, callbacks, stuck FSM, edit, webhook, API errors.
Pdbjork/hermosskills-site/skills/ce-debug Skill
no license0★ repoDiagnosis loop for bugs and failing behavior. Use for errors, stack traces, regressions, failed tests, issue-tracker bugs, stuck investigations after failed fixes, or asks to debug/fix a bug.
The same file is in 1 other repository
Ecc agent introspection debugging
Pdbjork/hermosskills-site/skills/ecc-agent-introspection-debugging Skill
no license0★ repoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
The same file is in 1 other repository
gulmezeren2-byte/industrial-engineering-ai-skills/skills/root-cause-pareto Skill
0★ repoBuild a decision-grade Pareto for downtime, defects, complaints or delays - with unit-of-measure discipline, category hygiene, exposure normalization and a follow-up metric. Use when the user mentions pareto analysis, kök neden, duruş analizi, downtime, arıza analizi, defect ranking, şikayet analizi, 80/20 analysis. Differentiator - treats the Pareto as the start of a causal investigation, not a bar chart deliverable.
ZC0325/sol-native-guardrails/plugins/sol-native-guardrails/skills/systematic-debugging Skill
0★ repoDiagnose reproducible bugs, failing tests, performance regressions, integration failures, or unexplained behavior that requires evidence and root-cause tracing before a reliable fix. Use for nontrivial technical failures; use a direct fast path when the cause is already demonstrated and local.
CodeSigils/py-review-skill/skills/py-error-handling Skill
no license0★ repoReview Python code for error-handling issues including missing boundary validation, generic exceptions, swallowed failures, missing exception chaining, partial batch failure handling, and cleanup behavior. Use when reviewing validation logic, exception paths, retries, file/network operations, or batch processing.
jcdavis131/cursor-agent-skills/skills/background-failure-triage Skill
0★ repoWhen a backgrounded command fails while the foreground lane is making progress, do not abort the foreground lane — log the failure, queue it for triage, and continue. Triage the failure at the next natural boundary. Use whenever a background shell task, background subagent, or parallel lane fails while you're mid-task on something independent.
jcdavis131/cursor-agent-skills/skills/diagnose-before-retry Skill
0★ repoWhen an operation fails, form a hypothesis from the logs/evidence before retrying — never retry blindly. Distinguish op-caused failures from self-caused artifacts (your own stops/kills), state the hypothesis with supporting context and appropriate uncertainty, and retry in the foreground with a timeout and observability so the retry is also a test of the hypothesis. Use when a long command (migrate, build, install, deploy, fetch) fails and you're tempted to just re-run it.
incuca/incuca-ads/skills/ads-server-side-tracking Skill
0★ repoServer-side tracking pipeline audit covering server-side Google Tag Manager (sGTM), Meta CAPI Gateway, Conversions API health, event deduplication via event_id, server-side hit ratio targets, pixel debugging, and PII hashing discipline. Use when user says server-side tracking, sGTM, server-side GTM, server-side tagging, CAPI, Conversions API, CAPI Gateway, Meta Conversions API, event deduplication, event_id, pixel debug, pixel health, Pixel/CAPI audit, first-party tracking, iOS 14.5 recovery, or server-side hit ratio.
vaibhavsaxena022/skills/debug-systematically Skill
0★ repoFind and fix a bug by root cause, not by guessing. Use when given a bug report, stack trace, or failing behavior. Follows reproduce → isolate → root-cause → fix → verify → add a regression test.
vaibhavsaxena022/skills/observability Skill
0★ repoAdd production observability to a service. Use when a service is hard to debug in prod or lacks logging/metrics/tracing. Adds structured logs, key metrics, and trace context — without noise.
SamyakJhaveri/loam/cultivation/marketplace/pocock-engineering/skills/diagnose Skill
0★ 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.
SamyakJhaveri/loam/cultivation/marketplace/pocock-engineering/skills/triage Skill
0★ 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.
ats4321/claude-engineering-skills/skills/debugging-playbook Skill
0★ repoSystematic debugging for ANY stack. Auto-load on any bug, test failure, crash, hang, wrong output, flaky behavior, or "why isn't this working". Enforces reproduce → isolate → hypothesize → test ONE variable → verify root cause. Covers reading error messages in full, binary-search isolation (git bisect, commenting out, minimal repro), distinguishing environment vs code vs dependency failures, and recognizing when a framework abstraction is itself the bug (drop to primitives). Trigger keywords: bug, error, exception, traceback, stack trace, crash, hang, fails, broken, "not working", flaky, regression, "worked yesterday", debug, troubleshoot.
ats4321/claude-engineering-skills/skills/observability-and-diagnostics Skill
0★ repoMake systems diagnosable BEFORE they fail — structured logging, honest levels, actionable errors, surfaced skips, and reconstructable runs. Auto-load when adding or reviewing logging, error messages, metrics, or health checks; when a production/runtime failure could not be diagnosed from available output; when asked "add logging" or "why can't we tell what happened"; or when designing what a long-running job or agent should record. NOT for diagnosing a live failure (debugging-playbook — this skill provides the evidence that playbook consumes) and NOT for measuring speed (performance-engineering).
kulapoo/opencode-agent-harness/.opencode/skills/debugging-and-error-recovery Skill
0★ repoGuides 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.
ceilidhboy/skills/skills/pest-testing-conventions Skill
0★ repoPest 4 testing conventions, workflows, and troubleshooting for Laravel projects. Activates when writing or debugging tests, working with browser/smoke/architecture tests, handling test output issues (PAO mode, crash diagnostics), setting up datasets or mocking, and following project conventions for assertions, higher-order expectations, and test organization.
ceilidhboy/skills/skills/troubleshooting-backend Skill
0★ repoTroubleshooting Laravel, PHP, and backend-related errors.
ceilidhboy/skills/skills/troubleshooting-frontend Skill
0★ repoTroubleshooting TypeScript, React, and frontend-related errors.
ceilidhboy/skills/skills/troubleshooting Skill
0★ repoGeneral troubleshooting guidance that routes to specific backend or frontend troubleshooting skills.
ChrisLamDev/cocos-creator-debug-skills/skills/cocos-creator-cli-build-debug Skill
0★ repoUse when Cocos Creator 3.x CLI build fails with scene or library errors.
Cocos creator install and debug
ChrisLamDev/cocos-creator-debug-skills/skills/cocos-creator-install-and-debug Skill
0★ repoUse when installing Cocos Creator 3.x and debugging scene import errors.
ChrisLamDev/cocos-creator-debug-skills/skills/cocos-gray-screen-debug-flow Skill
0★ repoUse when Cocos Creator 3.x shows gray or black screen in Preview mode.
IcodeNet/agent-skills/skills/debug Skill
0★ repoSystematic stop-the-line root-cause debugging for deterministic failures with a clear signal: a failing test, broken build, readable stack trace, or a reliably reproducible behavior mismatch. Do not use for greenfield feature work, live production outages (use incident-response), or hard, intermittent, or performance bugs that need a constructed feedback loop (use diagnose).
IcodeNet/agent-skills/skills/diagnose Skill
0★ repoDisciplined diagnosis loop for hard bugs — intermittent, non-deterministic, environment-dependent, or performance regressions — where the first step is constructing a reliable feedback loop. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when the user says "diagnose this", when a bug resists a simple repro, is flaky or timing-dependent, or when a performance regression needs measurement. For deterministic failures with a clear signal (failing test, build break, readable stack trace), use debug instead.
IcodeNet/agent-skills/skills/testing-strategy Skill
0★ repoDesigns test coverage plans and verification gates. Use when writing tests, planning coverage, asking how to test a change, or designing a test plan before implementation. Do not use for red-green-refactor implementation loops (use tdd) or stop-the-line failure triage (use debug).
IcodeNet/agent-skills/skills/triage Skill
0★ 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 1 other repository
shinzoxD/knackbox/skills/coding/debugging Skill
0★ repoDiagnose bugs systematically instead of guessing — form hypotheses, isolate the fault, and verify the fix. Use whenever the user shares an error message, stack trace, unexpected behavior, failing test, or says things like "why doesn't this work", "it crashes", or "I'm stuck on this bug" — even if they only paste an error with no question.
shinzoxD/knackbox/skills/coding/error-handling Skill
0★ repoDesign robust error handling, retries, and failure modes for application code. Use whenever the user asks about exceptions, error types, retry policies, circuit breakers, timeouts, or how to handle failures in APIs, jobs, and distributed calls.
shinzoxD/knackbox/skills/coding/logging-observability Skill
0★ repoDesign logging, metrics, and tracing that operators can use under pressure. Use whenever the user asks about structured logs, metrics, OpenTelemetry, dashboards, SLIs/SLOs, alerting, or how to instrument a service for production debugging.
shinzoxD/knackbox/skills/documents/incident-postmortems Skill
0★ repoWrite blameless incident postmortems with timeline, impact, root cause, and action items. Use whenever the user asks for a postmortem, RCA, incident write-up, outage report, or lessons learned after a production failure — even from rough Slack notes or pager logs.
shinzoxD/knackbox/skills/productivity/issue-triage Skill
0★ repoTriage bugs and tickets with severity, repro steps, and next actions. Use whenever the user asks to triage issues, prioritize a backlog of bugs, rewrite a bug report, classify severity, or clean up noisy tickets — even from messy Slack reports.
shinzoxD/knackbox/skills/productivity/oss-maintainer-triage Skill
0★ repoTriage open-source issues and PRs with labels, reproduction asks, and maintainer-friendly replies. Use whenever the user maintains a public repo and needs issue triage, good-first-issue labeling, incomplete bug report replies, or PR intake for an open-source project.
knownasnaffy/prompthound/dataset/case_00009 Skill
no license0★ repoGenerate and edit images with a bundled Gemini native image-generation CLI. Use when the user asks Codex to create images with Gemini, use Gemini image generation through a local bash CLI, run or debug Gemini image curl requests, choose Gemini image models/sizes/aspect ratios, inspect raw image-generation responses, or troubleshoot slow, timed-out, or failed Gemini image requests.