Git · Debugging

Investigates TiDB plan or test-result diffs that the change does not explain, ruling out failpoint setup and merge effects before expected outputs are updated.

pingcap/tidb

Applies a stop-the-line rule and a step-by-step triage when tests fail, builds break or something stops working, aiming at the root cause instead of guesses.

addyosmani/agent-skills

Audits a module by walking its git history commit by commit, tracking unresolved issues forward, and reporting the ones that survive to HEAD as findings.

ben-manes/caffeine

Has Leon's agent investigate, change and verify code in a repository with its file, search and shell tools, staying inside the scope the owner authorized.

leon-ai/leon

Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test…

google/adk-python

Drive and debug the real keifu TUI autonomously via its remote-control debug server (--debug-listen) — launch headlessly, inject keys/mouse, dump the rendered screen as text, and inspect app state.

trasta298/keifu

When generating a SuperPlane changelog from merged commits. An agent skill from superplanehq/superplane.

superplanehq/superplane

Behavioral guardrails for Codex coding work based on common user complaints.

noobnooc/agent

A skill your agent uses when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation…

sandgardenhq/sgai

Diagnoses a recurring failure such as a stuck task, repeated CI error or frequent reverts by sending sub-agents through the logs and returning one root-cause diagnosis.

yologdev/yoyo-evolve

Development harness for the stax Rust CLI project. An agent skill from cesarferreira/stax.

cesarferreira/stax

Sets up an isolated Burla dev cluster per git worktree so several agents can work in parallel, and explains when to use local-dev or remote-dev.

Burla-Cloud/burla

Debugs a concrete LazyCodex or upstream Codex defect, builds the smallest verified fix in a fresh temporary workspace, and routes the deliverable to the right repository and format.

code-yeongyu/oh-my-openagent

Diagnoses exception root causes from stack traces, logs, call-chain dumps, and debug output using the CodexQA CLI for structured repo analysis.

openqa-cn/codexqa

A skill your agent uses when contributing to the mcpp project — submitting bug fixes, new features, code optimizations, documentation improvements, or any PR.

mcpp-community/mcpp

Systematic root-cause debugging — reproduce, isolate, fix at the source, prove the fix.

gnomeria/usbtree

Evidence-gated diff review for PRs, branches, commit ranges, staged code changes, and merge readiness checks.

lynxlangya/techne

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

Audits a local LazyCodex and Codex CLI install against the latest upstream sources and reports PASS, WARN or FAIL per check without changing anything.

code-yeongyu/oh-my-openagent

The single entry point for the AgentSystem engineering pipeline.

AgentSystemLabs/core

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

blueberrycongee/termcanvas

Build, test, deploy, and troubleshoot Morphe patches — gradle commands, CLI usage, git workflow, common errors and fixes.

Paresh-Maheshwari/morphe-ai

Attempts one alternative fix for a bug, runs the given test command against it and reports what happened, always differing from existing PR fixes.

dotnet/maui

Versioning, branch, and release policy (semantic versioning, branch-per-minor, tag-per-patch).

relytcloud/pg_ducklake

Reproduces a Medusa Cloud build on your machine with mcloud local build, to debug build-failed deployments without pushing or waiting on Cloud.

medusajs/medusa-agent-skills

Workflow for producing auditable Git or jj history for a known compiler bug fix.

purefunctor/purescript-iris

Traces an opaque production error in an OpenWork build to its cause using local server logs and Sentry, names the regressing PR and files a report.

different-ai/openwork

Applies a minimal fix to an emergency bug through triage, root-cause location, a hotfix branch and a blast-radius check, with tests and review still required.

VeryGoodOpenSource/vgv-wingspan

Takes two git tags, compares them, and writes a release changelog in GitHub Markdown format listing new features, bug fixes, known issues, and development doc changes at the very end (strictly…

stormpanda/megingiard

Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code.

rohitg00/skillkit

Sync this fork of @anthropic-ai/claude-agent-acp (packages/agent/src/adapters/claude) with a newer upstream release: bump the claude-agent-sdk / @agentclientprotocol/sdk, port upstream bug fixes and…

PostHog/code

WHEN diagnosing a reproducible or observable software failure outside a CI-pipeline-specific workflow; NOT for speculative cleanup, general code review, or speculative behavior changes presented as…

citypaul/.dotfiles

Automatically rollback changes from failed workflow phases using changes log files.

maslennikov-ig/claude-code-orchestrator-kit

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery.

NVIDIA/skills

Common pitfalls that are slow to troubleshoot and that tend to get "fixed" by going in circles, because the error message points nowhere near the actual cause.

TheDecipherist/claude-code-mastery-project-starter-kit

Walks a person through code changes one step at a time in conversation, starting at the entry point and following the flow that changes, showing a small chunk per step and explaining it in plain…

testdouble/han

AI-assisted coding with Claude Code, Cursor, Copilot, Codex, Aider, or Windsurf.

jamditis/claude-skills-journalism

Configure build-time JavaScript sourcemap upload to Datadog using the Datadog build plugin (@datadog/esbuild-plugin, @datadog/rollup-plugin, @datadog/rspack-plugin, @datadog/vite-plugin…

datadog-labs/agent-skills

Systematically trace bugs backward through call stack to find original trigger.

secondsky/claude-skills

Systematic debugging strategies, troubleshooting methodologies, and problem-solving techniques for code and system issues.

einverne/dotfiles

Hypothesis-driven debugging with ranked hypotheses, git bisect strategy, instrumentation planning, and minimal reproduction design.

Mathews-Tom/armory

Identify bug-introducing commits using semantic analysis that extends traditional SZZ algorithm.

majiayu000/claude-skill-registry

Performs a deep code review of files, modules, a diff, or a branch - finding security vulnerabilities (mapped to OWASP Top 10:2025), correctness bugs, performance problems, and maintainability…

OneWave-AI/claude-skills

Locate root causes of failing regression tests by analyzing code changes, error messages, and test dependencies.

ArabelaTso/Skills-4-SE

Advanced debugging assistance and error analysis. An agent skill from CraftOS-dev/CraftBot.

CraftOS-dev/CraftBot

Structured debugging methodology — reproduce, isolate, hypothesize, verify.

spencerpauly/awesome-cursor-skills