NeVibeCode · 2,595 skills
Skills for Claude Code, Codex and Cursor
SKILL.md folders the agent loads on its own when a task matches the description.
bug-reproduction-brief
official Turns a vague or intermittent bug report into a minimal reproduction with evidence. Use it when the failure depends on the environment or is hard to repeat.
GitHub Copilot
62installs
qdrant-search-quality
official Diagnoses why Qdrant returns irrelevant matches and points to ways to improve search quality. Useful after an embedding model change or as your data grows.
GitHub Copilot
61installs
qdrant-scaling
official Guides Qdrant scaling decisions across data volume, query throughput, latency, and result payload sizes.
GitHub Copilot
61installs
qdrant-performance-optimization
official This skill maps Qdrant performance work across search speed, index building, and memory use. Use it when a deployment needs a focused performance review.
GitHub Copilot
61installs
qdrant-model-migration
official This skill guides Qdrant embedding-model migrations without taking search offline. Use it when changing providers, vector dimensions, or moving from dense to hybrid search.
GitHub Copilot
61installs
qdrant-deployment-options
official Guides the choice between Qdrant deployment types based on latency, operational overhead, and data residency needs.
GitHub Copilot
61installs
qdrant-clients-sdk
official This skill guides Qdrant integration through official SDKs and APIs. Use it when building with Python, TypeScript, Rust, Go, .NET, or Java.
GitHub Copilot
61installs
product-research Plans user research studies and synthesizes observations with strict evidence thresholds. Distinguishes recurring insights from single-source anecdotes.
Claude Code
213installs
qdrant-monitoring
official Guides Qdrant observability setup and incident diagnostics through metrics. Useful when search requests slow down or memory usage spikes.
GitHub Copilot
60installs
qdrant-version-upgrade
official Provides rules for upgrading Qdrant and its SDK without downtime or data corruption. Helps plan rolling cluster upgrades and multi-version storage migrations.
GitHub Copilot
59installs
efcore-d2-db-diagram
official Generates D2 ER diagrams from Entity Framework Core models. Use it when a database schema must reflect DbContext mappings and migrations.
GitHub Copilot
58installs
andreessen Pressure-tests venture bets and features through Marc Andreessen's market-first frameworks. Cuts out flattery, questions assumptions, and scores product/market fit.
Claude Code
202installs
tiny-stepping
official Enforces an incremental workflow where the assistant makes the smallest meaningful change, pauses for review, and commits before moving forward.
GitHub Copilot
57installs
msgraph-sdk
official This skill connects Microsoft Graph SDK to .NET, TypeScript/JavaScript, or Python projects. Use it when an app needs Microsoft 365 data.
GitHub Copilot
57installs
mvvm-toolkit-messenger
official A GitHub Copilot skill for CommunityToolkit.Mvvm Messenger: wires ViewModels together over pub/sub instead of direct references.
GitHub Copilot
56installs
bigquery-migration-sql-translator
official Translates SQL queries, DDL schemas, and procedures from Oracle, Snowflake, or Redshift to BigQuery GoogleSQL via BQMS. Fits database migration tasks.
Claude Code Gemini CLI CX Codex
45installs
mcp-implementation-security-review
official Audits MCP server and client code against baseline controls, RCE vectors, and the OWASP MCP Top 10, producing file and line evidence.
GitHub Copilot
49installs
python-azure-iot-edge-modules
official Guides the design and deployment of Python Azure IoT Edge modules. Useful for edge telemetry pipelines, protocol translation, and offline message queueing.
GitHub Copilot
47installs
aws-resource-query
official Turn natural-language questions about AWS resources into read-only AWS CLI queries. Use it to inspect infrastructure without changing resources.
GitHub Copilot
47installs
frontend-testing-debugging
official Guides coding agents through structured frontend testing, UI checks, and bug investigations. Runs validation loops using Browser tools or local Playwright.
CX Codex GP ChatGPT
159installs
gitmoji
official Turns a diff or a one-line description into a gitmoji commit message: one emoji for the intent, then a short imperative line. Useful where the repo history already runs on emoji.
GitHub Copilot
46installs
clinical-research Plan a prospective clinical study by selecting endpoints, estimating sample size, and checking feasibility before a phase-gate review.
Claude Code
156installs
slang-shader-engineer
official Guides the assistant in writing, reviewing, and optimizing Slang shader code. Helpful when porting pipelines or integrating Slang into C++ rendering engines.
GitHub Copilot
43installs
bug-receipt
official Closes defects and incidents using a mandatory BUG RECEIPT with VERIFIED, PARTIAL, or BLOCKED status. It stops the agent from guessing repairs.
GitHub Copilot
43installs
aws-cloudwatch-investigation
official Investigation patterns for AWS CloudWatch: Logs Insights query templates, CloudTrail deploy correlation, and a blast-radius decision tree.
GitHub Copilot
43installs
agent-architecture
official Designs AI agent architectures from requirements or audits existing agents for flaws. Focuses purely on architectural decisions and verification without implementing code.
GitHub Copilot
42installs
azure-well-architected-review
official Reviews Azure IaC and deployed resources against the five Well-Architected Framework pillars. Use it to surface risks and track remediation in GitHub issues.
GitHub Copilot
41installs
aws-resource-health-diagnose
official Assesses AWS resource health, analyzes CloudWatch metrics and logs, and builds an actionable remediation plan for outages or performance drops.
GitHub Copilot
40installs
ad-campaign-analyzer
official Analyzes campaign performance data to help decide what to pause, scale, or test. Use it when you have ad results to review, rather than when planning a campaign from scratch.
GitHub Copilot
40installs
research-finance Builds internal R&D program budgets, tracks burn rate and runway, and routes cost items for capitalization or expense review.
Claude Code
133installs
c-level-skills Index and router for a bundle of 33 executive advisory skills across 14 C-suite roles. Helps you find the right advisor and workflow for company decisions.
Claude Code
131installs
research-ops-skills Orchestrator skill for scoping clinical trials, tracking R&D budgets, calculating TAM, and synthesizing user interviews inside a forked context.
Claude Code
130installs
namecheap
official This skill manages Namecheap domain DNS through the API. Use it to change records, switch nameservers, or configure email forwarding.
GitHub Copilot
36installs
setup-my-iq
official An interview-driven skill that writes six markdown files about you: how you work, who is on your team, and how your tools are configured. Useful when the agent lacks that context.
GitHub Copilot
35installs
gem-devops-guidelines
official A set of rules for infrastructure reviews, CI/CD pipelines, Docker, Kubernetes, and rollbacks. Guides production readiness and mobile releases in GitHub Copilot.
GitHub Copilot
35installs
workflow-builder Creates deterministic multi-agent workflow scripts in JavaScript for Claude Code. Useful for coordinating sub-agents in fresh contexts with budget limits and resume support.
Claude Code
119installs
vardoger-analyze
official Reads your GitHub Copilot CLI conversation history and writes a fenced block of personalization rules into the instructions file Copilot already loads.
GitHub Copilot
33installs
repo-standardizer
official Polishes GitHub repository metadata, setting up issue forms, PR templates, CI workflows, labels, and rulesets. Never touches project code logic.
GitHub Copilot
33installs
competitor-ad-intelligence
official This skill finds competitors’ public ads on Meta and Google, then examines their creative and landing pages. Use it to review a paid campaign before launch or look for new ad angles.
GitHub Copilot
33installs
steno-mode
official Compresses agent replies into disciplined shorthand, cutting roughly 40% of response tokens while code, commands, paths and API names stay exact.
GitHub Copilot
32installs
2,241–2,280 of 2,595