performance-profiling
Analyze system and application performance using Linux kernel-level tools (perf, ftrace, eBPF, SystemTap) and application-level profiling to identify…
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
53,584 results
Analyze system and application performance using Linux kernel-level tools (perf, ftrace, eBPF, SystemTap) and application-level profiling to identify…
Generate local AI images and short media with Draw Things CLI on macOS. Use when you need local txt2img, img2img, model setup, imports, prompt refinement, or…
One-on-one tutoring teacher skill, used to solve math problems, generate HTML explanation documents and Manim animated videos with voiceover. Core workflow: Mathematical analysis → HTML visualization → Storyboard script → TTS audio → Validation update → Scaffolding → Manim code → Render validation Trigger conditions: Students paste images of math problems, need instructional videos, need HTML explanation materials
Interactive installer for Everything Claude Code — walks the user through selecting and installing Skills and Rules into a user-level or project-level directory, validates the paths, and optionally optimizes the installed files.
Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and cross-platform reuse campaigns. Use when the user needs social posts, threads, scripts, content calendars, or clear adaptation of a single source asset to multiple platforms.
An instinct-based learning system that observes sessions through hooks, creates atomic instincts with confidence scores, and evolves them into Skills, Commands, or Agents. Version 2.1 adds project-scoped instincts to prevent cross-project contamination.
Use when writing tests. Use when test structure is unclear. Use when arrange/act/assert phases are mixed.
Use when scanning an AAB or APK for Google Play policy compliance before submission, or checking signing key consistency across releases. Trigger when the user…
Build or extend an extensible UI self-check framework for Web UIs (React/Vite or plain HTML) using Playwright. Use when asked to add/upgrade ui-check or…
Laravel Backend Development Standards. Use this skill when developing Laravel web projects, implementing REST APIs with Eloquent ORM, JWT/Redis token authentication, RBAC…
Provide CI/CD best practices and pipeline templates for GitHub Actions and GitLab CI, recommending configurations based on project type (frontend, backend,…
Diagnose and fix Probe/Nexus health, join failures, and daemon issues. Use for repair dispatch, failed join.md steps, or probe doctor failures.
Execute the dispatched task end-to-end and complete the action after registering a pull request artifact.
Convert one approved idea into an executable project when dispatched a ProjectSetup action.
Clean AI-generated code slop with regression-safe workflow. Activate when user says: deslop, anti-slop, AI slop, cleanup slop, clean up this code, remove bloat.
Claude-Codex-Gemini tri-model orchestration for multi-perspective analysis. Activate when user says: ccg, tri-model, three models, multi-model, cross-validate,…
N coordinated agents on shared task list with staged pipeline. Activate when user says: team, spawn agents, parallel agents, coordinate agents, multi-agent,…
QA cycling workflow - test, verify, fix, repeat until goal met. Activate when user says: ultraqa, qa cycle, fix all tests, make tests pass.
Parallel execution engine for high-throughput task completion. Activate when user says: ulw, ultrawork, parallel execution, run these in parallel.
The **de-AI-ification** expert from 都爆鸭: point out sentence by sentence the places in a Chinese passage that "look AI-written at a glance"—stock connective phrases, "not A but B," three-part parallelism, general-specific-general structure, uniform sentence length, elevated endings, formulaic openings—**by default only produce a diagnostic report, do not revise**; revise only if asked, and attach "what was changed" for each item. **Only remove the AI tone, do not switch platform voice, do not do compliance checks.**…
Check, enable, disable, or restore Codex Skill visibility and loading overhead; do not uninstall the plugin.
Enforces spec-before-code workflow for AI-driven development. Automatically selects Spec-Kit or OpenSpec mode, triages complexity (quick/standard/thorough),…
Astro content-first framework - islands architecture, content collections, file-based routing, SSR/SSG hybrid rendering, View Transitions, server islands,…
Reactive programming with RxJS - Observables, operators, Subjects, error handling, and memory leak prevention