Directory

Discover and filter AI agent skills. 27,776 active skills available.

Popular guides from the directory

Start with intent-focused guides, then come back to the full directory when you need broader coverage.

Results

Showing 1897-1920 of 27,776Page 80 of 1158

laravel-expert

14
from nguyenthienthanh/aura-frog

Laravel/PHP gotchas and decision criteria. Covers N+1 prevention, Eloquent traps, and migration safety.

go-expert

14
from nguyenthienthanh/aura-frog

Go gotchas and decision criteria. Covers error handling patterns, concurrency pitfalls, and interface design.

git-worktree

14
from nguyenthienthanh/aura-frog

Auto-create git worktrees for workflows. Isolate changes, merge on success, discard on failure.

git-workflow

14
from nguyenthienthanh/aura-frog

Token-efficient git operations with security scanning and auto-split commits

failure-classifier

14
from nguyenthienthanh/aura-frog

Classifies execution failures into F1-F5 (transient/local-logic/local-design/story-level/architectural). Outputs JSON with class, confidence, evidence, and recommended action. Deterministic rule-based classifier; no LLM call.

extension-detector

14
from nguyenthienthanh/aura-frog

Detects when a new project-level skill / rule / command would reduce friction. Asks the user for confirmation before creating anything. NEVER writes plugin-level files — only `.claude/skills/`, `.claude/rules/`, `.claude/commands/` in the user's project.

documentation

14
from nguyenthienthanh/aura-frog

Create Architecture Decision Records (ADRs) and Runbooks for operational documentation.

design-expert

14
from nguyenthienthanh/aura-frog

UI/UX design expertise — component design, design system selection, responsive layout. Includes auto-detection from package.json and Context7 integration for library docs.

deep-debugging

14
from nguyenthienthanh/aura-frog

Systematic debugging protocol for bugs that resist quick fixes. Use bisection, hypothesis trees, and scientific method when a bug isn't obvious from the stack trace. Goes beyond bugfix-quick for production-grade root cause analysis.

conflict-detector

14
from nguyenthienthanh/aura-frog

L1-L4 conflict detection between a proposed T4 task and pending-confirm sibling tasks. L1 (file overlap) + L2 (function/region overlap) ship in v3.7.0-beta.2 as deterministic bash. L3 (semantic LLM) + L4 (architectural LLM) are stubbed for v3.7.0-rc.1.

code-simplifier

14
from nguyenthienthanh/aura-frog

Detect and simplify overly complex code. Apply KISS principle - less is more.

code-reviewer

14
from nguyenthienthanh/aura-frog

6-aspect structured code review (security, architecture, error handling, test gaps, type safety, simplification) with calibrated scoring and per-aspect breakdown. Use when the user asks to review code, check a PR, review a pull request, audit changes before merge, or give code feedback.

chain-of-verification

14
from nguyenthienthanh/aura-frog

Draft → generate verification questions → answer independently via tools → revise. Catches hallucinated facts in reports and reviews. MANDATORY for Phase 4 security/test claims. Paper: Dhuliawala et al. 2023.

bugfix-quick

14
from nguyenthienthanh/aura-frog

Fast bug fixes with root cause investigation + TDD. Enforces 'no fix without root cause' discipline and verification protocol. Without this skill, fixes are applied at symptoms instead of sources, and bugs return.

api-designer

14
from nguyenthienthanh/aura-frog

Designs RESTful APIs with endpoint naming, versioning strategies (URL path, header-based), pagination (offset and cursor), error response schemas, and OpenAPI conventions. Use when the user asks about REST API design, creating endpoints, URL structure, API versioning, status codes, Swagger, or OpenAPI specs.

angular-expert

14
from nguyenthienthanh/aura-frog

Angular 17+ gotchas and decision criteria. Covers signals vs observables, standalone patterns, and common pitfalls Claude gets wrong.

agent-detector

14
from nguyenthienthanh/aura-frog

CRITICAL: MUST run for EVERY message. Detects agent, complexity, AND model automatically. Without this, tasks route to wrong agents and use wrong models, degrading quality and wasting tokens.

vana-connect

14
from vana-com/data-connectors

Connect personal data from any web platform using browser automation. Use when: (1) user wants to connect a data source like ChatGPT, Instagram, Spotify, or any platform, (2) user says "connect my [platform]", (3) user wants to generate or update their profile from connected data. Also triggers on: "create a connector for [platform]".

data-connector

14
from vana-com/data-connectors

Build new Vana DataConnect data connectors that export user data from web platforms. Use when asked to "create a connector", "add a connector", "build a connector", "new data connector", "write a connector for X", or when working on the data-connectors repository and the task involves adding or modifying a Playwright-based connector.

auto-create-connector

14
from vana-com/data-connectors

Autonomously create, test, and validate a data connector for any web platform — end to end. Use when asked to "auto-create a connector", "automatically build a connector", or when a connector needs to be created from scratch and tested without manual guidance. Triggers on: "auto-create", "auto connector", "create and test connector", "build connector end to end", "generate connector".

virtualtabs

14
from winterdrive/vscode-virtual-tabs

Manages VS Code editor file groups using VirtualTabs MCP tools. Use this skill when the user wants to organize files into groups, create, rename, or delete groups, add or remove files from groups, manage bookmarks, set sorting rules, auto-group files by extension or date, or explore project structure.

writing-skills

14
from jay6697117/cx-switch

Use when creating new skills, editing existing skills, or verifying skills work before deployment

writing-plans

14
from jay6697117/cx-switch

Use when you have a spec or requirements for a multi-step task, before touching code

web-design-guidelines

14
from jay6697117/cx-switch

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".