Agent Skills

skill-creator

✓★ 753

by sentry

Alias for sentry-skills:skill-writer. Use when users explicitly ask for "skill-creator" or reference the legacy skill name. Redirects to the canonical skill authoring workflow.

🧰 Not standalone — use together with getsentry/sentry-mcp

create-pr

✓★ 753

by sentry

Alias for sentry-skills:pr-writer. Use when users explicitly ask for "create-pr" or reference the legacy skill name. Redirects to the canonical PR writing workflow.

🧰 Not standalone — use together with getsentry/sentry-mcp

openspec-explore

✓★ 753

by getsentry

Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.

🧰 Not standalone — use together with getsentry/sentry-mcp

openspec-apply-change

✓★ 753

by getsentry

Implement tasks from an OpenSpec change. Use when the user wants to start implementing, continue implementation, or work through tasks.

🧰 Not standalone — use together with getsentry/sentry-mcp

testing-guidelines

✓★ 753

by sentry

Guide for writing tests. Use when adding new functionality, fixing bugs, or when tests are needed. Emphasizes integration tests, real-world fixtures, and regression coverage.

🧰 Not standalone — use together with getsentry/sentry-mcp

openspec-archive-change

✓★ 753

by getsentry

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

🧰 Not standalone — use together with getsentry/sentry-mcp

openspec-sync-specs

✓★ 753

by getsentry

Sync delta specs from a change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change.

🧰 Not standalone — use together with getsentry/sentry-mcp

mcp-qa

✓★ 753

by getsentry

QA MCP tool changes with local CLI and real agent clients. Use when explicitly invoked via /mcp-qa or when asked to QA MCP tool changes end-to-end.

🧰 Not standalone — use together with getsentry/sentry-mcp

mcp-audit

✓★ 753

by sentry

Audit MCP servers for protocol compliance, metadata drift, and compatibility regressions. Use when reviewing tool annotations, tool/result schemas, structured output, lifecycle/init handshake, capabilities, prompts/resources support, transports, auth, security, version drift, or Warden/CI MCP compatibility checks. Trigger phrases include "audit MCP", "check MCP spec compliance", "review tool hints", "validate tools/list", "check initialize handshake", "review prompt or resource capabilities", an

🧰 Not standalone — use together with getsentry/sentry-mcp

teams-dev

✓★ 713

by microsoft

Use this skill whenever the user mentions Microsoft Teams in a development context — whether they're building, integrating, configuring, debugging, or just asking questions. Covers bots, message extensions, embedded web apps, Adaptive Cards, dialogs, SSO, infrastructure, the Teams Developer CLI/SDK, and general Teams platform queries. If the word "Teams" appears, err on the side of invoking this skill.

🧰 Not standalone — use together with microsoft/teams-sdk

mcpc

✓★ 705

by apify

Use the mcpc CLI to work with MCP (Model Context Protocol) servers from the shell - connect to a server as a persistent session, then list and call tools, read resources, get prompts, and run async tasks. Use --json for scripting and code mode. Reach for this whenever interacting with MCP servers, calling MCP tools, or accessing MCP resources programmatically.

🧰 Not standalone — use together with apify/mcpc

record-demo

✓★ 705

by apify

Record or regenerate the mcpc demo GIFs (the README hero docs/images/mcpc-demo.gif and the focused tapes in docs/vhs/) with VHS. Use whenever asked to create, refresh, restyle, shorten, or fix a terminal demo/animation/GIF of mcpc. The tapes drive real mcpc commands; for the authenticated step this skill ALWAYS prompts for a short-lived, low-permission TEST token first (never production). Captures the VHS + mcpc gotchas learned the hard way — read it fully before editing a tape.

🧰 Not standalone — use together with apify/mcpc

cuda-kernels

✓★ 704

by huggingface

Provides guidance for writing and benchmarking optimized CUDA kernels for NVIDIA GPUs (H100, A100, T4) targeting HuggingFace diffusers and transformers libraries. Kernels must be kernel-builder/ABI3-compliant: no pybind11, no setup.py, TORCH_LIBRARY_EXPAND bindings only. Supports models like LTX-Video, Stable Diffusion, LLaMA, Mistral, and Qwen. Includes integration with HuggingFace Kernels Hub (get_kernel) for loading pre-compiled kernels. Includes benchmarking scripts to compare kernel perform

🧰 Not standalone — use together with huggingface/kernels

rocm-kernels

✓★ 704

by huggingface

Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline injection.

🧰 Not standalone — use together with huggingface/kernels

cpu-kernels

✓★ 704

by huggingface

Provides guidance for writing, optimizing, and benchmarking C++ CPU kernels with SIMD intrinsics (AVX2/AVX512) for the Hugging Face kernels ecosystem. Includes a two-phase workflow: Phase 1 correctness (generic → AVX2) and Phase 2 performance exploration (AVX512 with branching trial loop), runtime CPU dispatch, OpenMP threading, and brgemm integration for GEMM-heavy kernels.

🧰 Not standalone — use together with huggingface/kernels

xpu-kernels

✓★ 704

by huggingface

Provides guidance for writing, optimizing, and benchmarking Triton kernels for Intel XPU GPUs (Battlemage/Arc Pro B50) using the Xe-Forge optimization framework. Includes an LLM-driven trial-loop workflow (analyze, validate, benchmark, profile, finalize), XPU-specific patterns (tensor descriptors, GRF mode, tile swizzling), KernelBench fused kernels, and Flash Attention.

🧰 Not standalone — use together with huggingface/kernels

logging-best-practices

✓★ 617

by neondatabase

Logging best practices focused on wide events (canonical log lines) for powerful debugging and analytics

🧰 Not standalone — use together with neondatabase/mcp-server-neon

claimable-postgres

✓★ 617

by neondatabase

Provision instant temporary Postgres databases via Claimable Postgres by Neon (pg.new) with no login, signup, or credit card. Use when users ask for a quick Postgres environment, a throwaway DATABASE_URL for prototyping/tests, or "just give me a DB now". Triggers include: "quick postgres", "temporary postgres", "no signup database", "no credit card database", "instant DATABASE_URL".

🧰 Not standalone — use together with neondatabase/mcp-server-neon

flags-sdk

✓★ 606

by vercel

Guide for feature flags and A/B tests with the Flags SDK (`flags` npm package) and Vercel Flags. Use when: declaring flags with `flag()`, using `vercelAdapter` or `vercel flags` CLI (add, list, enable, disable, inspect, archive, rm, sdk-keys), setting up providers/adapters (Vercel, Statsig, LaunchDarkly, PostHog, GrowthBook, Hypertune, Edge Config, OpenFeature, Split, Flagsmith, Reflag, Optimizely, or custom adapters), implementing precompute patterns for static pages, setting up `identify`/`ded

🧰 Not standalone — use together with vercel/flags

create-payment-credential

✓★ 602

by stripe

Gets secure, one-time-use payment credentials (cards, tokens) from a Link wallet so agents can complete purchases on behalf of users. Use when the user says "get me a card", "buy something", "pay for X", "make a purchase", "I need to pay", "complete checkout", or asks to transact on any merchant site. Use when the user asks to connect or log in to or sign up for their Link account.

🧰 Not standalone — use together with stripe/link-cli

pr-review-comments

✓★ 542

by microsoft

Guide for submitting/posting inline PR review comments to GitHub. Use this when you need to post code review comments on specific lines of a Pull Request.

🧰 Not standalone — use together with microsoft/semantic-link-labs

planning-with-files

✓★ 542

by microsoft

**USE THIS FOR COMPLEX TASKS.** Implements Manus-style file-based planning for multi-step tasks. Creates task_plan.md, findings.md, and progress.md in .agent_cache/<task-name>/. Use when: implementing multiple APIs, refactoring modules, research tasks, or ANY task requiring >5 tool calls.

🧰 Not standalone — use together with microsoft/semantic-link-labs

github-repo-explore

✓★ 542

by microsoft

Guide for searching and exploring external GitHub repositories using the gh CLI. Use this when you need reference implementations, patterns, or code examples from open-source projects to help complete your task.

🧰 Not standalone — use together with microsoft/semantic-link-labs

gh-stack

✓★ 511

by github

Manage stacked branches and pull requests with the gh-stack GitHub CLI extension. Use when the user wants to create, push, rebase, sync, navigate, or view stacks of dependent PRs. Triggers on tasks involving stacked diffs, dependent pull requests, branch chains, or incremental code review workflows.

🧰 Not standalone — use together with github/gh-stack

test-skill

✓★ 347

by getsentry

A test skill for integration tests

🧰 Not standalone — use together with getsentry/warden

test-skill-b

✓★ 347

by getsentry

Test skill B for integration tests

🧰 Not standalone — use together with getsentry/warden

testing-guidelines

✓★ 347

by sentry

Guide for writing tests. Use when adding new functionality, fixing bugs, or when tests are needed. Emphasizes integration tests, real-world fixtures, and regression coverage.

🧰 Not standalone — use together with getsentry/warden

security-review

✓★ 347

by getsentry

Finds exploitable application security vulnerabilities in code changes. Use for Warden security scans, appsec review, OWASP-style checks, authentication or authorization bugs, injection, XSS, SSRF, path traversal, secrets, unsafe crypto, webhook verification, open redirects, or sensitive data exposure.

🧰 Not standalone — use together with getsentry/warden

agent-prompt

✓★ 347

by sentry

Reference guide for writing effective agent prompts and skills. Use when creating new skills, reviewing prompt quality, or understanding Warden's prompt architecture.

🧰 Not standalone — use together with getsentry/warden

code-review

✓★ 347

by getsentry

Finds real correctness bugs in code changes. Use for adversarial code review, bug hunts, regression review, PR correctness review, logic errors, data loss, race conditions, state bugs, interface contract breaks, error handling bugs, edge cases, broken builds, or broken workflows. Excludes style, readability, architecture, AppSec, and best-practice-only feedback unless the issue causes a demonstrable bug.

🧰 Not standalone — use together with getsentry/warden