agentsclimarketplace

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

  • Plex diagnostic expert

    Lunatic16/LLM-Skills-Collection/plex-diagnostic-expert Skill

    no license0★ repo

    Troubleshooting Plex Media Server playback, instability, and library issues by analyzing server logs and environment metadata.

  • Logging

    ortus-boxlang/skills/boxlang-core-development/logging Skill

    no license0★ repo

    Use this skill when working with BoxLang logging: obtaining loggers via LoggingService, using BoxLangLogger (trace/debug/info/warn/error), pre-configured common loggers, creating named loggers, parameterized messages, accessing loggers from context and interceptors, and logging configuration in boxlang.json.

  • Ss diagnose

    JasonLo/skill-sommelier/skills/ss-diagnose Skill

    0★ repo

    Disciplined diagnosis loop for hard bugs and performance regressions: build a feedback loop → reproduce → hypothesise → instrument → fix → regression-test → cleanup. Use when the user says "diagnose this", "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression. Triggers on "diagnose", "debug", "broken", "throwing", "failing", "perf regression", "slow", "hangs".

  • Datadog cli

    payals/ai-skills-engine/dot_cursor/skills/ai-research/datadog-cli Skill

    0★ repo

    Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.

    The same file is in 3 other repositories

  • Loki mode

    payals/ai-skills-engine/dot_cursor/skills/ai-research/loki-mode Skill

    0★ repo

    Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

    The same file is in 4 other repositories

  • Error resolver

    payals/ai-skills-engine/dot_cursor/skills/development/error-resolver Skill

    0★ repo

    Systematic error diagnosis and resolution using first-principle analysis. Use when encountering any error message, stack trace, or unexpected behavior. Supports replay functionality to record and reuse solutions.

    The same file is in 2 other repositories

  • Systematic debugging

    arndvs/ctrlshft/skills/systematic-debugging Skill

    0★ repo

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

  • Debug

    jessedegans/jstack/skills/debug Skill

    no license0★ repo

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Enforces root cause investigation before fixing. No guessing, no shotgun debugging. Hard stop after 3 failed hypotheses. Use when: tests fail, errors appear, behavior doesn't match expectations, or something "just broke."

  • Rust tracing

    dawidpereira/rust-skills/skills/rust-tracing Skill

    0★ repo

    Rust observability with tracing — structured logging, spans, subscribers, and instrumentation. Use when choosing between tracing and log, setting up subscribers and layers, adding #[instrument] to functions, configuring RUST_LOG, instrumenting async code (.instrument() vs span.enter()), integrating tower-http or sqlx middleware, protecting sensitive data in logs, or preparing tracing for production with OpenTelemetry. Also use when reviewing code for logging quality or adding request correlation IDs.

  • Logging

    ColdBox/skills/coldbox/logging Skill

    no license0★ repo

    Use this skill for all ColdBox-specific logging concerns: configuring LogBox inside a ColdBox application (config/LogBox.cfc, inline DSL, configFile pointer), per-environment log levels, injecting loggers into handlers/interceptors/services via the WireBox logbox DSL, accessing logbox from the ColdBox proxy, and logging best practices specific to the ColdBox lifecycle.

  • Logbox

    ColdBox/skills/logbox Skill

    no license0★ repo

    Use this skill whenever working with LogBox -- standalone or inside a ColdBox application. Covers installation, configuration DSL (appenders, root logger, categories), all built-in appender types with their properties, logger injection via WireBox DSL, category inheritance, structured logging with extraInfo, performance patterns (can{} methods, closure messages), custom appenders, custom layouts, async logging, environment-specific config, and production best practices.

  • Cbdebugger

    ColdBox/skills/modules/cbdebugger Skill

    no license0★ repo

    Use this skill when installing, configuring, or using the CBDebugger visual debugging panel in a ColdBox application. Covers enabling the panel in development, performance profiling, SQL query tracking, cache monitoring, request inspection, and ensuring the debugger is disabled in production.

  • Debug

    RhythmMittal19/claude-config/skills/debug Skill

    0★ repo

    Debug errors with systematic 6-step protocol. Paste error message or describe the bug.

  • Backup

    scryptoginger/keith-claude-skills/skills/merlin-log-triage/backup Skill

    no license0★ repo

    Use this skill whenever someone hands over a MERLIN execution log (or VIGIL watchdog log) and needs a fast read on what happened — for post-cycle review, debugging a failed run, investigating why no trades executed, or daily operator-style triage. Trigger on phrases like "triage this log," "what went wrong in this run," "analyze MERLIN output," "post-mortem on the cycle," or any time a `.log` / `.txt` file path is provided alongside MERLIN-domain context (Oracle, Shield, Technician, Augur, blackboard, cycle, VETO). Recency window: a single log file or a contiguous excerpt — not historical trend analysis across many runs. Not for live trading decisions, fixing the underlying issues, restarting agents, or general application logs unrelated to MERLIN/VIGIL infrastructure.

  • Github label scout

    baronguyen001/ai-automation-skills/skills/github-label-scout Skill

    0★ repo

    Scan a public GitHub repo for open issues carrying a given label and drop the ones already taken - skips pull requests returned by the issues endpoint and any issue with assignees - using the public REST API with no token required. Use for find github issues by label, good first issue scout, skip assigned issues, github issue triage, or open source contribution finder.

  • Program debug

    locallaunchsc-cloud/solana-dev-skills/program-debug Skill

    0★ repo

    Use this skill when the user is debugging a Solana program error — reading transaction logs, decoding Anchor error codes, simulating transactions, handling compute budget issues, and diagnosing common runtime failures.

  • Triage status

    kompiro/hane/skills/triage-status Skill

    0★ repo

    `status: *` ラベルがまだ付いていない open Issue に、内容から推論した初期 status (ready / blocked / designed)を提案してユーザー確認のうえ付与する。pick-issue の 前段で status 空白を解消する triage 工程。既に status が付いた Issue や lifecycle の 遷移(implementing / designing / in-review)は対象外(start-dev / ship / pick-issue が管理)。 Trigger when the user says: "statusを付与", "初期statusを付ける", "status未設定のissue", "issueのstatusを整理", "statusをtriage", "assign status label", "triage issue status", "triage status", "set initial status", "add status to issue", or similar phrases requesting to assign an initial status label to Issues that lack one.

  • Agent introspection debugging

    bertbertov/claude-stack/skills/agent-introspection-debugging Skill

    0★ repo

    Structured self-debugging workflow for AI agent failures using capture, diagnosis, contained recovery, and introspection reports.

    The same file is in 5 other repositories

  • Vscode dotnet debug

    hsinhan-h/hh-claude-skills/vscode-dotnet-debug Skill

    no license0★ repo

    Automatically generate .vscode/launch.json and .vscode/tasks.json debug configurations for .NET projects, with browser auto-open, hot reload (dotnet watch) support, and multi-project compound launch support. Use when user asks to create VS Code debug files, set up debugging, configure launch.json or tasks.json for a .NET project, or mentions "debug 設定"、"除錯設定"、"launch.json"、"建debug檔"、"hot reload"、"dotnet watch"。

  • Garelier guardian

    aby-studio-works/garelier/skills/garelier-guardian Skill

    0★ repo

    Garelier-only: fire in a `__garelier/<pm_id>/` project or on explicit Garelier/guardian invocation, not on generic security / license / dependency wording. The security / privacy / dependency / license / provenance GATE for a Garelier merge or promote — diff scan for leaked secrets / tokens / private keys / credentials, customer data or PII, real data in fixtures or logs, vulnerable or malicious dependencies, forbidden or unknown licenses, copyright/provenance risk in curated knowledge, or dangerous auth / crypto / logging / CI / deploy / infra / migration changes. Commit-free on an ephemeral gavel branch; reads Librarian security/ knowledge; emits verdict PASS / PASS_WITH_NOTES / BLOCK / NO_OPINION; gates, never fixes. Also fires on gavel / preflight / delta gate / final gate / redact. Requires garelier-core.

  • Root cause

    marsloting/product-thinking-pack/skills/root-cause Skill

    0★ repo

    Apply 5 Whys + Fishbone (Ishikawa) + Pareto when something already broke and you need to find the root cause, not the symptom. Use whenever 用户 says "为什么会这样" / "找根因" / "这个 bug 怎么发生的" / "用户为什么流失" / "数据为什么跌" / "上次也踩过这个坑" / "incident postmortem" / "事故复盘". Forces 5-level "why" probing past the first surface answer, distinguishes proximate cause from root cause, uses Fishbone's 6M categories (man/machine/method/material/measurement/environment) for systemic issues, applies Pareto 80/20 to prioritize fixes. Stops "fix the symptom" pattern. Self-contained methodology — no external docs required.

  • Pm inbox triage

    kalyvask/pm-evaluation-framework/.claude/skills/pm-inbox-triage Skill

    0★ repo

    Pull recent Gmail threads, classify them into action categories (substantive response needed / quick reply / FYI / can ignore), and draft replies for the substantive ones. Surfaces stale threads where the user is awaiting a response and stale threads where someone is awaiting them. Used as part of pm-morning-brief or invoked directly when the inbox feels out of control. Drafts only — never auto-sends.

  • Rails logging

    mickzijdel/rails-toolkit/skills/rails-logging Skill

    0★ repo

    Rails logging and observability — Lograge for structured one-line request logs, tagged logging with request/user context, sensitive parameter filtering, ActiveSupport::Notifications for custom instrumentation, Sentry/error-tracker integration, health check endpoints, and log-level configuration. Use when setting up a new app's observability stack, debugging noisy logs, or adding structured logging.

  • Integration validator

    merge-api/merge-unified-skills/skills/integration-validator Skill

    0★ repo

    Validate a Merge Unified API integration end-to-end. Use when a developer says "validate my Merge integration", "test my Merge setup", "is my Merge connection working", "debug my Merge API call", "verify my Linked Account", "check my Merge scopes", "my Merge API returns empty", "Merge sync not working", "check my account_token", or after completing /merge-unified:onboarding. Runs diagnostic checks against the Merge API and outputs a pass/fail checklist with actionable fixes.

  • Opp repl tasks and results

    tabgab/opp_repl-skill/opp-repl-tasks-and-results Skill

    no license0★ repo

    The opp_repl Task/Result object model — SimulationTask, TestTask, UpdateTask, BuildTask, CompareSimulationsTask; result codes (DONE/SKIP/CANCEL/ERROR, PASS/FAIL, KEEP/INSERT/UPDATE, IDENTICAL/DIVERGENT/DIFFERENT); MultipleTaskResults filtering/drill-down/rerun; trajectories (fingerprint & stdout); project-state hashing; and git-bisect for test regressions. Load when you need to inspect, filter, or rerun anything opp_repl has produced.

  • Opp repl troubleshooting

    tabgab/opp_repl-skill/opp-repl-troubleshooting Skill

    no license0★ repo

    Decode opaque opp_repl errors into actionable fixes. Maps every common failure mode ("Building X failed", exit code 127, "Class not found", scalar/stderr None on ERROR, namespace mismatch) to its root cause and remedy. Load when a build or run fails and the immediate output gives no useful clue — this skill tells you WHERE the real information hides and HOW to extract it without leaving opp_repl. Required companion skill for any non-trivial project work, especially new projects from scratch.

  • Diagnose

    wachawo/claude-skills/skills/diagnose Skill

    0★ repo

    Disciplined loop for diagnosing complex bugs and performance regressions. Reproduce → minimize → hypothesize → instrument → fix → close with a regression test. Use when the user says "diagnose this" / "debug this", reports a bug, says something is broken / crashing / not working, or describes a performance regression.

  • Triage

    wachawo/claude-skills/skills/triage Skill

    0★ repo

    Triage issues using a small state machine driven by triage roles. Use when the user wants to file an issue, triage issues, sort through incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

  • Aem debugging log analysis

    prakash888kp/AEM-SKILLS/skills/tier-5-development/aem-debugging-log-analysis Skill

    0★ repo

    A curated catalog of Adobe Experience Manager (AEM) skills organized into tiers, with dependency chains and contribution guidelines.

  • Bug report to repro

    alexzhu0/agent-ready-skills/skills/bug-report-to-repro Skill

    0★ repo

    Use when converting bug reports, user complaints, screenshots, logs, or QA notes into a reproducible case with environment, steps, expected behavior, actual behavior, and missing evidence.

  • Error message improver

    kakarot-oncloud/claude-dev-skills/skills/error-message-improver Skill

    0★ repo

    Rewrites cryptic, unhelpful, or user-hostile error messages into clear, actionable ones that tell the user what went wrong, why, and what to do next. Use this skill when the user pastes an error message and asks to improve it, says "make this error better", needs user-facing error copy, or asks to audit error handling for clarity.

  • Debug systems

    aman-bhandari/claude-code-agent-skills-framework/.claude/skills/debug-systems Skill

    0★ repo

    Use when the student encounters an error, says something is broken, or asks for debugging help. Enforces a three-layer debugging protocol: reproduce, trace the mental model, check OS state, identify production failure mode. Invoke with /debug.

  • Debug

    SeidSmatti/misc-CC-Plugins/plugins/academic-latex/skills/debug Skill

    0★ repo

    Diagnoses LaTeX compilation failures by parsing the .log file, classifies the error (undefined control sequence, missing package, math-mode mistake, runaway argument, package error, citation/reference undefined, overfull box), and proposes a specific fix grounded in the package or kernel docs. Use when latexmk/pdflatex/xelatex/lualatex exits non-zero, when the user reports a build error, when a "?" prompt appears, or when /academic-latex:compile delegates here. Delegates to /academic-latex:docs-lookup before claiming a fix it isn't certain about.

  • Debug

    puukis/lstack/skills/debug Skill

    0★ repo

    Systematic root cause analysis — reproduce, isolate, hypothesize, verify before any fix

  • Debugging and error recovery

    dills122/ai-central/templates/skills/imported/agent-skills/debugging-and-error-recovery Skill

    0★ repo

    Guides 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.

    The same file is in 10 other repositories

  • General debug

    dills122/ai-central/templates/skills/imported/rust-agentic-skills/general-debug Skill

    0★ repo

    Systematic logic error isolation.

  • Supafax inbox triage

    riteshkew/yc-skills/skills/supafax-inbox-triage Skill

    0★ repo

    Apply an ordered set of triage rules to an inbox fixture and categorize each email into an action — reply, archive, unsubscribe, calendar, or review — with the matching rule's reason. Use this skill whenever you need to batch-process a raw inbox and produce an actionable triage report without touching an email provider.

  • Resilience engineer

    ak-ship/fullstack-agent-skills/skills/resilience-engineer Skill

    0★ repo

    Audit and upgrade error handling — replace silent try/catch swallows with typed errors, real recovery logic, retry/backoff, structured logging, and user-facing messages that aren't "Something went wrong". Use when the user says "improve error handling", "add logging", "make this resilient", "why are we losing errors", "this should retry", "audit the error paths", or "we never see anything in Sentry from this service".

  • Debugging lab notebook

    alinafe82/cognitive-deadlift/skills/debugging-lab-notebook Skill

    0★ repo

    Debug hard failures with reproduction, hypotheses, instrumentation, experiments, and regression proof. Use when bugs are flaky, poorly understood, production-facing, performance-related, or AI starts guessing fixes. NOT for simple bugs that already have a deterministic failing test.

  • Triage

    markbaindesign/bain-studio/skills/triage Skill

    no license0★ repo

    Triage an inbound signal — classify it, qualify it if it's an RFQ, and route it. Paste the signal text as the argument. Handles email, LinkedIn, referral, contact form, and direct outreach. For automated Upwork pipeline signals, use the PIPE project pipeline instead.

  • N8n error handling

    produtoramaxvision/maxvision-utilities/n8n-skills/skills/n8n-error-handling Skill

    no license0★ repo

    Wire n8n error handling so failures are loud, structured, and recoverable. Use when building any webhook/API workflow, a scheduled or unattended workflow, or any path where a silent failure would drop user-visible work — and whenever the user mentions error handling, onError, continueErrorOutput, error branches/outputs, retries, retryOnFail, Respond to Webhook status codes, 4xx/5xx, Error Trigger, or "my workflow fails silently". Covers per-node error outputs and wiring, retry/self-healing, error-trigger workflows, and 4xx/5xx response shapes.

    The same file is in 1 other repository

  • Postmortem

    GRIDLOCK-NYC/claude-skills/skills/postmortem Skill

    0★ repo

    Structured incident and bug analysis — timeline reconstruction, root cause identification, contributing factors, and prevention. Use when user says 'postmortem', 'what went wrong', 'why did this break', 'incident review', 'root cause analysis', 'RCA', 'failure analysis', 'what happened'. Do NOT use for session-level audits (use session-audit). Do NOT use for code quality review (use simplify).

  • Laser troubleshoot

    victorzhu-eng/industrial-laser-principles/skills/laser-troubleshoot Skill

    0★ repo

    General laser-system troubleshooting walkthrough — orders the diagnostics correctly so alignment isn't blamed for a power, optic, or focus problem. Use when the user says "cut quality dropped", "marks aren't right", "system isn't performing", "what should I check first", or has an open-ended performance complaint.

  • Rubber duck debugger

    tejasashinde/agent-skill-kit/rubber-duck-debugger Skill

    0★ repo

    Structured metacognitive debugging skill that forces step-by-step self-explanation of logic, code, or reasoning as if teaching a naïve “rubber duck.” Use when diagnosing bugs, resolving logical inconsistencies, or uncovering hidden assumptions in complex reasoning systems.

  • Systematic debugging

    fabioc-aloha/Alex_ACT_Edition/.github/skills/systematic-debugging Skill

    0★ repo

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Four-phase root-cause-first method (investigate → pattern-analyze → hypothesize → implement) that beats guess-and-check thrashing.

  • Debugging

    felixhennequin-gif/claude-code-config-template/.claude/skills/core/debugging Skill

    0★ repo

    Structured debugging workflow. Activates when fixing bugs, investigating errors, troubleshooting test failures, or when a previous fix attempt failed.

  • Error handling

    felixhennequin-gif/claude-code-config-template/.claude/skills/core/error-handling Skill

    0★ repo

    Error handling patterns for HTTP services. Activates when writing error handling code, creating error classes, working with try/catch blocks, or implementing error middleware in an HTTP backend (Express, FastAPI, Flask, Django, Gin, Axum, etc.).

  • Debugging

    felixhennequin-gif/claude-code-config-template/cli/template-files/claude/skills/core/debugging Skill

    0★ repo

    Structured debugging workflow. Activates when fixing bugs, investigating errors, troubleshooting test failures, or when a previous fix attempt failed.

  • Error handling

    felixhennequin-gif/claude-code-config-template/cli/template-files/claude/skills/core/error-handling Skill

    0★ repo

    Error handling patterns for HTTP services. Activates when writing error handling code, creating error classes, working with try/catch blocks, or implementing error middleware in an HTTP backend (Express, FastAPI, Flask, Django, Gin, Axum, etc.).

  • Nagi logs

    yukihirop/nagi/.claude/skills/nagi-logs Skill

    0★ repo

    Show nagi service logs. Triggers on "logs", "show logs", "nagi logs", "check logs", "ログ".

  • Github issue

    rokurokulab/dotai/claude/plugins/dotai-base/skills/github-issue Skill

    0★ repo

    Draft concise, repository-aligned GitHub issues with proportional detail based on change size.

  • Github issue

    rokurokulab/dotai/codex/skills/github-issue Skill

    0★ repo

    Draft concise, repository-aligned GitHub issues with proportional detail based on change size.

  • Github issue

    rokurokulab/dotai/shared/skills/github-issue Skill

    0★ repo

    Draft concise, repository-aligned GitHub issues with proportional detail based on change size.

  • Diagnose

    marzun9620/agent_skills/dev-process/skills/diagnose Skill

    no license0★ repo

    Disciplined 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

  • Effect ts observability

    marzun9620/agent_skills/effect-ts/skills/effect-ts-observability Skill

    no license0★ repo

    This skill should be used when the user asks about "Effect logging", "Effect.log", "Effect metrics", "Effect tracing", "spans", "telemetry", "Metric.counter", "Metric.gauge", "Metric.histogram", "OpenTelemetry", "structured logging", "log levels", "Effect.logDebug", "Effect.logInfo", "Effect.logWarning", "Effect.logError", or needs to understand how Effect handles logging, metrics, and distributed tracing.

  • Triage

    marzun9620/agent_skills/planning/skills/triage Skill

    no license0★ repo

    Triage 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

  • Hv debug

    l4ci/hv-skills/hv-debug Skill

    0★ repo

    Systematic root-cause investigation for a bug — reads the TODO entry + detail file, consults KNOWLEDGE.md, reproduces, hypothesizes, verifies, fixes with one atomic commit, and nudges /hv-learn. Use on "debug [B07]", "why is X broken", "investigate the crash", when a bug needs a proper cycle rather than a /hv-go shot.

  • Docker ephemeral volume fix

    aksheyw/claude-code-learned-skills/skills/docker-ephemeral-volume-fix Skill

    0★ repo

    Diagnose and fix the "settings randomly reset" pattern in Docker containers — when an app migration writes active config to a new path that isn't volume-mounted, dashboard/UI changes silently disappear on `docker compose down/up`. Includes diagnostic checklist and the copy-out-then-mount fix.

  • Thrunt debug

    3dcom2711/thrunt-god/thrunt-god/examples/brute-force-to-persistence/.github/skills/thrunt-debug Skill

    0★ repo

    Systematic debugging with persistent state across context resets

    The same file is in 1 other repository

  • Roblox debugging bugfix

    AshExplained/roblox-skills/roblox-debugging-bugfix Skill

    0★ repo

    Debug and fix Roblox bugs through Studio MCP. Use for repro steps, console errors, script search/read/edit flow, broken UI, failed gameplay systems, data issues, remotes, regressions, root-cause reports, and post-fix verification.