agentsclimarketplace

Debug & triage

5,150 rows, by stacks then stars

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

  • Ticket triage desk

    MadewellRD/skills-lab/dist/vendor/openai/customer-support-command-desk/ticket-triage-desk Skill

    2★ repo

    route and order support tickets by naming the queue, tier, and skill each contact requires, setting priority from the ordering rule in force and keeping it distinct from contractual severity, identifying spam, duplicates, machine-generated tickets, and misrouted work with the evidence for each, and separating contacts a published answer already resolves from contacts that need diagnosis. use for queue assignment, tier escalation criteria, skill-based routing, priority disputes, bounce-back loops, and misrouting patterns worth fixing in the rules.

  • Contract intake triage desk

    MadewellRD/skills-lab/dist/vendor/openai/legal-contracts-command-desk/contract-intake-triage-desk Skill

    2★ repo

    triage inbound contract requests by classifying matter type, posture, and whose paper the draft arrived on, scoring the risk tier against the named triage rubric, selecting review lanes, checking the repository for an existing agreement over the same scope, and assigning legal owner and committed turnaround. use for new contract requests, nda queues, vendor onboarding packages, quote-to-contract intake, deal desk escalations, renewal intake, self-serve template deflection, and legal front door routing.

  • Intake triage desk

    MadewellRD/skills-lab/dist/vendor/openai/procurement-vendor-management-command-desk/intake-triage-desk Skill

    2★ repo

    triage a purchase requisition by classifying the need as a capability rather than a product name, checking duplicates and overlap against existing agreements and licensed tools, converting a monthly or per-seat quote into annual and total contract value including renewal terms, testing the urgency claim against what actually creates the date, and routing to the sourcing method risk path and lead time the request requires. use for new purchase requests, intake queues, duplicate tool checks, total contract value calculations, emergency purchase claims, and requests where a team has already signed or already told a supplier.

  • Ci failure desk

    MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/ci-failure-desk Skill

    2★ repo

    create connector-grounded ci/cd failure triage and pipeline-health artifacts for software delivery. use when ChatGPT needs to diagnose github actions or build failures, classify flaky tests, inspect logs and workflow runs, decide rerun versus fix, identify failing checks, map ci failures to code changes or infrastructure, or prepare downstream handoff notes for review-quality-desk, verification-desk, release-operations-desk, incident-response-desk, issue-planning-desk, or implementation-handoff-desk workflows.

  • Incident response desk

    MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/incident-response-desk Skill

    2★ repo

    create connector-grounded incident response, bug triage, severity classification, root cause analysis, hotfix handoff, follow-up issue, post-incident review, and production-support artifacts from incidents, alerts, logs, metrics, traces, recent deploys, github issues, pull requests, ci evidence, runbooks, and stakeholder updates. use when ChatGPT needs to triage a production failure, summarize an incident, draft an rca, plan a hotfix, map remediation work, or prepare downstream handoff notes for implementation-handoff-desk, ci-failure-desk, deployment-desk, observability-readiness-desk, release-operations-desk, verification-desk, or docs-traceability-desk workflows.

  • Claude in chrome troubleshooting

    Fodhol/skills/plugins/claude-in-chrome-troubleshooting/skills/claude-in-chrome-troubleshooting Skill

    2★ repo

    Diagnose and fix Claude in Chrome MCP extension connectivity issues. Use when mcp__claude-in-chrome__* tools fail, return "Browser extension is not connected", or behave erratically.

    The same file is in 3 other repositories

  • Triage

    toRolex/rolex-skills/skills/engineering/triage Skill

    1★ repo

    将 issue 和外部 PR 通过一个分类角色状态机进行 triage 流转——分类、验证、必要时打磨,并编写 agent-ready brief。

  • Bug root cause analysis

    dss-time/repo-doctor-skills/plugins/repo-doctor/skills/bug-root-cause-analysis Skill

    1★ repo

    Reproduce and locate a specific runtime bug by tracing the first trustworthy failure through code, logs, configuration, existing tests, and minimal experiments into an evidence-backed causal chain. Use for non-CI symptom-to-root-cause diagnosis; do not absorb CI pipeline failures, general code review, broad health checks, requests to add or modify tests, or requests to implement a fix. 针对具体运行时 Bug,从第一个可信错误出发,结合代码、日志、配置、现有测试和最小实验复现并建立有证据的因果链。用于非 CI 的症状到根因分析;不要吸收 CI 流水线失败、普通代码审查、项目体检、新增或修改测试请求或直接修复请求。

  • Warcraftlogs

    Postmodum37/warcraft-helper/.claude/skills/warcraftlogs Skill

    no license1★ repo

    Query the WarcraftLogs API to answer World of Warcraft raiding and Mythic+ questions. Use this skill whenever the user mentions WarcraftLogs, WCL, raid parses, boss rankings, M+ scores, log analysis, combat logs, guild progression, DPS/HPS rankings, percentiles, or any WoW performance-related question. Also use when the user pastes a warcraftlogs.com URL, mentions a character name + server in a WoW context, asks about raid tier rankings, spec performance, or wants to compare players. Even casual questions like "how did I do last night" or "what's the best healer spec right now" should trigger this skill if there's any WoW context.

  • Debug root cause

    turntuptechnologies-ai/skills/skills/debug-root-cause Skill

    1★ repo

    バグの調査・修正をするとき。「このバグ直して」「エラーの原因を調べて」「なぜか動かない」等で使う。再現 → 切り分け → 根本原因の特定 → 回帰テスト → 修正 → 水平展開の順で進め、原因を説明できないまま症状だけ消す対症療法で終わらせない。

  • Debug

    broneq/bdk/skills/debug Skill

    1★ repo

    Debug issues through structured investigation, failing test creation, and targeted fixes. Use when the user provides an error message, traceback, steps-to-reproduce, or describes unexpected behavior.

  • Holy chain

    arbi-elezi/emperor-time/chains/holy-chain Skill

    1★ repo

    Emperor Time's thumb chain — restoration. Router for four aspects: triage (stop digging, snapshot, bracket the breakage), reproduce-and-bisect (make it fail on demand, isolate the cause one hypothesis at a time), heal-and-verify (minimal fix, root-cause proof, postmortem line), and process healing (recovering a derailed loop, skipped gates, bad merges from enlisted agents, delivered breaches). Engage when something breaks — a regression, a red build, corrupted state, or the process itself. Load one aspect file at a time per the Invocation Ritual.

  • Systematic debugging

    scoobydont-666/shared-claude-skills/skills/systematic-debugging Skill

    1★ repo

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

    The same file is in 30 other repositories

  • Abd triage

    RealDougEubanks/ClaudeMarketplace/skills/agent-based-development/skills/abd-triage Skill

    1★ repo

    ABD Planning Triage agent: reviews open critical/severe/moderate findings and creates rework assignments or marks them resolved.

  • Rem root cause

    darbin/claudecraft/plugins/rem-dev-core/skills/rem-root-cause Skill

    1★ repo

    Deep root cause analysis for bugs and errors. Traces execution paths, eliminates wrong hypotheses, finds the underlying architectural problem — not just symptoms. Convention-aware — checks learnings for known issues before investigating. Use when the user has a bug, error, or unexpected behavior and needs to understand why.

  • Vps incident triage

    goldenprofile/llm-skills/vps-incident-triage Skill

    1★ repo

    Runbook диагностики инцидентов на Linux VPS (systemd + nginx + postgres + redis, без Docker): сервис упал или рестартится (journalctl, коды выхода, OOM-killer), nginx 502/504, диск заполнен, CPU/память 100%, postgres не принимает соединения, бот молчит. Правило: сначала собрать улики, потом рестартить. Используй когда пользователь говорит «прод упал», «сервис не отвечает», «502/504», «диск заполнился», «сервис постоянно рестартится», и нужно найти причину на сервере. Django-исключение с трейсбеком — 500-error-eliminator; аудит конфигов — vps-deploy-auditor; алерты заранее — observability-bootstrap.

  • Ai debugging

    lennney/gate-all-skills/skills/ai/ai-debugging Skill

    no license1★ repo

    AI 调试 / AI debugging. 用户说"帮我 debug"、"报错了"、"这个 bug 怎么修"、"抛异常了"时加载。让用户描述问题,你在后台分析根因并修复。

  • Diagnosing bugs

    lennney/gate-all-skills/skills/engineering/diagnosing-bugs Skill

    no license1★ repo

    Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

  • Error handling

    lennney/gate-all-skills/skills/website/error-handling Skill

    no license1★ repo

    Frontend error handling patterns for Next.js — error boundaries, API error display, form validation errors, and global error recovery strategies. Use when implementing error states, debugging error UI, or designing error recovery flows.

  • Lambda logs zh

    YuAICode/ai-skills/skills/lambda-logs-zh Skill

    1★ repo

    拉 AWS Lambda 的 CloudWatch 最近报错,按频次聚类并给中文根因摘要。当用户说"看 lambda 日志 / lambda 报错排查 / 这个函数出错了 / 查 CloudWatch"时触发。脚本负责取日志,Claude 负责聚类去重 + 中文根因 + 修复建议。

  • Headsup diagnose

    wasulajr/headsup/skills/headsup-diagnose Skill

    1★ repo

    Actively exercise the headsup hook stack end-to-end. Flashes the three tab colors (idle → processing → waiting) on the current tab and verifies each round-trips through the daemon. Use when the user asks "is the headsup thing actually working", "test the headsup hooks", "/headsup-diagnose", or wants confirmation after a change. Different from /headsup-status (passive snapshot) — this skill performs writes and briefly changes the visible tab color. Add the `--restart` arg to also kill the daemon and verify the launchd watchdog respawns it (~30s extra).

  • Systematic debugging

    Yesterday-AI/ytstack/skills/systematic-debugging Skill

    1★ repo

    Root-cause debugging in four phases: investigate, analyze, hypothesize, implement. Iron Law -- no fixes without root cause. Thin ytstack wrapper around the vendored superpowers systematic-debugging procedure, routing findings into KNOWLEDGE.md / DECISIONS.md. Use when hitting a bug, test failure, or unexpected behavior.

  • Investigate

    Yesterday-AI/ytstack/vendor/gstack/investigate Skill

    1★ repo

    Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug directly) when the user reports errors, 500 errors, stack traces, unexpected behavior, "it was working yesterday", or is troubleshooting why something stopped working. (gstack)

  • Systematic debugging

    Yesterday-AI/ytstack/vendor/superpowers/skills/systematic-debugging Skill

    1★ repo

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

    The same file is in 30 other repositories

  • Debug team

    claude-hangar/claude-hangar/core/skills/debug-team Skill

    1★ repo

    Launch parallel debugging agents for systematic root-cause analysis. Use when: "debug team", "help me debug", "debug-team", "find the bug".

  • Org health diagnostic

    timdevai/proteus/skills/community/from-alireza/c-level-advisor/skills/org-health-diagnostic Skill

    1★ repo

    Cross-functional organizational health check combining signals from all C-suite roles. Scores 8 dimensions on a traffic-light scale with drill-down recommendations. Use when assessing overall company health, preparing for board reviews, identifying at-risk functions, or when user mentions org health, health check, or health dashboard.

    The same file is in 1 other repository

  • Analytics tracking

    timdevai/proteus/skills/community/from-alireza/marketing-skill/skills/analytics-tracking Skill

    1★ repo

    Set 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 1 other repository

  • Inbox triage

    timdevai/proteus/skills/community/from-alireza/productivity/email/skills/inbox-triage Skill

    1★ repo

    Runs 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. Triggers: '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', or any variation where the user wants their inbox processed. Requires the inbox-setup skill to have been run first.

  • Monitoring observability

    timdevai/proteus/skills/community/from-rohitg00/monitoring-observability Skill

    1★ repo

    Monitoring and observability with OpenTelemetry, Prometheus, Grafana dashboards, and structured logging

  • Systematic debugging

    pgoell/pgoell-claude-tools/plugins/workbench/skills/systematic-debugging Skill

    1★ repo

    Collection of my personal claude skills

  • Steward

    DataJinipk/contexai-consulting-agents/skills/steward Skill

    1★ repo

    Senior HSE, ESG, and Decarbonisation Specialist for oil & gas, refining, petrochemical, polymer, upstream, and energy projects. Use whenever the user mentions HSE management system (HSE-MS), ISO 14001 environmental management, ISO 45001 occupational health & safety, OHSAS 18001, ISO 50001 energy management, IOGP standards, IPIECA reporting, GRI Standards (Global Reporting Initiative), SASB, TCFD (Task Force on Climate-related Financial Disclosures), ISSB (IFRS S1/S2), CSRD (Corporate Sustainability Reporting Directive), CDP, Science Based Targets initiative (SBTi), Scope 1/2/3 GHG accounting (GHG Protocol), CO2e, CO2 equivalent, methane intensity, OGMP 2.0 (Oil & Gas Methane Partnership), flare reduction, fugitive emissions, leak detection and repair (LDAR), OGCI (Oil & Gas Climate Initiative), Aiming for Zero methane, IMO 2020 sulphur cap (0.5%), IMO 2050 GHG strategy, IMO 2030 / 2040 / 2050 carbon-intensity targets, MARPOL Annex VI, Tier III NOx, scrubber (open-loop / closed-loop), VLSFO / ULSFO / HFO / MGO, LNG bunkering, green hydrogen, blue hydrogen, grey hydrogen, ammonia as fuel, methanol as fuel, eFuel / synthetic fuel, sustainable aviation fuel (SAF), HEFA, FT-SPK, biofuel, biodiesel, ethanol blend, EU ETS (Emissions Trading Scheme), CBAM (Carbon Border Adjustment Mechanism), carbon credit / offset / VCM (Voluntary Carbon Market), CDM, Article 6 Paris Agreement, Verra VCS, Gold Standard, REDD+, nature-based solutions (NbS), carbon capture utilisation & storage (CCUS), CO2 enhanced oil recovery (CO2-EOR), direct air capture (DAC), HSEQ, process safety management (PSM), OSHA 1910.119 PSM, EPA RMP (Risk Management Plan), CCPS (Center for Chemical Process Safety), API RP 754 process safety indicators (Tier 1/2/3/4), Loss of Primary Containment (LOPC), HAZOP, LOPA, SIL (Safety Integrity Level), QRA (Quantitative Risk Assessment), Bowtie analysis, FMEA, root cause analysis, incident investigation (TapRoot, ICAM, Why-Tree, 5-Whys), Buncefield, Texas City, Macondo (Deepwater Horizon), Piper Alpha, Bhopal, Chernobyl, Fukushima - and the lessons learned therefrom. Also trigger on Pakistan-specific HSE / environmental regulation (Pak-EPA, NEQS - National Environmental Quality Standards, EIA / IEE under PEPA 1997, SindhEPA, PunjabEPA, KP-EPA, Balochistan EPA, Sindh Industrial Liaison Office, IFC Performance Standards, Equator Principles, World Bank EHS Guidelines). Inspired by Shell HSE leadership culture, Aramco safety performance, and OGCI/OGMP decarbonisation framework. Make sure to use this skill whenever the user mentions HSE, safety, environment, emissions, climate, sustainability, ESG, decarbonisation, methane, carbon footprint, or any process safety incident - even if the discipline is not explicitly invoked.

  • Spec protocol triage

    spec-protocol/spec-protocol-cli/.agents/skills/spec-protocol-triage Skill

    1★ repo

    Classifica card/demanda por tipo, risco e prontidão mínima; define fluxo do Spec Protocol recomendado. Ativar automaticamente ao receber card, bug, épico, incidente ou pedido de refinamento técnico.

  • Debug

    natthasath/natthasath-marketplace/plugins/projects/skills/debug Skill

    1★ repo

    วิเคราะห์และแก้ bug ด้วย root cause analysis รองรับทั้งโหมดปกติและ --hotfix สำหรับ production emergency ใช้ skill นี้เมื่อมี bug หรือ error เช่น "แก้ bug นี้หน่อย", "production error", "debug ให้หน่อย"

  • Aie web qa

    mrhinkle/aienterprise-skills/plugins/aie-web/skills/aie-web-qa Skill

    1★ repo

    Runs a unified pre-launch or post-update quality-assurance pass on a website — the holistic "does this actually work?" gate. Walks pages, forms, navigation, third-party integrations, cross-browser and mobile behavior, JavaScript console health, accessibility basics, HTTPS/security, and a performance smoke test. Produces a QA report with issues rated by severity, reproduction steps, and a launch recommendation; supports regression testing after fixes. Stack-agnostic. Trigger on "QA my site," "test my site," "does everything work," "smoke test," "test before launch," "regression test," "check all pages," "test my forms," "check mobile," "cross-browser test," "broken links," or "is my site ready to launch."

  • Signal triage

    faiz-sayyad/gtm-outreach-skills/skills/signal-triage Skill

    no license1★ repo

    Classify an incoming outbound signal by tier (T1/T2/T3), set the SLA, and recommend the outreach channel. Use whenever the user pastes signal data, describes a buying signal, mentions a target account firing a signal, or asks how to prioritize incoming outbound signals — even if they don't explicitly use the word "triage." Also use for questions like "should I reach out?", "how fast should I respond?", or "is this a hot lead?"

  • Security logging

    AL-JANEF/janefskills/security-logging Skill

    1★ repo

    Design and review security audit logging and monitoring — recording who did what and when, detecting suspicious activity (repeated failed logins, unusual access), and doing it without leaking sensitive data into the logs themselves. Use this skill whenever the user is building audit trails, adding logging to sensitive actions, setting up monitoring or alerting, investigating an incident, or asks "how do I track who did X?" — especially for auth events, data changes, and admin actions. Defensive only.

  • Troubleshooting

    AndriyKalashnykov/flight-path/.claude/skills/troubleshooting Skill

    1★ repo

    Diagnose and fix common issues in the flight-path project: build failures, test failures, port conflicts, Docker problems, and tool errors. Use when something fails, an error occurs, the server won't start, or a command produces unexpected output. Do NOT use for environment setup, workflow guidance, or adding new features.

  • Workflows

    AndriyKalashnykov/flight-path/.claude/skills/workflows Skill

    1★ repo

    Project-specific development workflows for the flight-path Go project: adding endpoints, benchmarking, releasing, Docker builds, and CI pipelines. Use when following a development process, preparing a release, running CI locally, or understanding the build pipeline. Do NOT use for environment setup, troubleshooting errors, or debugging specific failures.

  • Github actions writer

    JamesPrial/claude-plugins/version-control/skills/github-actions-writer Skill

    1★ repo

    This skill should be used when users need to create, modify, optimize, or troubleshoot GitHub Actions CI/CD workflows. Use when users ask about automating builds, tests, deployments, or any GitHub Actions-related tasks. Triggers include requests like "create a CI workflow", "deploy to AWS", "automate testing", "setup GitHub Actions", or when debugging workflow failures.

    The same file is in 6 other repositories

  • Debug

    mattjaikaran/meridian/skills/debug Skill

    1★ repo

    Skill that gives AI coding agents persistent memory and quality enforcement

  • Orchestrating azure deployments

    alexpizarro/azure-lean-stack-skills/skills/orchestrating-azure-deployments Skill

    1★ repo

    Routes Azure web app work (scaffold, deploy, troubleshoot, evolve) to the right Azure Lean Stack sub-skill. Built around branch-per-environment CI/CD where each git branch maps to one isolated Azure resource group via OIDC. Use when building or deploying a new Azure app, setting up GitHub Actions for Azure, troubleshooting a failed deploy, or adding FC1 / Container Apps / Logic Apps / multi-tenant patterns.

  • Pwp debug

    shandar/pwp-plugin/skills/pwp-debug Skill

    1★ repo

    Systematic debugging protocol — diagnose, isolate, and fix bugs with discipline. Use this skill whenever the user reports a bug, error, crash, or unexpected behavior. Also use when they say things like 'this is broken', 'not working', 'something's wrong', 'fix this', 'why is this failing', or share an error message or stack trace. Covers reproduce → isolate → root cause → fix → verify workflow.

  • Debug command

    datamaker-kr/synapse-claude-marketplace/plugins/synapse-plugin-helper/skills/debug-command Skill

    no license1★ repo

    Run the `synapse-plugin-helper:debug` workflow from the original Claude slash command. Use when the user asks to diagnose and fix common Synapse plugin issues

  • Logs command

    datamaker-kr/synapse-claude-marketplace/plugins/synapse-plugin-helper/skills/logs-command Skill

    no license1★ repo

    Run the `synapse-plugin-helper:logs` workflow from the original Claude slash command. Use when the user asks to stream logs from a running Synapse job

  • Severity

    lklimek/claudius/skills/severity Skill

    1★ repo

    Plugin with opinionated set of Claude Code agents nad skills

  • Triage findings

    lklimek/claudius/skills/triage-findings Skill

    1★ repo

    Plugin with opinionated set of Claude Code agents nad skills

  • Data defect investigator

    nicholashidalgo/claude-skillforge/data-engineering/data-defect-investigator Skill

    1★ repo

    Investigate mismatches, duplicates, missing records, broken keys, and reconciliation defects using structured SQL or Python diagnostics.

  • Focused fix

    DROOdotFOO/agent-skills/skills/focused-fix Skill

    1★ repo

    Structured 5-phase bug fix methodology with root cause verification. TRIGGER when: user wants to fix a bug, debug an issue, investigate a failure, or says "focused fix". Also when a fix attempt has failed and the user wants a systematic approach. DO NOT TRIGGER when: user wants architecture analysis (use architect), QA triage (use qa), or code review (use code-review).

  • Memory diagnose

    ladyiceberg/openclaw-memory-quality/skills/memory-diagnose Skill

    1★ repo

    Deep diagnosis of OpenClaw retrieval quality — identifies false positives, zombie entries, and gives configuration recommendations to fix weak embedding or FTS-only retrieval. Use this skill whenever the user asks about retrieval quality, wonders why memory seems off, wants to understand false positives or zombie entries, asks about embedding or memory configuration, or uses phrases like "memory diagnosis", "bad memories", "why is memory bad", "memory config", "记忆诊断", "检索质量", "假阳性", "记忆配置". Prefer this skill over generic troubleshooting when OpenClaw memory quality is the topic.

  • Tracecat validation debug

    adrojis/tracecat-skills/skills/tracecat-validation-debug Skill

    1★ repo

    Activate when users debug failed workflow executions, troubleshoot errors, or validate workflows before deployment

  • Eval result interpreter

    varunk130/AI-Eval-Skills/skills/eval-result-interpreter Skill

    1★ repo

    Analyzes AI agent evaluation results - primarily from Copilot Studio (the worked example here, via its CSV export) but also from custom harnesses or any evaluator that produces per-case pass/fail rows - using Microsoft's Triage & Improvement Playbook. Returns a SHIP / ITERATE / BLOCK verdict with root cause classification, diagnostic triage, prioritized remediation, and pattern analysis.

  • Eval triage and improvement

    varunk130/AI-Eval-Skills/skills/eval-triage-and-improvement Skill

    1★ repo

    Use this skill when AI agent evaluations have come back and the user needs to interpret scores, diagnose root causes of underperforming test cases, find remediation steps, or analyze patterns to improve their agent. Works against any agent platform - Copilot Studio is the primary worked example here, but the triage framework applies equally to custom harnesses, LangChain/LangGraph, AutoGen, Semantic Kernel, OpenAI Assistants, and other agent runtimes. Always use this skill when the user mentions: "eval failed", "why did this fail", "triage", "diagnose failure", "low pass rate", "fix evaluation results", "not passing", "failing test cases", "evaluation results", "improve my eval scores", or any situation where eval scores need interpretation and action.

  • Troubleshooting

    ryukyagamilight/terminal-skills/kubernetes/troubleshooting Skill

    1★ repo

    Kubernetes 故障排查

    The same file is in 1 other repository

  • Troubleshooting

    ryukyagamilight/terminal-skills/performance/troubleshooting Skill

    1★ repo

    性能问题排查

    The same file is in 1 other repository

  • Log analysis

    ryukyagamilight/terminal-skills/server/log-analysis Skill

    1★ repo

    日志分析与处理

    The same file is in 1 other repository

  • Systematic debugging

    MARUCIE/openclaw-foundry/web/public/packs/algorithm-engineer/skills/algorithm/systematic-debugging Skill

    1★ repo

    Use when encountering a bug, test failure, crash, or unexpected behavior. Enforces root-cause investigation before any fix attempt. NOT for writing new features. Trigger: bug, error, failing test, broken, unexpected, crash, regression.

  • Systematic debugging

    MARUCIE/openclaw-foundry/web/public/packs/backend-engineer/skills/backend/systematic-debugging Skill

    1★ repo

    Use when encountering a bug, test failure, crash, or unexpected behavior. Enforces root-cause investigation before any fix attempt. NOT for writing new features. Trigger: bug, error, failing test, broken, unexpected, crash, regression.

  • Observability

    MARUCIE/openclaw-foundry/web/public/packs/spellbook-platform-engineer/skills/observability Skill

    1★ repo

    Use when adding structured logging, instrumenting Prometheus metrics, wiring up distributed tracing with OpenTelemetry, writing alerting rules, defining SLOs and error budgets, or building a Grafana golden-signals dashboard.

  • Observability

    MARUCIE/openclaw-foundry/web/public/packs/spellbook-security-auditor/skills/observability Skill

    1★ repo

    Use when adding structured logging, instrumenting Prometheus metrics, wiring up distributed tracing with OpenTelemetry, writing alerting rules, defining SLOs and error budgets, or building a Grafana golden-signals dashboard.

  • Systematic debugging

    MARUCIE/openclaw-foundry/web/public/packs/test-engineer/skills/test/systematic-debugging Skill

    1★ repo

    Use when encountering a bug, test failure, crash, or unexpected behavior. Enforces root-cause investigation before any fix attempt. NOT for writing new features. Trigger: bug, error, failing test, broken, unexpected, crash, regression.