Skip to content

Skills

60 reusable skills, prompts and capabilities for leading AI assistants.

Browse all skills

60 skills

A protocol for measuring whether agents can discover and use your tool without being told about it — WITH/WITHOUT trials, binary scoring, and lift as the only metric. The subject under test is your docs, not the model.

5 views
New

SerpApi's official skill for structured search: which of 130+ engines to call for citations, local businesses, flights, hotels, shopping or jobs, which response key holds the answer, and the gotchas that silently return the wrong field.

5 views
New

OpenAI's skill for driving Linear through its MCP server: a read-first workflow for issue triage, sprint planning, documentation audits and workload balancing, with the MCP setup and OAuth steps written out.

6 views

OpenAI's skill for language- and framework-specific secure coding: detect the stack, load the matching reference guidance, then write secure-by-default code, flag critical issues passively, or produce a prioritised vulnerability report with fixes.

2 views

OpenAI's skill for repository-grounded threat modelling: derive trust boundaries, assets and attacker capabilities from the actual code, rank abuse paths by likelihood and impact, and write a reviewable Markdown threat model.

3 views
New

Production review rules for Cloudflare Workers — compatibility dates, observability wiring, and the runtime anti-patterns that only bite at the edge.

3 views

Skill: Turnstile Spin

by Cloudflare

New

Turns “set up Turnstile” into a working end-to-end bot check — widget, frontend snippets, canonical server-side siteverify, and a real validation pass before it reports success.

7 views

Build on @cloudflare/sandbox@next, the Sandbox SDK 1.0 preview — with a package gate that stops an agent mixing preview APIs into a stable app.

6 views
New

Cloudflare's routing skill for Next.js on Workers — sends the agent to vinext, the Vite-based Next.js runtime Cloudflare now recommends ahead of OpenNext.

7 views

Wire up Cloudflare Email Sending and Email Routing — the send_email binding, the inbound email() handler, and the deliverability setup that keeps mail out of spam.

4 views

Skill: Handoff

by Matt Pocock

New

Compress the current Claude Code session into a portable handoff document so a fresh agent can continue the work without re-reading the whole conversation.

6 views

Skill: Stitch: DESIGN.md

by Google Labs (Stitch)

New

Google's official Stitch skill for distilling a project into a DESIGN.md — a semantic design system agents can read before they generate anything.

Anthropic's official skill that appends 2-3 targeted follow-up questions to a substantive answer, prompting the reader to check facts, probe assumptions and spot missing context.

Microsoft's official Azure skill for cost work: query historical spend, forecast it, and hunt down waste like orphaned disks and oversized VMs.

9 views

Official Datadog skill for investigating one flaky test — pulls its history and failure pattern, categorises the root cause and recommends fixing, quarantining or escalating.

5 views

Official Datadog skill that triages a failing PR pipeline, attributing every CI failure as flaky, infra or genuine regression and proposing a targeted fix.

3 views

Official Datadog skill for the pup CLI — OAuth2 login with token refresh, plus a command map covering logs, monitors, traces, metrics, incidents, SLOs, on-call, security signals and audit logs.

7 views

Microsoft's official plugin for building, editing, running and debugging Power Automate cloud flows, with a bundled offline FlowAgent MCP server.

6 views 1 copies

Microsoft's official agent plugin for building, securing and deploying Power Pages code sites, with 34 skills covering the whole site lifecycle.

4 views

Grafana's official Alloy skill: write one collector config that carries metrics, logs, traces and profiles, validate it locally, and prove samples are actually leaving the box.

5 views

Grafana's official k6 skill: generate a load, stress, spike or soak test from a plain-language brief, then actually run the script before handing it over.

7 views

Grafana's official Tempo skill: stand up a tracing backend that needs nothing but object storage, then write TraceQL that finds the slow span instead of scrolling for it.

7 views

Grafana's official Loki skill: write LogQL that returns rows instead of timeouts, ship logs through Alloy, and reason about a store that indexes labels rather than log text.

9 views

Generates or refreshes an NVIDIA governance skill card for an existing agent skill — discovers assets, renders a deterministic markdown card, and blocks submission while human-review markers remain.

6 views

Trains, distils, quantises, evaluates, exports and runs inference for RT-DETR real-time object detection in NVIDIA TAO, routing training through AutoML hyperparameter search by default.

6 views

Inspects the host's hardware, OS, CUDA driver and existing tooling, recommends one Holoscan SDK install method with a reason, then hands off to the matching install skill.

5 views

Runs NVIDIA's NV-Reason-CXR-3B chest X-ray reasoning model through a documented wrapper, locally on GPU or via the public Hugging Face Space, and returns the model's full reasoning trace as engineering evidence.

6 views

Pillar Security's SAIL V2 framework as an agent skill: a 91-risk catalogue across seven lifecycle phases, for AI security gap assessments, roadmaps, and ISO 42001 / EU AI Act compliance checklists.

7 views

A single progressive-disclosure skill for production ROS 2 work — rclcpp/rclpy, colcon, QoS and DDS, tf2/URDF, ros2_control, Nav2, MoveIt 2, plus ROS 1 migration and hardware safety gates.

5 views

Ten SKILL.md modules that give coding agents real ROS engineering judgement — ROS 1 and ROS 2, design patterns, perception, testing, Docker, bringup and robot security.

7 views

Skill: Zeroize Audit

by Trail of Bits

Finds secrets left in memory in C, C++ and Rust — including wipes the compiler deleted — and requires IR or assembly evidence before calling one optimized away.

10 views

Audits npm, PyPI and Go dependencies for advisories, abandoned upstreams, publisher concentration and install-time scripts — measured by scripts, not estimated.

7 views

Compiles cryptographic code and reads the emitted assembly for variable-time instructions, then triages which flagged operations actually touch secrets.

7 views

Callstack's official React Native performance skill: a priority-ordered framework for FPS, time-to-interactive, bundle size, memory leaks and re-render problems.

6 views

Skill: Graphify

by Graphify Labs

Claude Code skill that turns any folder of code, docs, papers and images into a queryable knowledge graph, with every edge tagged as extracted, inferred or ambiguous.

6 views

Skill: GEO-SEO Analysis

by zubair-trabzada

Claude Code skill that audits a site for visibility in AI answers — citability scoring, AI-crawler access, llms.txt, schema markup and brand-mention scanning — plus classic technical SEO.

An output-style skill that stops a coding agent burying the answer: action first, numbered steps, state restated every turn, no preamble or filler.

Tinybird's own datafile and SQL rules for coding agents — datasources, pipes, endpoints, materialized views, deduplication and query optimisation.

6 views

Replicate's official skill for running models via its API — predictions, polling, Prefer: wait, webhooks with signature validation, streaming and file handling.

8 views

Composio's official skill for reaching 1,000+ external apps from an agent — CLI-driven actions, Tool Router sessions, per-user auth and trigger events.

6 views

VoltAgent's official conventions skill — when to reach for an agent versus a workflow, the expected project layout, and the core snippets for agents, workflows, memory and servers.

4 views

How to drive the PlanetScale CLI non-interactively: --format json everywhere, auth check before anything else, pscale sql instead of pscale shell, correct flag placement.

7 views

Skill categories

Browse skills by what they help you do.