826 results · page 3 of 35

agent-delegation

Rules for when and how to spawn sub-agents: Explore for 3+ file reads, parallel agents for independent tasks, summaries only — raw output never enters main context

Claude opencode Skill Screened 18
All 4 from yeisonrestrepo/code-conductor
LLM Mart 1 views

using-mcp-warden

Use when about to make any external HTTP API call, run a deploy command, or read a credential — invokes the `mcp-warden` MCP server (a local credential broker) so secrets never touch the conversation. Fires on requests like "call the GitHub API", "deploy via SSH", "use my Stripe

Claude Skill Screened 14
LLM Mart 1 views

figlens-code-review

Review a figlens change before it becomes a pull request, or review an open pull request. Use whenever the user asks to review a diff, branch, commit range or PR, check a change before opening a PR, or find what a change missed. It checks correctness, the repository's documented

Claude Cursor Skill Screened 21
All 2 from runkids/figlens
LLM Mart 3 views

h3-long-film

使用 H3 制作多镜头完整影片,规划分镜、绑定角色、审片、旁白、剪辑和母版交付。

ava

Use the AVA CLI to analyze CSV, Excel, JSON, and Parquet files, databases, and Feishu Bitable. Use for schema and data-quality checks, read-only SQL queries, transformation and aggregation, metric and trend analysis, clarifying and reusing business definitions, chart recommendati

Claude Skill Screened 1632
LLM Mart 2 views

beautify-github-readme

Redesign GitHub README homepages or create project-native pure SVG, hybrid SVG-composed PNG/WebP, and opt-in animated GIF assets. Use when a user asks to beautify, redesign, rebrand, visually upgrade, simplify, or audit a GitHub README; create only a hero, section headers, diagra

Claude Skill Screened 1964
LLM Mart 2 views

flawless-ui-ux

Create, redesign, refine, or review web, native mobile, and desktop interfaces with product-specific visual design and usable interactions.

Claude Skill Screened 235
LLM Mart 2 views

comprende

Explain code while building it, so the user ends up understanding what was built, why, and how — without drowning them in text. Use this skill whenever you write, change, or walk through code, even if the user doesn't say 'explain' — e.g. 'teach me while you build', 'explain as y

Claude Cursor Skill Screened 65
LLM Mart 1 views

apify-actor-idea-validator

Check whether a planned Apify Actor is worth building before writing code. The user describes the Actor; the skill measures demand (Google Ads search volume and CPC for "<site> scraper / api / mcp / data" keywords, plus the target site's Similarweb traffic), checks for an officia

Claude Skill Screened 295
All 28 from apify/awesome-skills
LLM Mart 2 views

andy-video-director

Unified video-production orchestrator for AI agents. Routes one natural-language video request to BB-Video, Remotion, MoneyPrinterTurbo, Andy video Skills, Manim, Wan/LTX/ComfyUI, WhisperX, and editing engines. Use when the user asks to make, caption, edit, localize, render, or r

genealogy-research-recipes

Investigate genealogy questions with DNA matches and historical records. Use when recovering an ancestor’s identity, parentage or place of origin; reconciling conflicting records or DNA results; searching archives, record sites or family papers; interpreting genetic comparisons;

Claude Skill Screened 29
LLM Mart 2 views

lean-code

Load lean-code for all coding-related tasks: implementing, fixing, refactoring, reviewing, testing, or optimizing code.

Claude Skill Screened 61
All 4 from linsaftw/lean-agents
LLM Mart 1 views

accounts

Let the tool apply on job boards that want an account (Workday today). Use when the user says /accounts or /account, with or without a subcommand (signin, password, add, setup, clear, off, on, forget, gmail), "Workday", "sign in for me", "why are Workday jobs skipped", or asks ab

Claude Skill Screened 356
All 13 from qbeka/jev-job-search
LLM Mart 1 views

Awesome Openclaw Skills CN

OpenClaw Skills 中文精选:2,868 个社区 Skills 分类整理 + 国产模型接入指南(DeepSeek/Qwen/GLM/Moonshot)|Awesome OpenClaw skills in Chinese

Claude Skill Link only
LLM Mart 2 views

channel-analysis

Use when the user wants to analyze a YouTube channel for its positioning, what works, what holds it back, and what to change first. Requires the TubeLab MCP.

add-effects

Use when adding visual effects to a PlayCanvas app, to choose between particle systems, shader chunks, runtime meshes, and post-processing.

Claude Cursor Skill Screened 40
All 16 from playcanvas/skills
LLM Mart 2 views

cancel-jeffy

Use when the user runs /cancel-jeffy to stop the active Jeffy improvement loop in the current project

Claude Skill Screened 13
All 2 from lenamonj/jeffy-loop
LLM Mart 1 views

turkish-humanizer

Türkçe metinleri yapay zeka izlerinden arındırıp doğal bir insan yazısına dönüştürür. Anlamı, sayıları, terimleri ve özel isimleri olduğu gibi korur. Kullanıcı "Türkçeleştir", "insanlaştır", "doğallaştır", "yapay zeka gibi durmasın", "daha doğal yaz", "robot gibi olmuş", "AI koku

Claude Skill Screened 17
LLM Mart 3 views

Axion1 0

Frontier-level agent capabilities with nothing more than high-quality data and a simple training recipe: 2 SFT + RL, no mid-training/DPO/OPD. Full recipe releas…

Claude Skill Link only
LLM Mart 2 views

glowup-ui

Build distinctive new web apps, transform existing frontends, refine interfaces, and implement purposeful UI motion or animation. Use when asked to create an app, redesign a frontend, improve responsive layouts, polish visuals, or implement UI interaction/motion. CREATE establish

Claude Skill Screened 20
LLM Mart 2 views

agent-flow-bootstrap

Interactive agent-flow setup. Scans the repo read-only, proposes AGENTS.md, DOCS_INDEX.md and CONTEXT_MANIFEST.json with a confidence marker per claim, asks the user for protected paths and risk boundaries, writes each file only after approval. Use when setting up agent-flow, whe

Claude Cursor opencode Skill Screened 12
All 10 from drix10/agent-flow
LLM Mart 3 views

capshelf

Use the capshelf CLI to manage shared skills, Pi extensions, subagents, settings, and MCP configs across multiple projects from a user-owned data repo.

autoconsultant

Autoconsultant owns the approval-gated workflow that takes an ambiguous repository change through a persistent Consultant consultation and adversarial plan review, then prepares separately approved, independent Optimizer and Evaluator instructions plus one copy-paste-safe handoff

appstore-rejection

Diagnoses an App Store rejection and drafts the Resolution Center reply. Parses an App Review rejection message (pasted text, a file, or a screenshot), maps every cited guideline (e.g. 'Guideline 2.1 - Performance - App Completeness', '5.1.1(v)', '4.8') and ITMS email error (e.g.