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
MARUCIE/openclaw-foundry/web/public/packs/test-engineer/skills/test/vibe-debug Skill
1★ repoAutomated test-driven debugging pipeline. Replaces human-in-the-loop 'still broken' prompting with: write reproducing test -> self-loop with test feedback -> exit when green.
KKenny0/Taku/skills/debug Skill
no license1★ repoWhen the user reports a bug, crash, error, or anything that is broken or behaving unexpectedly, invoke this skill FIRST — before writing any code or proposing any fix. This skill is the mandatory entry point for ALL bug-fix tasks. The user expects you to investigate root cause systematically before fixing. Without this skill, you will likely fix the symptom instead of the cause, which is the #1 debugging failure mode. Use this skill whenever the user says anything like: "fix this bug", "crashes", "returns null", "500 error", "not working", "wrong result", "throws exception", "timeout", "silent failure", "was working yesterday", "broke after deploy", "sometimes fails", "only in production", "works locally but not in CI/staging", "CLI crashes", "config missing", "test fails", or describes any error/stack trace. Also: "调试", "找bug", "报错", "排查问题", "不工作了", "挂了", "崩了", "数据不对". Do NOT use for: lint fixes, dependency updates, adding features, refactoring, or any task that is NOT about fixing broken behavior.
anotherben/claude-enterprise-skills/skills/enterprise-debug Skill
1★ repo4-phase systematic debugging: investigate, blast radius scan, root cause identification, TDD fix. Finds root causes not symptoms. Blast radius scan catches sibling bugs. 3-fail circuit breaker prevents fix-forward loops. Use for any bug, test failure, or unexpected behavior.
The same file is in 2 other repositories
manastalukdar/ai-devstudio/skills/debug-root-cause Skill
1★ repoRoot cause analysis with dependency tracing and call stack analysis
manastalukdar/ai-devstudio/skills/debug-session Skill
1★ repoDocument debugging sessions with hypothesis tracking and knowledge base
manastalukdar/ai-devstudio/skills/debug-systematic Skill
1★ repoSystematic debugging workflow with hypothesis testing
manastalukdar/ai-devstudio/skills/git-bisect Skill
1★ repoAutomated git bisect for bug hunting with test script execution
manastalukdar/ai-devstudio/skills/issue-triage Skill
1★ repoDiscover, deduplicate, prioritize, and label incoming GitHub issues and discussions — produce a structured priority queue with one-line summaries and suggested labels. Designed to run with /loop 2h or on demand.
Observability and instrumentation
manastalukdar/ai-devstudio/skills/observability-and-instrumentation Skill
1★ repoInstrument code with structured logging, metrics, and OpenTelemetry tracing — define the on-call questions first, then work backward to the telemetry that answers them.
manastalukdar/ai-devstudio/skills/triage Skill
1★ repoMove issues through a state machine with category and state labels — classify as bug or enhancement, assign triage state, reproduce bugs, and track out-of-scope requests. Use when triaging GitHub issues, processing a backlog, or managing issue lifecycle.
kreek/consult/agents/.agents/skills/debugging Skill
1★ repoUse to debug failures, reproduce symptoms, isolate causes, inspect evidence, and fix bugs.
kreek/consult/agents/.agents/skills/error-handling Skill
1★ repoUse for error handling, error types, propagation, retries, user messages, and recovery.
kreek/consult/consult/skills/debugging Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/consult/skills/error-handling Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/plugin/skills/debugging Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
kreek/consult/plugin/skills/error-handling Skill
1★ repoEngineering quality focused skills for AI coding agents that keep humans in the loop.
iamjosuho/memOrb/skills/core/orbtrack-triage Skill
no license1★ repo整理 OrbTrack(收集區)並依 PARA 原則分類搬移筆記。觸發詞:整理 OrbTrack、處理 OrbTrack、整理收集區、分類筆記、歸檔、搬移筆記、清空收集箱、整理。
1marcelserrano/mscreative-skills/skills/oracle-diagnostic-lite Skill
no license1★ repoMini-diagnóstico estratégico grátis — a porta de entrada do Creative Oracle™. Roda 3-5 perguntas curtas sobre o negócio do usuário e devolve uma leitura de superfície: aponta EM QUE dimensão a tensão se concentra (quem você é pra quem, como você soa, por que compram, como você entrega) sem dizer como resolver. Termina com handoff explícito para o Diagnóstico Oracle completo — o motor pago que faz a leitura cruzada das quatro dimensões ao mesmo tempo. TRIGGERS: diagnóstico grátis, mini diagnóstico, self-assessment, me avalia, onde meu negócio trava, qual meu gargalo, o que está travando, raio-x do negócio, check-up estratégico, diagnóstico estratégico, oracle diagnostic, por onde começo, o que eu priorizo, qual meu maior problema, me dá um norte, diagnóstico rápido, avalia minha marca, avalia meu posicionamento, o que está errado no meu negócio, quero entender meu gargalo, leitura do oracle, testar o oracle, experimentar o oracle, amostra do oracle. Use SEMPRE que alguém pedir uma avaliação rápida ou gratuita do próprio negócio/marca, quiser descobrir onde está o gargalo estratégico, ou pedir uma amostra do Oracle — mesmo sem citar "diagnóstico". É a única entrada grátis do Oracle e ativa o funil isca→motor pago. NÃO use para diagnóstico profundo, plano de ação, reestruturação de posicionamento ou qualquer entrega que prescreva COMO resolver — isso é o motor pago, faça o handoff.
The same file is in 1 other repository
kalyvask/entrepreneurship-lessons/.claude/skills/ent-prompt-troubleshoot Skill
1★ repoHelp the user fix AI prompts that aren't working — generic output, hallucinated facts, instruction-ignoring, output that's too long/short, no actionable conclusions. Use when the user complains about AI giving "slop," when they say "this prompt isn't working," or when they're frustrated with generic AI output.
NafisRayan/100x-Agent-Toolkit/skills/systematic-debugging Skill
no license1★ repoUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
The same file is in 30 other repositories
imtiazrayhan/agentscamp-library/skills/structured-logging-designer Skill
1★ repoDesign a structured (JSON) logging strategy with a stable field schema, correlation-ID propagation, and a disciplined level policy — then migrate ad-hoc string logs toward it. Use when logs are unsearchable plain text, when debugging a request across services means grepping multiple log streams by hand, or when standing up logging for a new service.
gitgitWi/council-flow/skills/review-triage Skill
no license1★ repoMulti-LLM Plan and TDD flow
Gesondian/ai-collab-governance-skills/skills/owner-boundary-triage Skill
1★ repoUse when an AI must decide whether a failure belongs to a feature owner, shared capability owner, data owner, environment owner, or verifier.
simanam/theaiteam/team/skills/engineering/agent-introspection-debugging Skill
no license1★ repoStructured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.
The same file is in 5 other repositories
simanam/theaiteam/team/skills/engineering/systematic-debugging Skill
no license1★ repoUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
The same file is in 30 other repositories
iwritec0de/wp-dev/skills/wp-debugging Skill
1★ repoThis skill should be used when the user asks to 'debug a WordPress error', 'fix a white screen', 'debug a plugin conflict', 'fix a 500 error', 'debug WooCommerce', 'fix a REST API error', 'debug a hook issue', 'investigate a fatal error', or mentions 'WordPress debugging', 'WP_DEBUG', 'error log', 'WSOD', 'plugin conflict', 'PHP fatal error', 'wp-cli debug'. Provides systematic WordPress/PHP debugging methodology covering fatal errors, white screens, plugin conflicts, REST API issues, and WooCommerce problems.
iggmasterdev/badquality-lab/bug-triage-advisor Skill
1★ repoTriage a bug using a clear decision model: is it a defect or a feature/change request? should it be logged at all, or just discussed? fix now, later, or never? and which medium — defect tracker, task card, a failing test, or nothing? Use this whenever someone is deciding what to do with a bug, asks "should I log this", "is this a bug or a feature", "fix now or later", how to handle a defect found mid-iteration vs in regression vs in production, or how to set up a lightweight bug policy / zero-bug approach. It adapts to your team's policy if you provide one, and otherwise uses sensible defaults. Trigger even when the user just describes a bug and asks "what do I do with this".
iggmasterdev/badquality-lab/rca-prevention-facilitator/skills/rca-five-whys Skill
1★ repoDrives a 5 Whys root-cause dig on a critical bug down to a SYSTEMIC cause you can act on — a process or design gap, never "a person made a mistake." Use when running the Root-Cause step of a SEV1/rollback RCA session, when someone asks "why did this actually break", when a proposed root cause still reads like a symptom, or when a team stops digging too early. Rejects person-blame and symptom-stopping; prompts one more "why" until the answer is a gap in the system. Called by rca-session-facilitator; usable standalone.
iggmasterdev/badquality-lab/rca-prevention-facilitator/skills/rca-ishikawa Skill
1★ repoRuns an Ishikawa / fishbone contributing-factors sweep across five categories — Process · People · Tooling · Requirements · Environment — so an RCA doesn't tunnel on the single obvious cause. Use for the Contributing-factors step of a SEV1/rollback RCA session, when a root cause feels too simple, or when you want to check "what else made this more likely." Only records categories that actually apply; keeps "People" blameless (systemic conditions, not fault). Called by rca-session-facilitator; usable standalone.
iggmasterdev/badquality-lab/rca-prevention-facilitator/skills/rca-knowledge-grounding Skill
1★ repoOn request, states the established best-practice principle behind any RCA step (5 Whys, blameless framing, contributing factors, prevention design, the feedback loop), and always separates the PRINCIPLE (why the step is sound) from the APPLICATION (how it maps to your team's context). Use when a facilitator or team asks "why do we do this step", "what's the reasoning", "is this best practice", or wants the rationale behind a recommendation. Grounds only in principles it can stand behind — it never invents a source or a citation. Called by rca-session-facilitator; usable standalone.
iggmasterdev/badquality-lab/rca-prevention-facilitator/skills/rca-prevention-design Skill
1★ repoConverts a systemic root cause into EXACTLY ONE concrete, buildable guard — a test, validation, checklist item, or gate — with a named owner, a home ("where it lives"), and a build-now/follow-up call. Use for the Prevention step of a SEV1/rollback RCA session, when turning a root cause into a safeguard, or when a proposed prevention is vague ("be more careful", "review better"). Rejects wish-lists and unbuildable preventions; picks the single guard that kills the whole failure class. Called by rca-session-facilitator; usable standalone.
iggmasterdev/badquality-lab/rca-prevention-facilitator/skills/rca-record-writer Skill
1★ repoEmits the finished RCA + Prevention Record as a .md file in a fixed template, and enforces the record's done-bar: systemic root cause, exactly one concrete prevention, a failure-class tag, and the "fix is not Done until root cause + prevention exist" rule. Use to write or finalize an RCA + Prevention Record, to check a record is complete before closing a SEV1/rollback ticket, or to format captured RCA findings into the shippable artifact. Called by rca-session-facilitator; usable standalone.
iggmasterdev/badquality-lab/rca-prevention-facilitator/skills/rca-session-facilitator Skill
1★ repoOrchestrates a full Root-Cause + Prevention session end-to-end for a SEV1 or rollback, unaided: intake the incident (ticket, SEV, origin label) → drive 5 Whys to a systemic cause → sweep contributing factors → design exactly one prevention → write the .md Record. Keeps it blameless and timeboxed (~30–45 min) and adapts to any team while holding one shared format. Use when a team needs to run an RCA/postmortem on a critical bug, "do a root-cause session", or turn a SEV1/rollback into a written prevention record. Calls the rca-* sub-skills; grounds on demand.
mehtab78/skills/skills/clients Skill
1★ repoUse to build and maintain a personal client system, one organized place per client for contacts, project history, documents (contracts, invoices, proposals), communication logs, preferences, and a leads pipeline. Trigger when the user mentions tracking a client, "pull up context on X before my call", logging a meeting, remembering a client's preferences/payment terms, or managing leads. Great companion to the agency skill for solo freelancers.
pipipip169/fable5-handoff/sources/adamentwistle-fable-skills/error-message-quality Skill
no license1★ repoWrite errors and log lines that name the failing thing, the offending value, and the likely fix — for the 3am reader. Use whenever writing a throw/raise, a log statement, a validation message, or a CLI/API error response.
pipipip169/fable5-handoff/sources/adamentwistle-fable-skills/root-cause-debugging Skill
no license1★ repoSystematic debugging — reproduce, bisect, prove the cause with a falsifiable hypothesis, fix minimally, re-verify against the original repro. Use for any bug, test failure, regression, or flaky behavior, before proposing a fix — and whenever a first fix didn't work.
pol-cc/agentic-data-engineer/skills/troubleshoot Skill
1★ repoDiagnose pipeline issues by reading logs and state across Airbyte, dbt, BigQuery, the VPS, and Tailscale. Invoke when verify-pipeline reports a failure, the user says 'something's broken', or a sync hasn't run.
omarfarahatoglu-tur/ai-agent-skills/skills/devops-team/cicd-debugger Skill
1★ repoOpen-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.
omarfarahatoglu-tur/ai-agent-skills/skills/engineering-team/debugging-engineer Skill
1★ repoOpen-source AI agent skills for Claude Code, OpenAI Codex, Cursor, and modern developer workflows.
amansingh909/claude-bounty-skills/skills/triage-responder Skill
1★ repoUse when a submitted bug bounty report gets pushback and you need to draft a reply — statuses like Needs More Info, Informative, Not Applicable (N/A), Duplicate, or a request to demonstrate more impact. Symptoms: "program said needs more info", "they marked it informative", "closed as N/A", "how do I respond to triage", "disputing a duplicate", "they want more impact".
Fyzel/claude-skills/skills/pr-comment-triage Skill
1★ repoTriage and resolve pull-request review comments end to end — fetch reviewer comments (especially GitHub Copilot automated review), fix each one in code, run the project's tests, then post a threaded reply under each original comment by its comment ID. Use this skill whenever the user says "check the Copilot comment(s) on PR N", "address the review comments", "reply to the review comments", "resolve PR feedback", "handle the PR comments", or asks to go through a reviewer's findings on a pull request. Works for any reviewer (Copilot, humans, bots) and any language or repo. Requires the `gh` CLI to be authenticated.
steph-frtech/cdesign-expo/.claude/marketplaces/pocock/skills/github-triage Skill
no license1★ repoTriage GitHub issues through a label-based state machine. 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.
steph-frtech/cdesign-expo/.claude/marketplaces/pocock/skills/triage-issue Skill
no license1★ repoTriage a bug or issue by exploring the codebase to find root cause, then create a GitHub issue with a TDD-based fix plan. Use when user reports a bug, wants to file an issue, mentions "triage", or wants to investigate and plan a fix for a problem.
The same file is in 1 other repository
steph-frtech/cdesign-expo/.claude/marketplaces/superpowers/skills/systematic-debugging Skill
no license1★ repoUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
The same file is in 30 other repositories
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/agent-teams/skills/parallel-debugging Skill
no license1★ repoDebug complex issues using competing hypotheses with parallel investigation, evidence collection, and root cause arbitration. Use this skill when debugging bugs with multiple potential causes, performing root cause analysis, or organizing parallel investigation workflows.
The same file is in 4 other repositories
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/developer-essentials/skills/debugging-strategies Skill
no license1★ repoMaster systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
The same file is in 4 other repositories
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/developer-essentials/skills/error-handling-patterns Skill
no license1★ repoMaster 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.
The same file is in 1 other repository
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/python-development/skills/python-error-handling Skill
no license1★ repoPython error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
steph-frtech/cdesign-expo/.claude/marketplaces/wshobson/plugins/python-development/skills/python-observability Skill
no license1★ repoPython observability patterns including structured logging, metrics, and distributed tracing. Use when adding logging, implementing metrics collection, setting up tracing, or debugging production systems.
The same file is in 1 other repository
Superpowers systematic debugging
steph-frtech/cdesign-expo/.claude/skills/superpowers__systematic-debugging Skill
no license1★ repoUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes
The same file is in 30 other repositories
janellecipriano/pm-skills/skills/postmortem Skill
1★ repoRun a blameless postmortem / incident review — timeline, impact, root cause analysis, and corrective actions. Use when the user says "postmortem", "incident review", "RCA", "root cause analysis", "what happened with the outage", or wants to turn an incident into a structured, blameless writeup with preventive actions.
hlsitechio/claude-skills-security/saas-security-pack/saas-compliance-audit Skill
1★ repoAudit SaaS applications against common compliance frameworks (SOC2, GDPR, HIPAA, PCI-DSS) with focus on technically-verifiable controls including audit logging, data retention, encryption at rest and in transit, DSAR (Data Subject Access Request) endpoints, breach notification readiness, vendor risk, and access reviews. Use this skill whenever the user asks about SOC2, GDPR, HIPAA, PCI-DSS, compliance audit, audit logging, data retention, DSAR, "right to be forgotten", erasure requests, evidence collection, ISO 27001, or "are we compliant". Trigger on phrases like "audit my compliance posture", "SOC2 readiness", "GDPR controls", "do we have the right logs", "data retention policy", "DSAR endpoint", "data deletion", "compliance evidence". Use this even when only one framework or control is mentioned.
JJuice22/classroom-ready-ai-skills/skills/iep-session-notes Skill
1★ repoConverts raw therapist or teacher session observations, voice memo transcripts, bullet-pointed notes, or stream-of-consciousness logs into structured, legally appropriate IEP progress notes and service documentation. Trigger this skill whenever the user mentions writing up session notes, documenting IEP progress, logging service minutes, recording intervention data, writing progress toward IEP goals, noting student performance in pull-out or push-in services, or any task involving documentation of services for students with disabilities. Also trigger when the user pastes raw observation notes and asks to "clean this up", "turn this into a note", or "write this professionally". Works with pasted text, voice memo transcripts, bullet lists, and uploaded .docx or .txt files. Always anonymize student names before producing output unless the user has confirmed FERPA-safe context.
viktor-milev/claude-skills/prompt-optimizer Skill
1★ repoRigorous mode prompt optimizer — audits a polished prompt, decides output architecture (single-turn vs. chained multi-stage), and rewrites it to elicit state-of-the-art output from Claude. Triages every input into OUT OF PURVIEW / BORDERLINE / IN PURVIEW; rigorous optimization (architecture decision, 9-dim diagnostic, archetype detection, capability activation) applies ONLY to IN PURVIEW. When chain signals fire, produces a chain deliverable (README + Project orchestrator + per-stage prompts) instead of a single-turn prompt. Simple prompts return substantially unchanged with a triage note. Use when the user asks to optimize, audit, score, diagnose, sharpen, or level up a prompt; trigger phrases include "optimize this prompt", "PO this", "run this through the optimizer", "sharpen this prompt". For messy dictated or flow-state input, a separate flow-mode counterpart exists. Do NOT trigger when the user wants the prompt EXECUTED rather than optimized.
kora-projects/kora-skills/plugins/kora-v1/skills/kora-aop-logging Skill
1★ repoDeclarative method logging in Kora via the logging-common module — @Log (args + result), @Log.in / @Log.out / @Log.result, @Log.off to suppress a parameter or method, and @Mdc for Mapped Diagnostic Context (key/value, ${expr} interpolation, global thread scope). Covers the imperative ru.tinkoff.kora.logging.common.MDC API and the SLF4J-MDC import pitfall. Use when adding entry/exit logging to a service method, enriching logs with contextual keys, hiding sensitive arguments from log output, or wiring LoggingModule into a @KoraApp.
kora-projects/kora-skills/plugins/kora-v1/skills/kora-telemetry-logging Skill
1★ repoStructured logging for Kora services via SLF4J + Logback (LogbackModule), the KoraAsyncAppender for non-blocking output, structured arguments/markers (StructuredArgument), Kora MDC (ru.tinkoff.kora.logging.common.MDC), and the @Log/@Mdc logging aspects (logging-common / LoggingModule). Use when adding logging-logback, wiring logback.xml with KoraAsyncAppender or ConsoleTextRecordEncoder, configuring per-package log levels via logging.levels in HOCON/YAML, enabling module telemetry logging (telemetry.logging.enabled), emitting JSON logs for ELK/Datadog/Splunk, or correlating logs with trace context.
bromso/metapowers/plugins/development/skills/debug Skill
1★ repoInvestigate root causes systematically using scientific method
bromso/metapowers/plugins/security/skills/logging-architecture Skill
1★ repoPlan centralized logging, retention, and audit trail design
tuannv14/claude-team-toolkit/skills/sentry Skill
1★ repoUse when user references Sentry, sentry.io URLs, *.sentry.io/issues/ links, error/exception/release alerts, pastes a stack trace for triage, or checks release health on cloud or self-hosted. Multi-org via SENTRY_PROFILE.
mkreindel/seo-toolkit-template/.claude/skills/triage Skill
1★ repoScore every site in `sites/` by SEO opportunity and recommend the top 3 to focus investment on. Considers revenue potential, current authority, technical health, content gap, and conversion potential. Outputs a ranked list with rationale. Use when the user types `/triage` or asks "which sites should I focus on."