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

  • Thinking kepner tregoe

    onfire7777/universal-ai-skills-library/skills/thinking-kepner-tregoe Skill

    14★ repo

    Systematic rational process for complex problem analysis, decision making, and risk assessment. Use for high-stakes engineering decisions, root cause analysis beyond 5 Whys, and multi-factor evaluations requiring structured criteria.

  • Track improve

    onfire7777/universal-ai-skills-library/skills/track-improve Skill

    14★ repo

    Track mistakes and improvement opportunities with 5-whys root cause analysis. Use when Claude makes an error, gives a wrong answer, misunderstands intent, or when you spot a pattern worth capturing. Triggers on: 'track this mistake', 'log this issue', 'remember this for next time', 'you keep doing this', 'improvement opportunity', 'track improvement', 'what went wrong'.

  • Triage

    onfire7777/universal-ai-skills-library/skills/triage Skill

    14★ repo

    Initial response to incidents, impact scope identification, recovery procedure formulation, and postmortem creation. Used when incident response and recovery are required. Does not write code (delegates fixes to Builder).

  • Typescript unit testing

    onfire7777/universal-ai-skills-library/skills/typescript-unit-testing Skill

    14★ repo

    Complete unit testing skill for TypeScript/NestJS projects using Jest, @golevelup/ts-jest, and in-memory databases. ALWAYS use this skill when user needs to: **SETUP** - Initialize or configure unit testing: - Set up Jest for a new project - Configure test infrastructure (jest.config.ts) - Install testing dependencies (@nestjs/testing, @golevelup/ts-jest) - Create mock helpers or test utilities - Set up coverage configuration **WRITE** - Create or add unit tests: - Write, create, add, or generate unit tests - Test a service, usecase, controller, guard, interceptor, pipe, or filter - Add tests for new code or features - Improve test coverage or add missing tests - Mock dependencies or set up test fixtures - Working on any file ending in .spec.ts **REVIEW** - Audit or evaluate unit tests: - Review existing tests for quality - Check test coverage and gaps - Audit testing patterns and conventions - Evaluate assertion quality **RUN** - Execute or analyze test results: - Run unit tests - Analyze test results or coverage reports - Understand test failures or successes - Check which tests are passing/failing **DEBUG** - Fix failing or broken tests: - Fix failing unit tests - Debug test errors or exceptions - Resolve mock issues or setup problems - Troubleshoot test timeouts or flaky tests - Diagnose "undefined" or unexpected results **OPTIMIZE** - Improve test performance and maintainability: - Speed up slow tests - Fix open handles preventing clean exit - Improve test organization - Reduce test execution time - Clean up test code Keywords: unit test, spec, jest, typescript, nestjs, mock, DeepMocked, createMock, AAA, test coverage, TDD, .spec.ts, testing, write test, add test, create test, fix test, debug test, run test, review test, optimize test, test setup, jest config

  • Ios logging

    rusel95/ios-agent-skills/skills/ios-logging Skill

    13★ repo

    Enterprise skill for iOS production error observability and logging (iOS 15+, Swift 5.5+). The trigger is OBSERVABILITY intent — the user wants errors captured and visible in production, not just handled. Use when: adding os.Logger or replacing print() with structured logging; setting up or integrating a crash SDK (Sentry, Crashlytics, PostHog); auditing error handling for silent failures (catch blocks with no Logger/ErrorReporter call, try? on network/auth/payment operations, Task {} with no do-catch, Combine .replaceError() killing error visibility); adding privacy annotations to logs; integrating MetricKit for OOM/hang detection; or asking why errors are disappearing silently in production. Also use when reviewing any catch block, try?, or Task {} specifically to ensure errors reach a remote crash reporting service — not just for writing error handling in general.

    The same file is in 1 other repository

  • Issue triage

    Marcel-Bich/marcel-bich-claude-marketplace/plugins/credo/skills/issue-triage Skill

    13★ repo

    Use when the user wants to triage GitHub issues - decide whether an issue is still relevant, reproducible, closeable, a duplicate, or what concretely needs doing. Selects and prioritizes first (never dumps all issues at once), then deep-triages the chosen issues via parallel subagents, recommends actions for the owner to approve, and can optionally kick off a reviewed fix. Works for any repo; produces no sensitive or personal data.

  • Debugging

    DojoCodingLabs/code-sensei/skills/debugging Skill

    13★ repo

    Reading errors, troubleshooting, and fixing bugs. Activated when Claude encounters errors or when the user is debugging. Teaches the most valuable skill: understanding what went wrong.

    The same file is in 1 other repository

  • Debugging and error recovery

    kevinnft/ai-agent-skills/skills/addyosmani/debugging-and-error-recovery Skill

    13★ 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.

  • Diagnose

    kevinnft/ai-agent-skills/skills/mattpocock/engineering/diagnose Skill

    13★ 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.

  • Triage

    kevinnft/ai-agent-skills/skills/mattpocock/engineering/triage Skill

    13★ 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.

  • Debugging hermes tui commands

    kevinnft/ai-agent-skills/skills/software-development/debugging-hermes-tui-commands Skill

    13★ repo

    Debug Hermes TUI slash commands: Python, gateway, Ink UI.

  • Node inspect debugger

    kevinnft/ai-agent-skills/skills/software-development/node-inspect-debugger Skill

    13★ repo

    Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

  • Systematic debugging

    kevinnft/ai-agent-skills/skills/software-development/systematic-debugging Skill

    13★ repo

    4-phase root cause debugging: understand bugs before fixing.

  • Systematic debugging

    kevinnft/ai-agent-skills/skills/superpowers/systematic-debugging Skill

    13★ repo

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

  • Error handling

    Dragoon0x/everything-design-taste/skills/error-handling Skill

    13★ repo

    Error states, error messages, recovery flows, error prevention, and graceful degradation.

  • Error message writing

    Dragoon0x/everything-design-taste/skills/error-message-writing Skill

    13★ repo

    Error message copy patterns including validation, system errors, and recovery guidance.

  • Diagnose

    devnomad-byte/techneering/skills/diagnose Skill

    13★ repo

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

  • Debug

    kriscard/Skills/skills/dev/debug Skill

    13★ repo

    Debugs errors, test failures, and unexpected behavior with systematic root-cause analysis. Use when the user reports a bug, says "this isn't working", a test is failing, an exception is thrown, output is wrong, or asks to investigate "why does X happen". Applies to frontend, backend, database, network, and performance issues.

  • Test and debug

    olgaiv39/claude-oss-skills/skills/test-and-debug Skill

    13★ repo

    Diagnose and repair a failing test, build, or runtime error in a public open-source project using the narrowest reproduction and validation. Use when something is broken and the cause is not yet known. Classifies the failure, isolates a reproduction, applies the smallest fix, and confirms with a targeted check. Does not add features.

  • Autorun maintainer

    ahundt/autorun/plugins/autorun/skills/autorun-maintainer Skill

    no license12★ repo

    Expertise in maintaining, debugging, and deploying the autorun hook system across Claude Code, Codex CLI, Gemini-family CLIs, Google Antigravity, Qwen Code, ForgeCode, custom harnesses, and desktop app integrations. Use when the user asks to "fix hooks", "deploy autorun", "debug hook errors", "update autorun version", or when troubleshooting "invisible failures" where safety guards appear inactive, piped commands are blocked, or work appears to have "reverted" after a session.

  • Debug hunt

    Flagrare/agent-skills/plugins/flagrare/skills/debug-hunt Skill

    no license12★ repo

    Evidence-first debugging for bugs that are hard to reproduce, intermittent, performance-related, or where previous static-analysis fixes have failed. Declares an explicit goal via /goal (the bug no longer reproduces), then loops through Hypothesis → Instrument → Reproduce → Analyze → Fix until that goal is met. Uses ATDD via /flagrare:atdd-plan to write the fix when the codebase has tests. Triggers when the user reports a difficult bug, says 'this only happens sometimes', 'my fix didn't work', 'I can't reproduce this consistently', 'what's causing this crash', 'hunt this bug down', 'there's a weird bug', 'something is broken intermittently', 'debug-hunt', or describes runtime behaviour that diverges from what the code says should happen.

  • Bug report

    IdoCohen560/claude-unity-game-studio/examples/my-first-game/.claude/skills/bug-report Skill

    12★ repo

    Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.

  • Bug triage

    IdoCohen560/claude-unity-game-studio/examples/my-first-game/.claude/skills/bug-triage Skill

    12★ repo

    Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.

  • Tools unity sentry

    IdoCohen560/claude-unity-game-studio/examples/my-first-game/.claude/skills/tools-unity-sentry Skill

    12★ repo

    Sentry Unity SDK integration patterns for error tracking, performance monitoring, transactions, spans, and custom instrumentation.

  • Unity performance

    IdoCohen560/claude-unity-game-studio/examples/my-first-game/.claude/skills/unity-performance Skill

    12★ repo

    Unity 6 performance profiling and optimization guide. Use when profiling, optimizing frame rate, reducing memory usage, debugging performance bottlenecks, or using the Profiler, Memory Profiler, or Frame Debugger. Based on Unity 6.3 LTS documentation.

  • Uw unity debugging

    IdoCohen560/claude-unity-game-studio/examples/my-first-game/.claude/skills/uw-unity-debugging Skill

    12★ repo

    Systematic 4-phase debugging framework for Unity projects with GameDebug wrapper generation. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Triggers on requests like "this doesn't work", "there's a bug", "it crashes when", "fix this error", "why is this happening", "null reference exception", "test is failing", "unexpected behavior", "something broke", or any debugging task. Four-phase framework (gather evidence, isolate, hypothesize, fix) that ensures understanding before attempting solutions.

  • Bug report

    IdoCohen560/claude-unity-game-studio/game-studios-template/.claude/skills/bug-report Skill

    12★ repo

    Creates a structured bug report from a description, or analyzes code to identify potential bugs. Ensures every bug report has full reproduction steps, severity assessment, and context.

  • Bug triage

    IdoCohen560/claude-unity-game-studio/game-studios-template/.claude/skills/bug-triage Skill

    12★ repo

    Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.

  • Uw unity debugging

    IdoCohen560/claude-unity-game-studio/unity-ai-workflow/.claude/skills/uw-unity-debugging Skill

    12★ repo

    Systematic 4-phase debugging framework for Unity projects with GameDebug wrapper generation. Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes. Triggers on requests like "this doesn't work", "there's a bug", "it crashes when", "fix this error", "why is this happening", "null reference exception", "test is failing", "unexpected behavior", "something broke", or any debugging task. Four-phase framework (gather evidence, isolate, hypothesize, fix) that ensures understanding before attempting solutions.

  • Unity performance

    IdoCohen560/claude-unity-game-studio/unity-knowledge-skills/skills/unity-performance Skill

    12★ repo

    Unity 6 performance profiling and optimization guide. Use when profiling, optimizing frame rate, reducing memory usage, debugging performance bottlenecks, or using the Profiler, Memory Profiler, or Frame Debugger. Based on Unity 6.3 LTS documentation.

  • Console clear logs

    IdoCohen560/claude-unity-game-studio/unity-mcp/Unity-MCP-Plugin/.claude/skills/console-clear-logs Skill

    12★ repo

    Clears the MCP log cache (used by console-get-logs) and the Unity Editor Console window. Useful for isolating errors related to a specific action by clearing logs before performing the action.

  • Console get logs

    IdoCohen560/claude-unity-game-studio/unity-mcp/Unity-MCP-Plugin/.claude/skills/console-get-logs Skill

    12★ repo

    Retrieves Unity Editor logs. Useful for debugging and monitoring Unity Editor activity.

  • Tools unity sentry

    IdoCohen560/claude-unity-game-studio/unity-middleware-skills/skills/tools-unity-sentry Skill

    12★ repo

    Sentry Unity SDK integration patterns for error tracking, performance monitoring, transactions, spans, and custom instrumentation.

  • Debug triage

    iuliandita/skills/skills/debug-triage Skill

    12★ repo

    · Triage a live incident to localize an unknown failing layer, then route. Triggers: incident, outage, triage, production down, crashloop, 502. Not for known-component debugging (systematic-debugging) or repo audits (deep-audit).

  • Diagnostic accuracy

    choxos/BiostatAgent/plugins/r-tidy-modeling/skills/diagnostic-accuracy Skill

    12★ repo

    Diagnostic accuracy analysis in R, including sensitivity, specificity, ROC curves, likelihood ratios, and decision curves.

  • Systematic debugging

    JustMichael-80/MasterVault/skills/superpowers/skills/systematic-debugging Skill

    12★ repo

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

    The same file is in 8 other repositories

  • Code mentor

    serejaris/kimi-skills/skills/code-mentor Skill

    12★ repo

    Comprehensive AI programming tutor offering interactive lessons, code reviews, debugging help, algorithm practice, and project guidance for Python and JavaScript. Triggers when users ask to learn a language, debug code, review their work, practice algorithms, prepare for interviews, or build a project.

  • Incident retrospective

    serejaris/kimi-skills/skills/incident-retrospective Skill

    12★ repo

    线上事故复盘与结构化 Blameless Postmortem 撰写工具,遵循 SRE 最佳实践。帮助用户撰写专业的事故复盘报告,通过六步 SOP 引导完成从时间线梳理、5 Whys 根因分析到制定 SMART 改进措施的全过程,输出格式化的复盘文档。当用户需要撰写事故复盘、进行根因分析(RCA)、创建 blameless postmortem、分析线上故障、制定改进措施(action items)或总结事故教训时触发,常见于提到 postmortem、事故复盘、故障分析、RCA、5 Whys、incident review、故障报告等关键词的场景。

  • Incident review guide

    serejaris/kimi-skills/skills/incident-review-guide Skill

    12★ repo

    Blameless postmortem and incident review writing tool based on SRE best practices. Produces structured incident reports with timelines, root cause analysis (5 Whys), action items, and lessons learned. Trigger when users need to write incident reviews, perform RCAs, analyze production outages, or use keywords like postmortem, incident report, root cause analysis, or 5 Whys.

  • Log diagnostic

    serejaris/kimi-skills/skills/log-diagnostic Skill

    12★ repo

    分析日志文件的错误模式,支持JSON、syslog、Nginx等常见格式,自动检测并输出错误聚类、频率统计和时间分布报告,用于排查问题、定位高发时段。当用户上传.log文件并要求排查错误、分析错误分布、定位高发时段,或提及错误统计、日志分析等关键词时触发。

  • Log error digest

    serejaris/kimi-skills/skills/log-error-digest Skill

    12★ repo

    Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or get distribution stats.

    The same file is in 1 other repository

  • Websearch

    mirkobozzetto/arsenal/plugins/websearch/skills/websearch Skill

    12★ repo

    Power search via Exa MCP. Modes: quick, deep research, code, docs, debug, news, compare. Use when searching the web, finding docs, debugging errors, or researching any topic.

  • Debug move

    pivyme/suiperpower/core/skills/build/debug-move Skill

    12★ repo

    Debug Sui Move compile errors, runtime aborts, or capability leaks. Use when the user has a Move error, abort code, failed PTB, or compiler issue.

  • Scientific debugging

    VidyFoo/antigravity-skill-engine/.agent/skills/2-audit/scientific-debugging Skill

    12★ repo

    科学调试专家 - 观察(Observe) -> 假设(Hypothesize) -> 实验(Experiment) -> 修复(Fix)

  • Investigating builds

    technicalpickles/pickled-claude-plugins/plugins/buildkite/skills/investigating-builds Skill

    12★ repo

    Use when the user is working with an existing Buildkite CI run and wants to understand, diagnose, or act on it. Strong signals: a buildkite.com URL, the word "buildkite", the `bk` CLI, the `bktide` tool, or a reference to a specific pipeline, build, or job. Covers intents like: "why did this build fail", "what's flaking", "summarize pass/fail rates across recent builds", "pull logs for this job", "figure out the exact command CI ran so I can reproduce it locally" (often via docker-compose), "why didn't my downstream build trigger", and debugging `bk`/`bktide` behavior itself (auth failures, query errors, sandbox issues). Do NOT use for authoring pipeline YAML or adding pipeline steps (that's `buildkite:developing-pipelines`). Do NOT use for meta-work on the Claude buildkite plugin itself (editing SKILL.md, reviewing pickled-claude-plugins PRs, adding reference docs under the plugin's directory). Do NOT use for GitHub Actions, PR review, app code changes, git merge conflicts, or local `bk` config (`~/.bk/config.yml`) that don't involve investigating an actual build. This skill reads and investigates CI runs that already exist.

  • Triage

    technicalpickles/pickled-claude-plugins/plugins/git/skills/triage Skill

    12★ repo

    Use when reviewing git state across worktrees, stashes, and branches - helps decide what to clean up, resume, or address

  • Cyber kev triage

    0x-Professor/Agent-Skills-Hub/skills/cyber-kev-triage Skill

    12★ repo

    Prioritize vulnerability remediation using KEV-style exploitation context plus asset criticality. Use for CVE triage, patch order decisions, and remediation reporting.

  • Teamwork debug

    JinPLu/Teamwork/skills/teamwork-debug Skill

    12★ repo

    Use when a request or active workflow encounters a failure, crash, flake, regression, or unexpected result whose cause is still unknown and prevents a safe fix; do not use when the cause and narrow fix are already clear, for general fact finding or design, or when the user asks only for review.

  • Systematic debugging

    takaakit/superpowers-uml/plugins/superpowers-uml/skills/systematic-debugging Skill

    no license12★ repo

    Superpowers-UML modifies Superpowers to ensure a software development workflow in which AI agents design through UML modeling.

  • Agent introspection debugging

    S3YED/appie-kit/skills/agentic/agent-introspection-debugging Skill

    12★ 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

  • Clawflow inbox triage

    S3YED/appie-kit/skills/automation/clawflow-inbox-triage Skill

    12★ repo

    Example ClawFlow authoring pattern for inbox triage. Use when messages need different treatment based on intent, with some routes notifying immediately, some waiting on outside answers, and others rolling into a later summary.

  • Systematic debugging

    S3YED/appie-kit/skills/automation/software-development/systematic-debugging Skill

    12★ repo

    Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

    The same file is in 1 other repository

  • Error handling

    S3YED/appie-kit/skills/ecc/error-handling Skill

    12★ repo

    Patterns for robust error handling across TypeScript, Python, and Go. Covers typed errors, error boundaries, retries, circuit breakers, and user-facing error messages.

    The same file is in 2 other repositories

  • Debugging tools

    S3YED/appie-kit/skills/fleet/debugging-tools Skill

    12★ repo

    Debugging tools for development: pdb, debugpy, and Node.js inspect debugger.

  • Node inspect debugger sd

    S3YED/appie-kit/skills/fleet/node-inspect-debugger-sd Skill

    12★ repo

    Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

    The same file is in 3 other repositories

  • Gws gmail triage

    S3YED/appie-kit/skills/integrations/gws-gmail-triage Skill

    12★ repo

    Gmail: Show unread inbox summary (sender, subject, date).

    The same file is in 1 other repository

  • N8n error handling

    S3YED/appie-kit/skills/integrations/n8n-error-handling Skill

    12★ 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.

  • N8n error handling

    S3YED/appie-kit/skills/integrations/n8n-workflows/n8n-error-handling Skill

    12★ 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

  • Debugging hermes tui commands

    S3YED/appie-kit/skills/misc/debugging-hermes-tui-commands Skill

    12★ repo

    Debug Hermes TUI slash commands: Python, gateway, Ink UI.

  • N8n error handling

    S3YED/appie-kit/skills/misc/n8n-error-handling Skill

    12★ 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.