Root cause analysis

Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.

automagik-dev/genie

A skill your agent uses when the user has a known, already-observed anomaly in their data — a metric spike or drop, an outlier, an unexpected number — and wants its root cause diagnosed, not guessed.

gaasher/Agent-Loop-Skills

Diagnose why a product metric changed (dropped, spiked, or plateaued) by orchestrating breakdowns, actors, paths, lifecycle, retention, and annotations queries.

PostHog/posthog

Full workflow for fixing a GitHub issue - understand the problem, reproduce, diagnose root cause, fix, test on iOS/Android simulators, review, and raise a PR

Shopify/flash-list

Traces a failing call or callback between C# and the native Android or iOS wrappers of the AppsFlyer Unity plugin to find the first broken link.

AppsFlyerSDK/appsflyer-unity-plugin

ALWAYS use this skill in the beginning of any incident investigation, root cause analysis, or operational troubleshooting.

aws/tools-for-devops-agent

Triage a GitHub issue using diagnostics archives and logs. An agent skill from homebridge-plugins/homebridge-eufy.

homebridge-plugins/homebridge-eufy

Diagnoses which of three failure modes a stalled AI-assisted build is in, then chooses a targeted fix, a hard reset or a rethink instead of more prompting.

jsmastery-pro/jsm-agent-skill

Check gate status for a Bitbucket PR by resolving the PR head commit, finding the gate merge commit, inspecting builds on that merge commit, and summarizing root-cause failures with actionable next…

oracle/graalpython

Walks an agent through an evidence-first incident investigation across logs, metrics, code and screenshots, from first symptom to the smallest safe mitigation.

madebyaris/advance-minimax-m3-cursor-rules

Log a concrete issue (bug, technical debt, open design problem, or retire candidate) into tracker/ with elaboration — symptoms/impact, affected code links, root-cause notes, fix approaches, and…

cdiggins/plato

Runs a Five Whys root cause analysis, asking why repeatedly from the stated problem until it reaches an actionable cause, then lists corrective actions and verification.

neurofoo/agent-skills

End-to-end Dynatrace alerting lifecycle — anomaly detector setup and model selection (static threshold, adaptive baseline, seasonal baseline), alert event storage in Grail, problem grouping and…

Dynatrace/dynatrace-for-ai

Internal — for Boundless team members only. An agent skill from boundless-xyz/boundless.

boundless-xyz/boundless

Performs systematic root cause analysis to identify the true source of bugs, errors, and unexpected behavior through structured investigation phases — not just treating symptoms.

rohitg00/skillkit

Diagnose and fix GitHub Actions CI failures. An agent skill from warpdotdev/oz-skills.

warpdotdev/oz-skills

Save completed analyses to the knowledge system's analysis archive for future reference.

ai-analyst-lab/ai-analyst

A skill your agent uses when the user has concrete failing cases in code or a guardrail/classifier/filter/prompt/API they own — a red-team failure catalogue OR a CI/CD test-failure report (failing…

gaasher/Agent-Loop-Skills

Answers questions about code structure, history, bugs and PR risk using a CodeScope knowledge graph and semantic index built from the repository.

QwenLM/qwen-code

Diagnose ambiguous failures before editing. Use for unknown causes, intermittent behavior, performance regressions, or investigations needing…

JuliusBrussee/caveman

Analyze a failing E2E test, determine root cause, and fix it using Playwright Test Agents and RHDH project conventions

redhat-developer/rhdh

Apply when debugging. An agent skill from cursor/plugins.

cursor/plugins

Run scoped OpenClaw issue/PR repair campaigns: coordinate workers, prove root causes, and land or close verified work under the requested authority.

openclaw/openclaw

Investigates a LazyCodex or Codex CLI defect, decides which GitHub repository owns it, and drafts an evidence-backed issue or pull request with repro steps.

code-yeongyu/oh-my-openagent

Runs a parallel security audit with three vulnerability hunters and two proof-of-concept engineers, rating each finding by whether it is actually exploitable.

code-yeongyu/oh-my-openagent

Investigates a failed GitHub Actions run from its URL: pinpoints the real failure, checks the job's history for flakiness, and finds the breaking commit and any existing fix PR.

ykdojo/claude-code-tips

Traces intermittent UI, stale state, ordering and navigation bugs through a browser to find the first boundary where correct data becomes wrong.

lobehub/lobehub

Project-wide engineering principles for VibeX. An agent skill from Xircth/VibeX.

Xircth/VibeX

When a fault is localized and the proximate cause is known but the systemic root is not, chain evidence-linked whys with a counterfactual stop and a countermeasure.

tjboudreaux/cc-thinking-skills

Diagnoses failing ML and AI work, such as OOM, NaN, divergence, crashes, slow throughput, wrong outputs and dependency conflicts, with every claim backed by documentation citations.

Leeroo-AI/superml

A skill your agent uses when a team sees repeated @codex review cycles or Codex Cloud feedback churn and needs root-cause attribution by development stage.

victorGPT/vibeusage

Walks a problem or decision through the OODA loop: observe the facts, orient on causes and assumptions, decide among at least three options, and plan the execution.

neurofoo/agent-skills

End-to-end AscendC custom operator development for Ascend NPU in an ascend-kernel (csrc/ops + build.sh + torchnpu PyTorch custom op) project.

ascend-ai-coding/awesome-ascend-skills

Perform CWE-grounded security code reviews and precise weakness mapping using a locally derived MITRE CWE corpus, relationship graphs, mapping notes, detection methods, mitigations, and schema…

SpecterOps/skills

Runs a hypothesis-driven debugging loop for crashes, hangs and silent failures in any language, grounding every claim in runtime evidence and locking the fix with a test.

code-yeongyu/oh-my-openagent

Analyze MSBuild binary logs to diagnose build failures. An agent skill from rodri-oliveira-dev/Dapper-FluentMap.

rodri-oliveira-dev/Dapper-FluentMap

Systematic debugging skill. An agent skill from blueberrycongee/termcanvas.

blueberrycongee/termcanvas

Route verl-omni training/inference consistency checks through MindStudio's MSProbe collection and root-cause analysis skills.

verl-project/verl-omni

Flaky test fixes: detect nondeterministic tests empirically (repeat/shuffle/parallel runs), diagnose the root cause, fix it — never retry/skip/sleep — and verify across many randomized runs.

maddhruv/absolute

Find recent errors in a Lensflare dataset and summarise their root cause.

voidhashcom/lensflare

Capture, inspect, compare, and root-cause iOS memory graph leaks using Apple's leaks and memgraph tools.

omarshahine/HomeClaw

Android and KMP debugging techniques for crashes, ANRs, memory leaks, R8 traces, Gradle failures and Compose recomposition, built on finding the root cause first.

rcosteira79/android-skills

Read the evidence a nightly UT run produced, decide which failures share a root cause and which are machine breakage rather than product bugs, and write one issue draft per root cause to drafts.json.

intel/torch-xpu-ops

Applies a systematic debugging workflow to errors, exceptions and failures, with error-type tables, localization techniques and reference notes for Python, JavaScript and shell.

Galaxy-Dawn/claude-scholar

Finds which commit broke a failing Swift package suite in the cmux repo by bisecting on CI, then judges per test whether it went stale or the code regressed.

manaflow-ai/cmux

Parallel read-only multi-agent root-cause investigation for bugs, regressions, crashes, flaky behavior, or unexplained failures.

Dimillian/Skills

Structured work modes for agent sessions. An agent skill from 0xNyk/lacp.

0xNyk/lacp

Debugs in four phases (investigate, analyze, hypothesize, implement) under one rule: no fix is made until the root cause is found.

garrytan/gstack