Discover
Discover and install skills, docs, and rules to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
eks itsmostafa/aws-agent-skills AWS EKS Kubernetes management for clusters, node groups, and workloads. Use when creating clusters, configuring IRSA, managing node groups, deploying applications, or integrating with AWS services. | Skills | 84 1.03x Agent success vs baseline Impact 84% 1.03xAverage score across 3 eval scenarios Securityby  Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
temporal-developer temporalio/skill-temporal-developer Develop, debug, and manage Temporal applications across Python, TypeScript, Go, Java and .NET. Use when the user is building workflows, activities, or workers with a Temporal SDK, debugging issues like non-determinism errors, stuck workflows, or activity retries, using Temporal CLI, Temporal Server, or Temporal Cloud, or working with durable execution concepts like signals, queries, heartbeats, versioning, continue-as-new, child workflows, or saga patterns. | Skills | 84 1.03x Agent success vs baseline Impact 96% 1.03xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.5 |
payment-assistant binance/binance-skills-hub Binance Pay Assistant - Send and Receive crypto payments. Send: QR code payment from Funding Wallet (C2C + PIX). Use when user wants to buy/purchase/pay/transfer/send, confirm/cancel payment, or query order status. Requires QR code data. PIX QR codes (pix, br.gov.bcb.pix) are auto-detected. Receive: Generate QR codes and payment links to collect crypto. Use when user wants to receive/collect payment (generate receive link, receive QR). Do NOT use for earning, buying/selling crypto, or digital goods. | Skills | 84 1.75x Agent success vs baseline Impact 100% 1.75xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
building-native-ui expo/skills Complete guide for building beautiful apps with Expo Router. Covers fundamentals, styling, components, navigation, animations, patterns, and native tabs. | Skills | 84 4.13x Agent success vs baseline Impact 95% 4.13xAverage score across 8 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.2 |
git-advanced-workflows Dicklesworthstone/pi_agent_rust Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues. | Skills | 84 1.09x Agent success vs baseline Impact 96% 1.09xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
git-advanced-workflows wshobson/agents Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues. | Skills | 84 1.09x Agent success vs baseline Impact 96% 1.09xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
tessleng/skill-insights v0.12.0 Scan a directory or workspace for SKILL.md files across all agents and repos, capture supporting files (references, scripts, linked docs), dedupe vendored copies, enrich each Tessl tile with registry signals, and emit a canonical JSON inventory validated by JSON Schema. Then run four analytical phases in parallel against the inventory — staleness + git provenance (history, broken refs, contributors), quality (Tessl `skill review`), duplicates (similarity + LLM judgement), registry-search (per-standalone-skill registry suggestions, HTTP only) — and render a self-contained interactive HTML report with a top-of-report health overview, top-issues panel, recently-changed list, and per-tessl.json manifests view. Contains: analyze-skill-quality Score every skill in a discovery.json using `tessl skill review --json` (Tessl's canonical rubric — validation checks + description judge + content judge + 0-100 review score). Pulls tile-level quality directly from registry data already in discovery for tiles scored on the registry. One of three analytical phases that run in parallel after discovery. Use when asked to assess skill quality, find low-quality skills, or surface description / activation issues. analyze-skill-staleness Compute per-skill staleness + git-provenance signals from a discovery.json — git mtime, days since last commit, broken file references (git-history backed), registry-update-available factor for installed Tessl tiles, a 0-100 staleness score per skill, and authorship/contributor data (created_by, last_modified_by, top contributors, recent commits). Fully deterministic, no LLM. One of three analytical phases that run in parallel after discovery. Use when asked to identify stale skills, find skills that haven't been touched in a while, surface skills referencing deleted files, or audit who created/last modified each skill. detect-skill-duplicates Find skills that overlap or duplicate each other across one or more repos. Reads a discovery.json, computes candidate pairs via name+description Jaccard similarity, dispatches one subagent per pair for an LLM duplicate/overlap judgement, then clusters confirmed duplicates transitively. One of three analytical phases that run in parallel after discovery. Use when asked to find duplicate skills, sprawl, near-copies, or overlapping coverage. discover-skills Discover every SKILL.md file across one or more repositories, capture supporting files (references/, scripts/, linked docs, inline-backtick paths), dedupe vendored copies, and enrich each Tessl tile with registry data (quality, security, uplift, eval scores), outdated check, and context-cost analysis. Emits a canonical JSON inventory. Use when asked to inventory skills across a repo or workspace, build a discovery.json, or as the first phase of a skill-estate pipeline. posthog-skill-query Fetch org-wide skill activations, install footprint, MCP-tool calls, and session aggregates from PostHog (the cli:agent-signals event stream emitted by the Tessl CLI) and emit a self-contained org_usage.json plus an interactive HTML report. Standalone — does not read discovery.json or any other phase output, and is not coupled to any particular repo. The output is raw counts only; no buckets, scores, or judgements are encoded in the JSON. Use when asked to pull org-wide skill usage from PostHog, audit cross-team skill adoption, see what skills users have loaded vs activated, look at tessl-MCP tool usage, find skills people are using that this repo doesn't have installed, render an interactive PostHog usage report, or produce the org_usage.json input for the cross-reference step of the skill-insights pipeline. registry-search For every skill in a discovery.json with source_type: "standalone", query the Tessl registry's hybrid search endpoint for the closest matching skill AND the closest matching tile, surface their eval / quality / impact / security scores, and emit the higher-aggregate-score hit as best_match. Output (registry-search.json) is one record per standalone skill, suitable for the report renderer to flag where a published Tessl tile or skill could replace the local one. Stdlib + HTTP only — no LLM, no auth. One of the parallel analytical phases that run after discovery. Use when asked to suggest registry replacements, find similar skills on the registry, or evaluate whether locally-authored standalone skills overlap with published Tessl tiles. run-skill-insights Orchestrate the skill-insights pipeline against one repo, a workspace, or a curated set of repos. Runs discovery, then three analytical phases in parallel (staleness + git provenance, quality, duplicates), then renders a single self-contained interactive HTML report with health overview, top-issues, recently-changed, manifests, and per-skill drill- down drawers. Produces .skill-insights/{discovery,staleness,quality,duplicates}.json plus report.html. Use when someone asks to run skill insights, audit skills, inventory + analyze skills across repos, audit who created/last modified each skill, or kick off a skill-estate scan. | Skills | 84 1.44x Agent success vs baseline Impact 97% 1.44xAverage score across 2 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.12.0 |
x-api joelhooks/joelclaw Read and post to X/Twitter via API. Check mentions, post tweets, search. Use app bearer tokens for read-only fetches and OAuth 1.0a user context for account actions. | Skills | 84 2.25x Agent success vs baseline Impact 99% 2.25xAverage score across 3 eval scenarios Securityby Advisory Suggest reviewing before use Reviewed: Version: 0.0.1 |
otel-ottl dash0hq/agent-skills OpenTelemetry Transformation Language (OTTL) expert. Use when writing or debugging OTTL expressions for any OpenTelemetry Collector component that supports OTTL (processors, connectors, receivers, exporters). Triggers on tasks involving telemetry transformation, filtering, attribute manipulation, data redaction, sampling policies, routing, or Collector configuration. Covers syntax, contexts, functions, error handling, and performance. | Skills | 84 1.14x Agent success vs baseline Impact 95% 1.14xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
langfuse-hello-world jeremylongshore/claude-code-plugins-plus-skills Create a minimal working Langfuse trace example. Use when starting a new Langfuse integration, testing your setup, or learning basic Langfuse tracing patterns. Trigger with phrases like "langfuse hello world", "langfuse example", "langfuse quick start", "first langfuse trace", "simple langfuse code". | Skills | 84 1.53x Agent success vs baseline Impact 83% 1.53xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.2 |
databricks-core-workflow-a jeremylongshore/claude-code-plugins-plus-skills Execute Databricks primary workflow: Delta Lake ETL pipelines. Use when building data ingestion pipelines, implementing medallion architecture, or creating Delta Lake transformations. Trigger with phrases like "databricks ETL", "delta lake pipeline", "medallion architecture", "databricks data pipeline", "bronze silver gold". | Skills | 84 1.68x Agent success vs baseline Impact 91% 1.68xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
consult saadshahd/moo.md Simulates expert perspectives grounded in documented positions. Use when asking "what would [expert] say", "best practice", "panel", "debate", or needing domain guidance. Triggers on expert names, style requests, tradeoff questions, or "stuck on". | Skills | 84 1.54x Agent success vs baseline Impact 79% 1.54xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
building-api-gateway jeremylongshore/claude-code-plugins-plus-skills Create API gateways with routing, load balancing, rate limiting, and authentication. Use when routing and managing multiple API services. Trigger with phrases like "build API gateway", "create API router", or "setup API gateway". | Skills | 84 1.02x Agent success vs baseline Impact 99% 1.02xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.2 |
mcollina/init v0.1.0 Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant. Contains: init Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant. | Skills | 84 1.14x Agent success vs baseline Impact 72% 1.14xAverage score across 5 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.1.0 |
managing-database-testing jeremylongshore/claude-code-plugins-plus-skills This skill manages database testing by generating test data, wrapping tests in transactions, and validating database schemas. It is used to create robust and reliable database interactions. Claude uses this skill when the user requests database testing utilities, including test data generation, transaction management, schema validation, or migration testing. Trigger this skill by mentioning "database testing," "test data factories," "transaction rollback," "schema validation," or using the `/db-test` or `/dbt` commands. | Skills | 84 1.04x Agent success vs baseline Impact 90% 1.04xAverage score across 9 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.3 |
iwsdk-physics facebook/immersive-web-sdk Guide for implementing physics in IWSDK projects. Use when adding physics simulation, configuring rigid bodies, collision shapes, applying forces, creating grabbable physics objects, or troubleshooting physics behavior. | Skills | 84 1.02x Agent success vs baseline Impact 99% 1.02xAverage score across 3 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.1 |
frontend-design boisenoise/skills-collections Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics. | Skills | 84 1.35x Agent success vs baseline Impact 96% 1.35xAverage score across 5 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.4 |
frontend-design freekmurze/dotfiles Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics. | Skills | 84 1.35x Agent success vs baseline Impact 96% 1.35xAverage score across 5 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.4 |
frontend-design douglasvought/wiggle-skills Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics. | Skills | 84 1.35x Agent success vs baseline Impact 96% 1.35xAverage score across 5 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.4 |
frontend-design anthropics/skills Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics. | Skills | 84 1.35x Agent success vs baseline Impact 96% 1.35xAverage score across 5 eval scenarios Securityby Passed No known issues Reviewed: Version: 0.0.4 |
Can't find what you're looking for? Evaluate a missing skill.