awesome-ai-agent-skills

A curated list of essential skills, tools, and resources for building and enhancing advanced AI agents.

150
Install command
npx skhub add --skillset @thienanblog/awesome-ai-agent-skills

Included Skills

Explore and compare practical options before implementation. Use for requested brainstorming, requirements tradeoffs, diagnosis options, or UI concepts; skip when the approach is already selected.
00
Reproduce, isolate, and fix unexplained failures, regressions, or flaky behavior. Use when the cause is uncertain; a known-cause fix usually needs only the normal implementation workflow.
00
Create, audit, or compact repository instructions in AGENTS.md, scoped overrides, and requested tool compatibility files. Use to preserve non-obvious project rules while removing stale, duplicated, or generic guidance.
00
Create or revise a project design system covering tokens, components, accessibility, motion, and visual verification. Use when the durable design-system document is the deliverable, rather than a one-off UI edit.
00
Create or repair local Docker Compose services, Dockerfiles, mounts, networking, and readiness checks. Use when container configuration is the deliverable; ordinary container commands and production deployment are separate concerns.
00
Create, audit, or consolidate durable project documentation, including feature rules, contracts, workflows, and runbooks. Use when documentation is the main deliverable; routine code changes can update their owning docs directly.
00
Implement changes in Laravel 11 or 12 using the installed framework, frontend, and command runner. Select by composer evidence; Laravel 12-to-13 upgrades use laravel-13-app-guidelines.
00
Implement Laravel 13 changes or upgrade Laravel 12 to 13 using verified package versions and project conventions. Use only for the installed or requested major; optional framework features are not required dependencies.
00
Build or improve operational dashboards, admin tools, CRM/ERP, CRUD, reporting, and record-management interfaces. Use for dense workflows and dashboard reference matching; excludes marketing and unrelated consumer UI.
00
Measure and improve latency, resource use, queries, rendering, or build/test throughput. Use when performance is the primary problem; preserve correctness and compare equivalent workloads.
00
Plan and carry repository changes through implementation, verification, and handoff. Use for project work that needs a general development workflow; select specialist guidance when it adds task-specific value.
00
Deliver an explicitly requested multi-subtask plan as sequential reviewed and verified commits with one aggregate publication path. Use only when the user requests or accepts this workflow; subtasks do not authorize subagents.
00
Design or assess tests, acceptance checks, CI coverage, and browser verification. Use when verification is the main deliverable or requires specialist judgment; ordinary implementation can keep its focused checks inline.
00
Implement a selected mockup, screenshot, or visual reference in an existing project and compare the rendered result. Use when visual fidelity drives the work; use dashboard guidance for operational surfaces when it fits better.
00
Prepare or operate production Docker Compose deployments on a VPS with Traefik, DNS, registries, persistent storage, backups, and rollback. Use for production infrastructure and releases, rather than local development.
00