Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 341 files from 1 736 authors, of which 61 700 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
> On-demand sync of the upgrade working branch with its source branch (typically main) using merge or rebase. Detects divergence, resolves conflicts using upgrade context (prefer upgraded code in files we changed, prefer source elsewhere), validates with a build, and rolls back on any failure. "branch sync", "catch up with source".
> Create, validate, and iteratively improve agent skills that follow Anthropic's best practices. Use this skill whenever someone wants to create a new skill, improve an existing skill, write a SKILL.md, set up a skill directory structure, or needs guidance on skill authoring patterns. Also triggers when users mention "custom instructions", "agent skill", "skill template", or want to codify a workflow into a reusable skill. This skill enforces a create-validate-improve loop that produces production-ready skills passing code review on the first submission.
Generate a persistent final-report.md summarizing everything the scenario changed
How to create plans, scenario-instructions, and progress documents
Discover and present potential modernization (upgrade) opportunities for a solution or set of projects
Generic guidance for presenting scenario completion and next-step recommendations to the user
How to manage workflow state and tasks.md files
Full task lifecycle — assess, break down, execute, validate, complete
How to reconcile tasks.md with plan.md when plan changes are detected
Estimate and present the token-usage budget for an upgrade before execution. Run this when the user directly requests an estimate, or to present a budget that the assessment tool already appended to its output. Never auto-run it after assessment — that path is now handled programmatically by the assessment tool.
> Includes command references, safety boundaries, and the deploy-audit ConfigMaps in osdc-system (what version is running where, who deployed it, when, did it succeed, is a deploy stuck). Applies to ~/meta/ci-infra/osdc. Load when investigating cluster state, debugging pods, inspecting infrastructure, comparing deployed versions across clusters, or diagnosing a failed or stuck deploy.
> OSDC deployment workflow, just recipes, base deploy order, module deploy order, clusters.yaml configuration, Terraform architecture, smoke tests, justfile conventions. Applies to ~/meta/ci-infra/osdc. Load when deploying, adding modules, or modifying deploy scripts.
> OSDC runners, NodePools, BuildKit, GitHub Actions constraints, EKS node taints, image mirroring, and the runner/nodepool change checklist. Applies to ~/meta/ci-infra/osdc. Load when modifying runners, nodepools, BuildKit, or node configurations.
> OSDC PyPI wheel cache module — per-CUDA-slug nginx+pypiserver fanout backed by shared EFS wheelhouse, fed by an external wheel-build pipeline via S3. Covers architecture (4 components), slug naming, EFS PVC, NVMe nginx cache, S3 bucket layout, needbuild override, prebuilt-cache.txt matrix invalidation, njs merge handler, /whl/ rewrites, NetworkPolicy, IRSA roles, log rotation, pod resource computation, cache-enforcer SNI matching. Applies to ~/meta/ci-infra/osdc. Load when developing, debugging, or maintaining the pypi-cache module, investigating pip install failures on runners, adding CUDA versions, or working with the wants/wheel-syncer pipeline.
> Harbor pull-through cache configuration, Helm chart gotchas (inconsistent value paths, per-component image overrides, taint tolerations), and image mirroring strategy. Applies to ~/meta/ci-infra/osdc. Load when working on Harbor, image mirroring, or container registry configuration.
> Grafana Cloud Loki + Mimir queries, label strategy, credential setup, and troubleshooting. Applies to ~/meta/ci-infra/osdc. Load when working on monitoring, logging, Alloy, or querying logs.
> OSDC NodeLocal DNSCache (NLD) base component — per-node CoreDNS DaemonSet under base/kubernetes/nodelocaldns/. Covers iptables-mode rationale (vs IPVS-mode), dynamic kube-dns ClusterIP substitution via deploy.sh (validates the kube-dns ClusterIP is IPv6 and fails fast on IPv4 — OSDC EKS is IPv6-only by design and NLD is single-family by deploy-script enforcement; the IPv6-only cluster recreate has already shipped in commit a6b4c8c), Service-before-DaemonSet apply ordering (KUBE_DNS_UPSTREAM env-var injection), kube-dns-upstream auxiliary Service, two metrics ports (9253 CoreDNS plugin / 9353 binary setup_errors_total), the coredns_nodecache_* vs nodelocaldns_* metric-name confusion, no preStop / no memory limit / no startup taint design decisions, Harbor ≥3-day soak gate (applies to any FUTURE cluster-wide NLD cutover). Applies to ~/meta/ci-infra/osdc. Load when developing, debugging, or maintaining the nodelocaldns base component, investigating DNS issues on runner nodes, modifying its Corefile / DaemonSet manifest, or preparing a future cutover that touches NLD.
> OSDC platform architecture, project organization, directory tree, key design decisions, external knowledge base, key files, and docs index. Applies to ~/meta/ci-infra/osdc. Load when working on OSDC to understand project layout and architecture.
> How PyTorch CI jobs in .github/workflows/ resolve to a specific runner, AND which vs current OSDC ARC-on-EKS) and the dot-vs-dash prefix split (linux./lf./c. = old EC2; mt-/lf-/c-mt- = OSDC ARC). Covers the runner determinator (fleet prefixes mt- default / lf- / c-mt- plus the separate amd-do-), the test-infra #5132 experiment config (lf, amd-do), the now-unconditional EC2->ARC label translation via .github/arc.yaml and map_ec2_to_arc.py (the meta_only_runners H100/B200 override and the onnx exclusion), build-vs-test runner decoupling, and the _runner-determinator.yml / _linux-build.yml / _linux-test.yml flow. Old-infra ownership spans test-infra/terraform-aws-github-runner, test-infra scale-config.yml / lf-scale-config.yml, and pytorch-gha-infra/runners; OSDC ownership lives in the osdc repo (clusters.yaml + modules/arc-runners*). Applies to ~/meta/pytorch. LOAD THIS SKILL for ANY question about PyTorch CI runners, runner labels, test matrices, runs-on values, runner prefixes (mt-, lf-, c-mt-, amd-do-, or legacy linux./lf./c.), WHICH infra a label runs on ("does lf.linux.2xlarge run on ARC or EC2?", "mt- vs lf- vs lf.?", "old ALI vs OSDC runners", "where is this runner defined?"), experiments (lf / amd-do), the determinator, ARC fleet routing, H100/B200/ A100 placement, or how a job gets assigned to a runner pool.
> OSDC tools (tofu, just, mise, crane, uv), automation hierarchy, unit tests, code style and linting rules (13 linters, indentation), "Don't Do" list, and quality gates. Applies to the OSDC project (`osdc/`). Load when writing code, running linters, adding scripts/tests, or debugging and trying to understand issues.
Provision a Redis Cloud database end-to-end — Essentials (fixed plan) or Pro (custom) — using Redis Cloud MCP tools
Profile and explore a Redis dataset - key types, sizes, TTLs, encodings, and sample values
Audit a RediSearch index for health, efficiency, and optimization opportunities
Recommend Redis data structures and patterns for a given workload before committing to an approach
Comprehensive pre-operation health check for a Redis Enterprise cluster — verify cluster state, node health, license status, and active alerts before making changes
Prototype and compare 2-3 Redis data model alternatives for the same workload
Create and compare multiple RediSearch index configurations to find the best one
Analyze a Redis dataset and recommend an optimal RediSearch index schema
Manage Redis Cloud subscriptions, databases, and resources via the redisctl CLI. Use when provisioning, updating, or monitoring Redis Cloud infrastructure.
Connect to Redis databases using the redisctl CLI. Use when opening redis-cli sessions, managing connection profiles, or working with multiple Redis clusters.
Analyze and optimize RediSearch queries using FT.EXPLAIN and FT.PROFILE
Plan and execute a zero-downtime RediSearch index schema migration using aliases
Day-to-day Redis Enterprise cluster operations via the redisctl CLI. Use when checking cluster status, managing databases, viewing stats and logs, or monitoring Active-Active deployments.
Advanced Redis Enterprise administration via the redisctl CLI. Use for RBAC, LDAP, cluster policy, licensing, certificates, proxy management, and diagnostics.
Install and configure redisctl CLI for Redis Cloud, Enterprise, and direct database access. Use when setting up redisctl for the first time, creating profiles, or configuring shell completions.
Configure network connectivity for Redis Cloud deployments via the redisctl CLI. Use when setting up VPC peering, Transit Gateway, Private Service Connect, or PrivateLink.
Multi-step operational workflows combining redisctl commands. Use for end-to-end provisioning, cluster initialization, migrations, and backup and recovery procedures.
Use before every substantive design answer. Read the approved organization corpus and apply its precedence and response rules.
Use when drafting or editing release notes or a changelog entry in the house voice.
Use when drafting or editing a blog post or long-form article in the house voice.
Use when drafting or editing a post or thread for X (Twitter) — voice, hooks, length, threads, hashtags, and links.
Use when drafting or editing a LinkedIn post in the house voice.
Use when drafting or editing an email newsletter issue in the house voice.
Build explorative, interactive learning experiences as Next.js apps using the Geist design system. Use when creating tutorials, explorable explanations, interactive lessons, code sandboxes, quizzes, or any educational UI. Covers the Learning Loop pedagogy, 23+ learning component patterns, progress tracking, spaced repetition, and Bret-Victor-style interactive exploration — all with Geist's dark-first minimal aesthetic.
Convention for the v3 bundle documentation system: a single bundle.dot + bundle.png per repo, generated by bundle_repo_dot(). Use when generating, validating, or interpreting bundle documentation files. Covers 7-cluster DOT structure, token cost model, color conventions, external reference distinction, freshness tracking via source_hash, generation recipes, and the lifecycle model.
> Use when starting work in any repository, and again at each work-phase transition (design, coding, debugging, verification, opening a PR). Loads the canonical per-repo-conventions guidance from PR templates, CONTRIBUTING.md, and contextual files (PRINCIPLES.md, SMOKE_TESTS.md, KNOWN_ISSUES.md), plus the re-read cadence and verification gradient.
Use when creating a new Amplifier module (tool, hook, orchestrator, context, or provider). Covers the mount() contract, protocol compliance validation, placeholder patterns, and the module directory structure. Prevents the common mistake of creating no-op mount() stubs that fail protocol_compliance validation.
Sets up the full Neon SDK with authentication AND database queries in React apps (Vite, CRA). Creates typed client, generates database types, and configures auth UI. Use for auth + database integration.
Sets up Neon Auth in React applications (Vite, CRA). Configures authentication adapters, creates auth client, and sets up UI components. Use when adding auth-only to React apps (no database needed).
Sets up Neon Auth in Next.js App Router applications. Configures API routes, middleware, server components, and UI. Use when adding auth-only to Next.js apps (no database needed).
Write a Twitter/X post or thread based on research findings or a given topic. Use this skill when asked to create tweets, X posts, or social media threads.
Write a LinkedIn post based on research findings or a given topic. Use this skill when asked to create LinkedIn content, professional posts, or thought leadership pieces.
Use when Claude Code is asked to build, run, test, debug, or configure an OpenAI-backed or provider-unspecified AI app, UI, script, CLI, generator, or tool, especially requests phrased only as "using AI" or generators driven by forms/user input; also use for OPENAI_API_KEY or sk-proj setup. Treat this as the credential gate: inspect safely, ask reuse-vs-new before API work, guide manual local setup when needed, verify presence, and never expose plaintext.
Use whenever the user asks anything about OpenAI products, APIs, models, or SDKs — including factual lookups, coding requests, latest/current/default model selection, prompting guidance, model upgrades, and citation requests. Invoke before calling any openaiDeveloperDocs MCP tool.
Use when an OpenAI API request fails or the user asks what an error means, including blocked access to api.openai.com, 401 invalid_api_key, missing OPENAI_API_KEY, 429 insufficient_quota, 429 rate_limit_exceeded, or 403 model_not_found. Classify the failure, name the next step, route credential setup to openai-platform-api-key, and current guidance to openai-docs.
Use when a developer needs a ChatGPT Apps submission import file from an MCP server. Inspect the implementation, generate chatgpt-app-submission.json with app info, tool-hint justifications, positive and negative test cases, then report review findings and outputSchema warnings.
Use when the user wants to build, adapt, run, or evaluate an OpenAI Agents SDK app from Claude Code. Prefer a docs-first workflow and route API credential decisions through openai-platform-api-key before API-backed work.
Use when the user explicitly wants a ChatGPT App, Apps SDK project, MCP server plus widget UI, ChatGPT-compatible tool UI, or submission/deployment work for that surface. Build, scaffold, refactor, or troubleshoot those projects from Claude Code, consult openai-docs before generating code, and use openai-platform-api-key before any app path that requires live OpenAI API credentials.
Add evaluation results to Hugging Face model repositories using the .eval_results/ format. Uses HF CLI for PR management and manual YAML creation.
>- Expert-level implementation assistant for the Universal Commerce Protocol (UCP). Provides comprehensive tooling for adding UCP support to Next.js ecommerce codebases — from initial consultation through full implementation, testing, and validation.
Claude Skills — questions
Answers built from the skills we actually parsed.