AI & LLM Engineering · Git · For developers

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.

fossasia/eventyay-interpretation

Fix a GitHub issue on OpenPipe/ART and open a PR. An agent skill from OpenPipe/ART.

OpenPipe/ART

Measures and shrinks the ExecuTorch runtime binary by building a size test, analyzing it with bloaty and landing each reduction as its own pull request.

pytorch/executorch

设置 Claude Code hooks，在危险 git commands（push、reset --hard、clean、branch -D 等）执行前阻止它们。适用于用户想防止破坏性 git 操作、添加 git safety hooks，或在 Claude Code 中阻止 git push/reset 时。

vinvcn/mattpocock-skills-zh-CN

Sets up an isolated per-worktree Python environment for attention-gym development using nightly PyTorch and the CI-mirroring uv flow.

meta-pytorch/attention-gym

Run the repository commit workflow when the user explicitly asks to commit changes or create a save-point commit.

Julian-adv/OpenMMO

Adds a new local feature matching model from a GitHub repository to the image-matching-webui project as a working WebUI option.

Vincentqyw/image-matching-webui

Syncs or audits ccLoad's CLIProxyAPI protocol-conversion core and registered provider adapters against one pinned upstream commit, then verifies the result.

caidaoli/ccLoad

在 Paddle 代码库中定位问题并输出高质量调试报告的专用技能。当遇到以下场景时优先使用：(1) Paddle 框架 bug 调试，(2) 算子实现问题排查，(3) 训练脚本异常诊断，(4) 分布式训练故障定位，(5) CUDA/GPU 相关错误处理，(6) 需要生成结构化调试报告。

PaddlePaddle/Paddle

Create, manage, and use E2B sandboxes — run commands, manage files, use git, persist state, and configure networking.

agent-sandbox/agent-sandbox

Review changed code for reuse, quality, and efficiency, then fix any issues found.

truffle-ai/dexto

Open OwnMem Console, the local dashboard for this repository's memory.

grpcer/ownmem

Answer "where did I stop?" for this project. An agent skill from Avijit07x/claude-db.

Avijit07x/claude-db

Walks through releasing a new datadog-lambda-js Lambda layer version — the automated Commercial release (version bump, tag, GitLab sign/publish jobs, npm publish, GitHub release) and the manual…

DataDog/datadog-lambda-js

Turn on Rekal memory in the current repository by running rekal init.

rekal-dev/rekal-cli

Build the standalone ZenDNN native library (zendnnl) from source with the alternate compute backends OFF (no oneDNN, libxsmm, parlooper, fbgemm), keeping AOCL DLP, which is the GEMM backend zendnnl…

amd/ZenDNN

Delegate a coding task to Mistral Vibe and supervise the result via git diff.

pcx-wave/vibe-skill

A skill your agent uses for genuinely high-volume Levyra work such as builds, tests, lint, logs, broad searches, dependency output, Git/GitHub or CodeRabbit inspection, CI diagnostics, agent setup…

LUC4N3X/Levyra-deepsound

A skill your agent uses when opening a PR — produces a clean PR description (what / why / how to verify / risks) from a branch diff against base.

oxbshw/LLM-Agents-Ecosystem-Handbook

Use in a repo with Rekal initialized (.rekal/ exists). An agent skill from rekal-dev/rekal-cli.

rekal-dev/rekal-cli

设置 Claude Code 钩子，在危险 Git 命令（push、reset --hard、clean、branch -D 等）执行前将其拦截。当用户想要防止破坏性 Git 操作、添加 Git 安全钩子或在 Claude Code 中阻止 git push/reset 时使用。

devcxl/mattpocock-skills-zh

Measures the throughput difference between two branches with force-balanced routing.

mlc-ai/pith-train

A skill your agent uses when the user asks to "create an agent catalog", "generate agent catalog source", "build agent catalog from repo", "catalog my agents", or wants to scan a repository…

kubeflow/hub

Install the Rekal binary on this machine. An agent skill from rekal-dev/rekal-cli.

rekal-dev/rekal-cli

A skill your agent uses when the user describes a task and wants to know whether something similar has been done before, then turn the closest prior session into a task playbook.

entireio/skills

GitHub operations via gh CLI: issues, PRs, CI runs, code review, API queries.

swarmclawai/swarmclaw

Sync documentation with project state using ICAV workflow. An agent skill from Netis/heron.

Netis/heron

A checklist for upgrading the pinned ONNX version and opset in ONNX Runtime, covering the files to change, archive hashes, patch rebasing and release-candidate handling.

microsoft/onnxruntime

Checks the Lumen semantic search setup for the current project: embedding service reachability, index freshness and storage totals, with remediation notes.

ory/lumen

Launch and watch Guaardvark's Swarm Orchestrator: parallel coding agents, each in its own git worktree, working a markdown plan and merging back deterministically.

guaardvark/guaardvark

Maintaining packages/phoenix-sqlean, the vendored fork of nalgeon/sqlean.py published as arize-phoenix-sqlean.

Arize-ai/phoenix

對 OpenSpec、Git Diff、frontend、bff、backend、LangGraph、Tool、MCP 與安全邊界進行獨立唯讀審查，輸出 Blocker、Major、Minor 與標準 Verdict。

HsienW/chat-gun

A skill your agent uses when collapsing a feature branch into a single commit before opening or merging a PR.

lbedner/aegis-stack

Critical safety guardrails for protected branches: never commit, push, or force-push directly to main, latest, or release branches; no destructive history rewrites without explicit user approval.

redis/RedisInsight

当系统提示面向编程代理（Coding Agent）场景时调用。适用于构建代码编辑、文件操作、Git 工作流、自动化编程助手的系统提示。不适用于代码解释或教学场景（无文件修改），不适用于 DevOps 基础设施配置（非代码层），不适用于纯对话式代码问答（无工具调用）。

kangarooking/system-prompt-skills

Plan and run local PR validation for tetherto/qvac PRs. An agent skill from tetherto/qvac.

tetherto/qvac

Safety guardrails — blocks destructive commands (rm -rf, DROP TABLE, force-push, git reset --hard) and optionally restricts file edits to a specific directory.

Houseofmvps/ultraship

Run the full implement → test → CI → review → PR pipeline for a task.

tetherto/qvac

Safety guardrails for destructive commands. An agent skill from mr-daedalium/ostack-saas.

mr-daedalium/ostack-saas

A skill your agent uses to promote overlay files and built artifacts into the staged BSP image.

NVIDIA/skills

A skill your agent uses when embedding @mariozechner/pi-coding-agent as a coding-agent runtime in Node scripts, writing pi extensions (plugins) with pi.registerTool / pi.registerCommand / pi.on…

mizchi/skills

Recall prior work from past sessions — how a bug was fixed, what was decided, where a pattern lives.

oliver-kriska/claude-elixir-phoenix