plugins/git-master/skills/git-master/SKILL.md
Complete Git expertise system for ALL git operations. PROACTIVELY activate for: (1) ANY Git task (basic/advanced/dangerous), (2) Repository management, (3) Branch strategies and workflows, (4) Conflict resolution, (5) History rewriting/recovery, (6) Platform-specific operations (GitHub/Azure DevOps/Bitbucket), (7) Advanced commands (rebase/cherry-pick/filter-repo). Provides: complete Git command reference, safety guardrails for destructive operations, platform best practices, workflow strategies, reflog recovery techniques, and expert guidance for even the most risky operations. Always asks user preference for automatic commits vs manual control.
npx skillsauth add JosiahSiegel/claude-plugin-marketplace git-masterInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Comprehensive Git skill covering basic to advanced operations, with mandatory safety guardrails for destructive commands and platform-specific workflows.
When using Edit or Write tools on Windows, use backslashes (\) in file paths, NOT forward slashes (/):
D:/repos/project/file.tsxD:\repos\project\file.tsxApplies to: Edit/Write file_path parameters and all file operations.
NEVER create new documentation files unless explicitly requested by the user. Prefer updating existing README.md files. Keep documentation concise, direct, and professional.
Before ANY destructive operation:
# ALWAYS check status first
git status
git log --oneline -10
# For risky operations, create a safety branch
git branch backup-$(date +%Y%m%d-%H%M%S)
# Remember: git reflog is your safety net (90 days default)
git reflog
User Preference Check (ALWAYS ASK at start of any Git task):
"Would you like me to:
Respect this choice throughout the session.
Activate for ANY Git command or operation including:
Key indicators: user mentions Git, GitHub, GitLab, Bitbucket, Azure DevOps, version control, commit/push/pull/merge/rebase, branch management, history modification, or recovery scenarios.
Before ANY destructive operation (reset --hard, force push, filter-repo, etc.):
See references/dangerous-operations.md for full safety protocols and confirmation scripts.
ALWAYS ask the user preference at the start of any Git task (automatic / stage-only / guidance-only). Respect this choice throughout.
Git behavior differs across platforms and hosting providers:
core.autocrlf), path separators, case sensitivity, Windows Credential Managergh CLI), Azure DevOps (PRs, Pipelines, policies), Bitbucket (PRs, Pipelines, Jira), GitLab (MRs, CI/CD)See references/platform-workflows.md for hosting-specific commands and references/cross-platform.md for Windows/Linux/macOS handling.
This SKILL.md is a lean orchestrator. Detailed command catalogs and procedures live in references/:
| Reference | Contents |
|-----------|----------|
| references/basic-operations.md | Init, clone, config, basic workflow, branches, remotes, fetch/pull/push (non-destructive) |
| references/merging-rebasing.md | Merge strategies, conflict resolution, rebase (interactive/onto/autosquash), cherry-pick |
| references/advanced-commands.md | Stash (incl. Git 2.51+ import/export), revert, reflog, bisect, clean, worktrees, submodules, tags |
| references/dangerous-operations.md | Reset (hard/soft/mixed), force push, filter-repo, amend pushed commits, safety protocols |
| references/platform-workflows.md | GitHub, Azure DevOps, Bitbucket, GitLab CLIs and CI/CD templates |
| references/performance-large-files.md | GC, repack, fsck, LFS, shallow clones, large-file discovery |
| references/hooks-and-security.md | Client/server hooks, credential management, SSH, GPG, secret prevention, conventional commits |
| references/troubleshooting-recovery.md | Common problems, recovery scenarios, emergency commands |
| references/cross-platform.md | Line endings, case sensitivity, Git Bash/MINGW path conversion, shell detection |
| Task | Reference |
|------|-----------|
| git init, git clone, git add, git commit, git log, git diff | basic-operations |
| git branch, git switch, git remote, git fetch, git pull, git push | basic-operations |
| git merge, conflict markers, git rebase -i, git cherry-pick | merging-rebasing |
| git stash, git revert, git reflog, git bisect, git clean, git worktree, git submodule, git tag | advanced-commands |
| git reset --hard, git push --force[-with-lease], git filter-repo, amend pushed | dangerous-operations |
| gh pr, az repos pr, bb pr, glab mr, CI/CD YAML | platform-workflows |
| git gc, git repack, git lfs, shallow clone | performance-large-files |
| .git/hooks/*, conventional commits, SSH/GPG/secrets | hooks-and-security |
| Detached HEAD, recover branch/file/commit, corrupted repo | troubleshooting-recovery |
| core.autocrlf, core.ignorecase, MSYS_NO_PATHCONV, cygpath, $MSYSTEM | cross-platform |
A Git workflow using this skill should:
Combined with the reference files and safety guardrails, this skill provides the knowledge to handle ANY Git operation safely and effectively. Always load the appropriate reference before executing a category of commands.
development
This skill should be used when the user asks to train, debug, scale, or improve ML models. PROACTIVELY activate for: (1) PyTorch, TensorFlow/Keras, JAX, Flax, Hugging Face Trainer/Accelerate training loops, (2) distributed training, DDP/FSDP/DeepSpeed, TPU/GPU setup, (3) mixed precision AMP/bf16, gradient accumulation, checkpointing, seeding, (4) overfitting, imbalance, loss functions, regularization, LR schedules, warmup, (5) memory optimization, gradient checkpointing, offloading, quantization-aware training. Provides: reproducible training best practices across deep learning and classical ML.
development
This skill should be used when the user asks to productionize, track, version, govern, monitor, or automate ML systems. PROACTIVELY activate for: (1) MLflow, Weights & Biases, Neptune, Comet, ClearML experiment tracking, (2) model registry, model versioning, artifact lineage, reproducibility, (3) Kubeflow, SageMaker Pipelines, Vertex AI Pipelines, Azure ML pipelines, Databricks workflows, (4) CI/CD, continuous training/evaluation, A/B tests, canary/shadow deployments, (5) drift detection, model monitoring, data validation, responsible AI governance. Provides: end-to-end MLOps architecture and operational safeguards.
development
This skill should be used when the user asks to optimize, export, serve, compress, or accelerate ML inference. PROACTIVELY activate for: (1) latency, throughput, p95/p99, batching, concurrency, KV cache, memory, or cost issues, (2) quantization INT8/INT4, GPTQ, AWQ, bitsandbytes, pruning, sparsity, distillation, (3) ONNX export, ONNX Runtime, TensorRT, TorchScript, torch.compile, XLA, OpenVINO, Core ML, TFLite, (4) Triton, TorchServe, TF Serving, BentoML, Seldon, KServe configuration, (5) edge deployment, CPU/GPU/TPU/Inferentia serving. Provides: hardware-aware inference optimization and safe benchmarking.
testing
This skill should be used when the user asks to tune hyperparameters, run sweeps, optimize search spaces, or use AutoML. PROACTIVELY activate for: (1) Optuna, Ray Tune, FLAML, AutoGluon, Hyperopt, Nevergrad, KerasTuner, W&B sweeps, (2) grid search, random search, Bayesian optimization, TPE, Gaussian processes, evolutionary search, (3) ASHA, Hyperband, successive halving, multi-fidelity optimization, population-based training, (4) learning-rate finder, batch-size search, early stopping, pruning, (5) reproducible sweep design and experiment analysis. Provides: budget-aware hyperparameter search strategy.