43 results · page 1 of 2

3d-generation-harness

Use when: roast it, hazlo con el harness, genera un modelo 3D completo, no des nada por supuesto, production-ready 3D, vanilla-parity rebuild. Owns research→plan→build→roast→ship gates. Not a single mesh or static visual QA: blender-assembly / blender-visual-review.

cost-check

Estimate the monthly cost of a Pulumi or Terraform project with the FinFocus CLI, flag expensive resources, cost increases, and total cost against thresholds in .cost-check.yml, and write a COST_CHECK.md report. Reads machine-readable JSON, checks the CLI version, and names what

Claude GitHub Copilot opencode Skill Screened 11
All 38 from rshade/finfocus
LLM Mart 2 views

dokimi-design-evals

Design, review or repair evals (tasks, verifiers, negative controls, coverage report) for a skill or repository before a dokimi run. Use when asked to write evals, add tasks for a subject, check whether existing evals or graders can be trusted, or state what a suite does not cove

GitHub Copilot Skill Screened 12
All 2 from intel/dokimi
LLM Mart 3 views

make-video

Make videos drawn with code: motion graphics, launch and explainer videos, animated shorts, animated charts and data, logo reveals, social clips, music visualizers, UI demos and GIF loops. Write one HTML page that draws any frame from its time t, render it frame-exact to MP4 with

Claude GitHub Copilot Skill Screened 123
All 3 from bintzgavin/helios
LLM Mart 2 views

operating-system

Supreme policy layer governing all agent behavior. Autonomy, one-line prompt interpretation, speed standards, emphasis signal processing, cross-skill coordination, done definitions, conflict resolution. Loaded every prompt.

Claude Cursor GitHub Copilot opencode Skill Screened 28
All 22 from heymegabyte/agent-skills
LLM Mart 3 views

ai-visibility

Use when you want your product to surface in AI-generated answers (ChatGPT, Perplexity, Gemini) — creates llms.txt, optimizes structured data, and configures AI crawler access for GEO.

Claude GitHub Copilot Skill Screened 49
All 113 from drvoss/everything-copilot-cli
LLM Mart 2 views

context-decay

Revalidate persistent agent knowledge by classifying why it can become stale and how quickly it changes, then retain, revise, externalize, or retire it. Use when reviewing skills, stored instructions, facts, preferences, assumptions, or workflows; when an owner, decision, or depe

Claude GitHub Copilot Skill Screened 336
All 62 from pskoett/pskoett-ai-skills
LLM Mart 3 views

dbops-changeset

Generates Liquibase database changesets via a structured workflow: resolve schema+instance (from context or via API discovery), confirm DB engine type, generate Liquibase YAML, and present for HITL review with Accept / Deny / Accept & Commit actions. Use when asked to create, mod

Claude Cursor GitHub Copilot Skill Screened 134
LLM Mart 3 views

suno-music

Suno music by Ace Data Cloud. Generate songs, instrumental music and lyrics, extend tracks, create covers and edit multitrack Studio projects. Use when the user asks for Suno music or song generation.

Claude GitHub Copilot Skill Screened 17
All 113 from acedatacloud/skills
LLM Mart 3 views

assessing-change-impact

Assessing what a ServiceNow change request touched and what followed it: affected CIs, other changes on the same CIs in an overlapping window, and incidents on those CIs after the change, without trusting hidden incident-to-change links. Use this skill whenever the user asks whet

Claude GitHub Copilot Skill Screened 27
All 8 from jschuller/mcp-server-servicenow
LLM Mart 2 views

architect

Place one slice in the C4 model (LikeC4) by interviewing the driver on each design decision: layer by layer in arc42's views, and a runtime view only for a complex sequence. A short MADR only for a cross-cutting decision. Use after the spec, before code.

Claude GitHub Copilot Skill Screened 22
All 4 from novibe-org/novibe
LLM Mart 4 views

通用-作者风格进化

用于对小说作者做"自我进化"蒸馏:①手动 / 周期回访(挖创作判断、捕获叙述原声(A 类)与创作判断原声(B 类)、周期蒸馏回填"作者小说风格画像"(十层)并反向净化防 AI 自创);②全流程嵌入(选题构思 / 竞品 / 大纲 / 人物 / 背景 / 章节创作等全部环节自动调用,低频环节必采 1–2 问、高频草稿环节只读消费画像);③散落触点(改稿痕迹 / 审阅回流 / 作者窗口 / 口述转写原声);④像不像审计(原声句占比 / 惯用语命中 / 立场显影溯源 / 风格漂移,脚本取数)。与 通用-蒸馏作者文风 组成"静态种子 + 动态进化"双闭环,让写出来

Claude GitHub Copilot Skill Screened 245
All 45 from lornshrimp/lorn.novelwriteskills
LLM Mart 5 views

provider-skill-name

Use this skill for a specific cloud workflow. Mention provider, trigger phrases, expected inputs, and when not to use it.

Claude Cursor GitHub Copilot Skill Screened 24
All 293 from vincentchuwaichow/vanguard-frontier-agentic
LLM Mart 4 views

klaussy-init

Use when the user wants to make this repository AI-agent-ready. Scaffolds per-agent conventions (CLAUDE.md / GEMINI.md / AGENTS.md / Cursor rules / Copilot instructions, path-scoped via klaussy-repo-conventions), repo-namespaced skills, settings, hooks, and a PR template for ever

Claude Cursor GitHub Copilot opencode Skill Screened 16
All 3 from steph-dove/klaussy-agents
LLM Mart 2 views

contributing

Use when contributing to Tel-Agent - picking an issue to work on, setting up the repository for the first time, starting or finishing a task, opening a pull request, or asking "what can I work on" / "how do I start" / "is my change ready to submit". Covers the full path from a fr

Claude Cursor GitHub Copilot Skill Screened 1203
All 2 from dpro-at/tel-agent
LLM Mart 2 views

explore

Use this whenever you need to know what is actually in a database, warehouse, or DuckDB file before you trust it: ranked inventory of what exists, column profiles, PII detection, grain and data-quality problems, verified join inference, Mermaid ER diagrams, guarded ad-hoc SQL pro

Claude Cursor GitHub Copilot Skill Screened 136
All 3 from exmergo/dex
LLM Mart 1 views

operating-system

Supreme policy layer governing all Claude Code behavior. Autonomy, one-line prompt interpretation, speed standards, emphasis signal processing, cross-skill coordination, done definitions, conflict resolution. Loaded every prompt.

Claude Cursor GitHub Copilot opencode Skill Screened 27
All 13 from heymegabyte/claude-skills

preset-admin

Manage Preset teams, workspaces, memberships, invites, role identifiers, seat checks, and audit logs through direct Management API calls. Use only for direct API workflows; Do not use for MCP-only work.

Claude Cursor GitHub Copilot Skill Screened 13
All 26 from preset-io/agent-skills
LLM Mart 2 views

chisle

Maximum-efficiency dev mode. Terse, precise prose with zero fluff combined with YAGNI/ladder-first code decisions. One persona: the senior dev who deletes code for fun and bills by the syllable. Trigger: /chisle. Deactivate: "stop chisle" / "normal mode". Use when user says "chis

Claude Cursor GitHub Copilot opencode Skill Screened 736
All 4 from jaypokale/chisle
LLM Mart 2 views

ai-ready

**ANALYSIS SKILL** — Analyze any repository and generate AI-ready configuration — a canonical AGENTS.md, thin per-tool pointer files, skills, CI workflows, issue templates. WHEN: "make this repo ai-ready", "set up AI config", "add copilot instructions", "prepare this repo for AI

Claude GitHub Copilot Skill Screened 236
LLM Mart 3 views

Babysitter

Babysitter enforces obedience on agentic workforces and enables them to manage extremely complex tasks and workflows through deterministic, hallucination-free s…

Claude ChatGPT Codex CLI Cohere Cursor Gemini GitHub Copilot GLM Grok Mistral Skill Link only
LLM Mart 2 views

anti-entropy-governance

Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or schema/persistence/source-of-truth boundaries; identify opportunities automatically; destructive execution requires explicit confirmation.

Claude Cursor GitHub Copilot opencode Skill Screened 1439
All 21 from ganyuanran/aegis
LLM Mart 2 views

k-dense-ai/scientific-agent-skills

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 190,000+ scientists worldwide. 165 ready-to-use validated skills plus 1…

Claude ChatGPT Codex CLI Cohere Cursor Gemini GitHub Copilot Grok Mistral Skill Link only
LLM Mart 9 views

agent-guardrails

Stop an AI agent damaging your repo: PreToolUse hooks, permission deny rules, protected paths, verification gates. Use when "claude keeps force pushing", "CLAUDE.md says X but it still does Y", "stop the agent touching prod or .env", or making a repo safe for unattended agent wor

Claude Cursor GitHub Copilot Skill Screened 24
All 20 from rainmanjam/poka-yoke
LLM Mart 4 views