agentsclimarketplace
Sign in

Shelves Debug & triage

Root cause

240 rows from 160 repositories

Getting past the symptom to the thing that caused it.

What Root cause skills agree on

117 skill files read, by 120 of the 151 authors on this shelf whose files we hold, 2026-09-06

Counted by distinct author, so one author publishing three of these counts once. Where a claim sits in fewer files than authors, that is said: a claim held by forty authors across three files is one file people copied, not forty people who agreed. Near-identical wordings are grouped and the other wordings are shown, so the grouping is yours to check.

What they tell the agent to do

  1. Add stack trace instrumentation when manual tracing fails8 of 120 in 5 filesalso worded as Add instrumentation when manual tracing fails
  2. Trace backward through the call chain8 of 120 in 5 filesalso worded as Trace backward through the call chain to the original trigger
  3. Use console.error in tests instead of logger8 of 120 in 5 filesalso worded as Use console.error for debug logging in tests; Use console.error not logger in tests
  4. Capture the full call chain with new Error().stack8 of 120 in 5 filesalso worded as Capture the complete call chain with new Error().stack; Capture stack with new Error().stack
  5. Fix the root cause, not the symptom7 of 120also worded as Fix the root cause, not just the symptom; Choose the solution that attacks the root cause, not the symptom
  6. Log before the dangerous operation, not after it fails7 of 120 in 4 filesalso worded as Log before the dangerous operation, not after
  7. Log directory, cwd, environment variables, and stack7 of 120 in 4 filesalso worded as Include directory, cwd, and environment variables in logs; Include directory, cwd, environment variables, timestamps in logs
  8. Add validation at each layer as defense-in-depth6 of 120 in 3 filesalso worded as Add defense-in-depth validation at each layer
  9. Run tests and grep for the debug output6 of 120 in 3 filesalso worded as Run tests and grep the debug output; Run tests and grep for debug output
  10. Analyze stack traces for test file names and line numbers6 of 120 in 3 filesalso worded as Find the triggering test and line number in stack traces; Analyze stack traces for test names and line numbers
  11. Fix at the source, not the symptom5 of 120 in 2 filesalso worded as Fix at the source, not where the error appears
  12. Assign every action item an owner5 of 120also worded as Give every action item an owner, date, issue; Assign every action item an owner and due date
  13. Define the problem before measuring.4 of 120 in 1 file
  14. Run the ten-command triage sweep first.4 of 120 in 1 file
  15. Check errors and saturation before utilization.4 of 120 in 1 file

What they tell it not to do

  1. Never fix just where the error appears9 of 120 in 6 filesalso worded as Never fix where the error appears
  2. Do not blame individuals9 of 120also worded as Blaming individuals; Blaming individuals instead of systems
  3. Do not use logger in tests7 of 120 in 4 filesalso worded as Don't use logger for test debug output; Don't use logger in tests
  4. Do not stop at the symptom7 of 120also worded as Never stop at a symptom; Stopping at symptoms
  5. Never name a person as the root cause7 of 120also worded as naming a human as the root cause; Do not accept a root cause that blames a person
  6. Do not fix the bug5 of 120also worded as Do not treat catching the bug as the fix; Do not fix the symptom
  7. Don't change any code before finding the root cause5 of 120also worded as Don't record a root cause before confirmation; Changing production code before test and root cause are confirmed
  8. Do not change tunables at random until the symptom stops.4 of 120 in 1 file
  9. Do not trust low average utilization to rule out saturation.4 of 120 in 1 file
  10. Do not treat deployment or green dashboards as verification.4 of 120 in 1 file

What they expect to be installed

  1. grep20 of 120 in 17 files
  2. git bisect18 of 120 in 17 files
  3. git14 of 120
  4. git log10 of 120
  5. npm test9 of 120 in 6 files
  6. gh8 of 120
  7. console.error8 of 120 in 5 files
  8. find-polluter.sh7 of 120 in 4 files
  9. new Error().stack6 of 120 in 3 files
  10. git bisect run5 of 120

What they ask it to produce

  1. RCA report9 of 120 in 5 filesalso worded as RCA_Report.md; Full RCA report
  2. Debug stack trace logging6 of 120 in 3 filesalso worded as Instrumented debug logging with stack traces; instrumented debug log with stack trace
  3. Defense-in-depth validation layers5 of 120 in 2 files
  4. Regression test5 of 120also worded as Proposed regression test
  5. Failing test reproducing the bug5 of 120also worded as A failing test reproducing the symptom; Failing regression test pinning the bug
  6. Markdown postmortem document5 of 120also worded as Post-mortem markdown file; Postmortem document
  7. Triage note4 of 120 in 1 file
  8. Postmortem with evidence table4 of 120 in 1 file

When Root cause authors say to reach for one

The situations these authors wrote into their own files, counted out of the same 120 authors, with the skills that name each one

How Root cause skills are built

230 skill directories by 149 authors, read from their repositories’ own file trees 2026-08-05

The middle bundle among those shipping files is 2 files, 10.2 KB beside SKILL.md

Counted by distinct author, same as above, so one author publishing forty template copies counts once. SKILL.md itself is not counted as a file, so a single-file skill is one where that file is the whole skill.

The shape

  1. SKILL.md is the whole skill72 of 149 authors, 124 of 230 skills
  2. files ship beside it77 of 149 authors, 106 of 230 skills
  3. executable scripts ship inside27 of 149 authors, 37 of 230 skills

The folders they converge on

  1. references/34 of 149 authors, 46 of 230 skills
  2. agents/15 of 149 authors, 23 of 230 skills
  3. scripts/13 of 149 authors, 21 of 230 skills
  4. examples/7 of 149 authors, 8 of 230 skills
  5. evals/5 of 149 authors, 5 of 230 skills

  • Analyze and plan

    Optim-Agent/optim-plans/skills/analyze-and-plan Skill

    494★ repo

    Human-in-the-loop planning plugin for Claude and Codex: turn ideas into reviewed Markdown plans, record decisions, enforce explicit execution gates, and provide tested controller primitives for safer agent workflows.

  • Cps rca

    jeannesulzer/international-criminal-tribunals-skills/cps-rca Skill

    no license3★ repo

    International Justice and tribunals

  • After action report

    rampstackco/claude-skills-pm/skills/after-action-report Skill

    3★ repo

    PM-focused 12-skill curated subset of claude-skills. For product managers using Claude Code.

  • A3 problem solver

    manojsurapaneni/manufacturing-ops-skills/a3-problem-solver Skill

    2★ repo

    AI tools that turn 2-hour Toyota A3 reports into 12-second drafts. Built by an ops director, for the people who actually run factories. Free and open-source.

  • Lean bisect

    r-irbe/proof-skills/skills/_overrides/lean-bisect Skill

    2★ repo

    APM-installable agent skills for Lean 4 and Mathlib4 — proof tactics, math domains, review and research workflows, generic tooling.

  • Bisect

    tokyubevoxelverse/bisect Skill

    1★

    Claude Code skill that finds the exact commit that broke it — describe the bug in plain English and it writes the check, drives git bisect in an isolated worktree, and explains why the guilty commit is guilty. 🎯

  • Build intuitive rca wiki

    cskwork/build-intuitive-rca-wiki Skill

    1★

    Turn technical incident RCAs into intuitive standalone HTML wikis for nondevelopers

  • K8gentS — Kubernetes RCA MCP Server

    JDoornink/K8gentS/io.github.JDoornink/k8gents MCP server

    no license1★ repo

    Kubernetes RCA agent that sandboxes its own AI with OPA Gatekeeper. MCP-ready for any client.

  • Debug by bisection

    duliangkuan/cc-clone/examples/demo-brain/skills/debug-by-bisection Skill

    0★ repo

    Clone a Claude Code brain — package/redact/distribute memory, skills, agents & rules; one-click install others' brains; export to Codex/Gemini/Cursor/OpenCode.

  • Continuous improvement opex

    Sofigf/continuous-improvement-opex Skill

    no license0★

  • Git bisect regression

    alexngai/skill-tree/docs/demo/skills/git-bisect-regression Skill

    0★ repo

    Version control and evolution for AI agent skills — versioned storage, dynamic serving/loadouts, multi-agent git sync, and cross-repo federation.

  • Structured root cause research skill

    meiiie/structured-root-cause-research-skill Skill

    0★

    Portable SKILL.md for evidence-based root-cause analysis across Claude Code, Codex, and AI coding agents

  • Root cause analysis

    Rokurolize/codex-skills/skills/root-cause-analysis Skill

    0★ repo

    Reusable Codex Agent Skills by Rokurolize

  • Nutanix aiops

    AIops-tools/Nutanix-AIops/skills/nutanix-aiops Skill

    0★ repo

    Governed Nutanix Prism Central v4 ops: clusters/VMs/storage/DR/LCM, ETag-safe, 47 MCP tools (preview)

  • Inference aiops

    AIops-tools/Inference-AIops/skills/inference-aiops Skill

    0★ repo

    Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 30 MCP tools (preview)

  • Cc sample triage bug

    RobertIonutF/codecurrent-studio-sample/skills/cc-sample-triage-bug Skill

    0★ repo

    Evidence-aware AI workflow sample for software bug triage by CodeCurrent Studio

  • Code root cause

    YZYY95K/test/skills/code-root-cause Skill

    no license0★ repo

    Auditable AgentTeams multi-agent software delivery with contract-driven Skills.

  • RCA-MCP

    dave1362/rca-mcp-connector/io.github.dave1362/rca-mcp-connector MCP server

    0★ repo

    Causal root-cause analysis MCP server -- 56 tools across graphs, RCA models, PyRCA.

  • Analyze root cause

    monte-carlo-data/mc-agent-toolkit/skills/analyze-root-cause Skill

    91★ repo

    Official Monte Carlo toolkit for AI coding agents. Skills and plugins that bring data and agent observability — monitoring, triaging, troubleshooting, health checks — into Claude Code, Cursor, and more.

  • Kubectl investigator

    anyshift-io/sre-skills/skills/kubectl-investigator Skill

    17★ repo

    Open-source library of methodology-shaped SRE skills for AI agents (Apache 2.0)

  • Implementation blueprint

    viacheslav-tronko/claude-code-harness/.claude/skills/implementation-blueprint Skill

    6★ repo

    Claude Code Harness

  • Ko

    rhino-ty/principled-git-commit/lang/ko Skill

    1★ repo

    Claude Code skill: Conventional Commits + best-practice workflow + project-dialect scaffolding. Treats commits as durable history serving four readers — git log scanners, git blame tracers, git bisect hunters, and AI agents.

  • Diagnose root cause

    contextosai/skills/skills/diagnose-root-cause Skill

    1★ repo

    A collection of Agent Skills — self-contained folders that teach AI agents to perform specialized tasks. Includes a production-readiness harness-audit skill, a plugin marketplace, a SKILL.md spec, and CI validation.

  • Bisect driver

    Evan-Daruwalla/claude-skill-suite/bisect-driver Skill

    0★ repo

    Claude Code skills for running models cost-effectively: security gates (secret scanner, commit-gate), model-quality tooling (eval harness, token-squeeze, compact-io, opus-workers), review/advisory (trusted-advisor, audit, skill-vet, research-brief), and a read-only reorg-proposal advisor.

  • Csat root cause

    SkillMedev/customer-support-copilot/skills/csat-root-cause Skill

    0★ repo

    Six skills to resolve faster, escalate smarter, and turn tickets into self-service.

  • Monte carlo analyze root cause

    sickn33/agentic-awesome-skills/plugins/agentic-awesome-skills-claude/skills/monte-carlo-analyze-root-cause Skill

    44,658★ repo

    AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 1,987+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

  • Monte carlo analyze root cause

    sickn33/agentic-awesome-skills/plugins/agentic-awesome-skills/skills/monte-carlo-analyze-root-cause Skill

    44,658★ repo

    AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 1,987+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

  • Monte carlo analyze root cause

    sickn33/agentic-awesome-skills/skills/monte-carlo-analyze-root-cause Skill

    44,658★ repo

    AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 1,987+ agentic skills. Includes CLI, local MCP, catalog, plugins, and Workbench.

  • Incident postmortem

    github/awesome-copilot/skills/incident-postmortem Skill

    37,897★ repo

    Community-contributed instructions, agents, skills, and configurations to help you make the most of GitHub Copilot.

  • Tao analyze changenet rca

    NVIDIA/skills/skills/tao-analyze-changenet-rca Skill

    2,853★ repo

    Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.

  • Debugging patterns

    a5c-ai/babysitter/library/methodologies/cc10x/skills/debugging-patterns Skill

    1,665★ repo

    Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

  • Rca analysis

    a5c-ai/babysitter/library/specializations/domains/business/customer-experience/skills/rca-analysis Skill

    1,665★ repo

    Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

  • Root cause analyzer

    a5c-ai/babysitter/library/specializations/domains/business/operations/skills/root-cause-analyzer Skill

    1,665★ repo

    Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

  • Root cause analyzer

    a5c-ai/babysitter/library/specializations/domains/science/industrial-engineering/skills/root-cause-analyzer Skill

    1,665★ repo

    Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free self-orchestration

  • Structured debug

    codeaholicguy/ai-devkit/skills/structured-debug Skill

    no license1,577★ repo

    The control plane for AI coding agents.

  • Root cause analysis

    rohitg00/skillkit/packages/core/src/methodology/packs/debugging/root-cause-analysis Skill

    1,458★ repo

    Supercharge AI coding agents with portable skills. Install, translate & share skills across Claude Code, Cursor, Codex, Copilot & 40 more

  • Trace and isolate

    rohitg00/skillkit/packages/core/src/methodology/packs/debugging/trace-and-isolate Skill

    1,458★ repo

    Supercharge AI coding agents with portable skills. Install, translate & share skills across Claude Code, Cursor, Codex, Copilot & 40 more

  • Nw five whys methodology

    nWave-ai/nWave/nWave/skills/nw-five-whys-methodology Skill

    591★ repo

    AI agents that guide you from idea to working code, with you in control at every step.

  • Nw five whys methodology

    nWave-ai/nWave/plugins/nw/skills/nw-five-whys-methodology Skill

    591★ repo

    AI agents that guide you from idea to working code, with you in control at every step.

  • After action report

    rampstackco/claude-skills/dist/pi/.agents/skills/after-action-report Skill

    531★ repo

    Stack-agnostic Claude Skills covering the full website lifecycle: brand, design, content, SEO, dev, ops, growth, and research. Build, ship, audit, optimize.

  • After action report

    rampstackco/claude-skills/skills/after-action-report Skill

    531★ repo

    Stack-agnostic Claude Skills covering the full website lifecycle: brand, design, content, SEO, dev, ops, growth, and research. Build, ship, audit, optimize.

  • 03 performance eval global

    minhnv0807/ai-business-skills/skills/en/03-performance-eval-global Skill

    527★ repo

    63 bilingual AI marketing skills (31 VN + 31 Global) for Claude Code, OpenCode, Codex, VS Code. Marketing strategy, content production, performance analytics, personal brand, AI avatar, dropshipping mastery, design master (8 design types). 4 regions (US/EU/SEA/LATAM) + Vietnam 2025-2026. Anthropic-pattern aligned. Companion: opa-kit.

  • Bug diagnose and root cause and fix

    aiskillstore/marketplace/skills/727474430/bug-diagnose-and-root-cause-and-fix Skill

    no license408★ repo

    Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

  • Git advanced

    aiskillstore/marketplace/skills/autumnsgrove/git-advanced Skill

    no license408★ repo

    Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

  • Smart bug fix

    aiskillstore/marketplace/skills/dnyoussef/smart-bug-fix Skill

    no license408★ repo

    Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

  • Root cause tracing

    aiskillstore/marketplace/skills/dyai2025/root-cause-tracing Skill

    no license408★ repo

    Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.

  • Postmortem

    nicepkg/ai-workflow/workflows/product-manager-workflow/.claude/skills/postmortem Skill

    277★ repo

    🚀 170+ pre-built skills for Claude Code, Cursor, Codex & 14+ AI tools. Stop re-teaching your AI the same things. One command → instant domain expertise. Marketing, SEO, Trading, Video, PM workflows included.

  • Monte carlo analyze root cause

    lingxling/awesome-skills-cn/antigravity-awesome-skills/plugins/agentic-awesome-skills-claude/skills/monte-carlo-analyze-root-cause Skill

    238★ repo

    热门Skills中文cn学习版+教程，提供7000+Skills，集成claude skills (11w+Star) | awesome-openclaw-skills (4w+Star) | ui-ux-pro-max-skill (4w+Star)等10余个热门Skill项目

  • Monte carlo analyze root cause

    lingxling/awesome-skills-cn/antigravity-awesome-skills/plugins/agentic-awesome-skills/skills/monte-carlo-analyze-root-cause Skill

    238★ repo

    热门Skills中文cn学习版+教程，提供7000+Skills，集成claude skills (11w+Star) | awesome-openclaw-skills (4w+Star) | ui-ux-pro-max-skill (4w+Star)等10余个热门Skill项目

  • Monte carlo analyze root cause

    lingxling/awesome-skills-cn/antigravity-awesome-skills/skills/monte-carlo-analyze-root-cause Skill

    238★ repo

    热门Skills中文cn学习版+教程，提供7000+Skills，集成claude skills (11w+Star) | awesome-openclaw-skills (4w+Star) | ui-ux-pro-max-skill (4w+Star)等10余个热门Skill项目

  • Root cause tracing

    secondsky/claude-skills/plugins/root-cause-tracing/skills/root-cause-tracing Skill

    204★ repo

    Production-ready skills for Claude Code CLI - Cloudflare, React, Tailwind v4, and AI integrations

  • Bisect aware instrumentation

    ArabelaTso/Skills-4-SE/skills/bisect-aware-instrumentation Skill

    142★ repo

    A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows.

  • Git bisect assistant

    ArabelaTso/Skills-4-SE/skills/git-bisect-assistant Skill

    142★ repo

    A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows.

  • Regression root cause analyzer

    ArabelaTso/Skills-4-SE/skills/regression-root-cause-analyzer Skill

    142★ repo

    A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows.

  • Vulnerability root cause analyzer

    ArabelaTso/Skills-4-SE/skills/vulnerability-root-cause-analyzer Skill

    142★ repo

    A curated list of 180+ useful Claude Skills for Software Engineering and resources for customizing AI for SE workflows.

  • Root cause analysis

    itseffi/agentic-os/.agents/skills/root-cause-analysis Skill

    no license104★ repo

    Agentic personal OS to automate high-leverage workflows with Codex, Claude Code, Pi, OpenClaw and other coding agents/ runtime platforms.

  • Hk rca

    deepklarity/harness-kit/.claude/skills/hk-rca Skill

    89★ repo

    A kit for building with AI agents and also the engineering patterns around it.

  • Postmortem writer

    aAAaqwq/AGI-Super-Team/skills/postmortem-writer Skill

    83★ repo

    14 AI executives powered by legendary minds (Musk/Buffett/Simons/Feynman) — deploy your virtual C-Suite in one git clone.

  • Sp root cause tracing

    aAAaqwq/AGI-Super-Team/skills/sp-root-cause-tracing Skill

    83★ repo

    14 AI executives powered by legendary minds (Musk/Buffett/Simons/Feynman) — deploy your virtual C-Suite in one git clone.

  • Scout

    simota/agent-skills/scout Skill

    71★ repo

    124 specialist AI agents for Claude Code / Codex CLI / Antigravity CLI (agy). Anthropic Agent Skills spec-aligned, gerund-form descriptions, hub-spoke orchestration via Nexus. Covers development, security, design, testing, FinOps, compliance, observability, AI/ML, and more.

All 240 in the catalog