LLM commands

1,171 tagged LLM, measured the same way as everything else here.

Browse within: inference 141lm-studio 139Apple Silicon 136benchmark 136claude-code-plugin 130agent-memory 122model-context-protocol 86knowledge-graph 82obsidian 78knowledge-management 72agentic 68gemini-cli 66coding-agent 64agent-framework 61

translate

49

takeshy/obsidian-gemini-helper

Command Claude Code

Translate the following documentation files to all supported languages.

not rated 114 2d ago A 0 tokens original MIT

rp-build-cli

50

gmickel/gno

Command Claude Code

Build with rp-cli context builder → chat → implement.

not rated 110 yesterday A 10 tokens original MIT

dev

51

hnaymyh123-henry/claude-dev-skill

Command

You are an experienced Tech Lead overseeing multiple AI Worker Agents on software projects. The user is the PM / product owner. You drive all technical execution and communicate in natural language.

not rated 106 3mo ago A 0 tokens original MIT

closedloop-ai/claude-plugins

Command Claude Code

You are a release engineer responsible for maintaining the root-level CHANGELOG.md and verifying plugin READMEs. Analyze git changes, update the single CHANGELOG.md following the Keep a Changelog format organized by plugin, and ensure plugin READMEs accurately reflect their contents.

not rated 103 7d ago A 0 tokens original Apache-2.0

story

53

Xiaoyangy/novel-studio

Command

A Chinese-language command that routes vague writing requests to the appropriate web-novel writing, analysis, or ranking tool.

not rated 100 +1 1mo ago A 30 tokens original Apache-2.0

release

54

SFARPak/AliFullStack

Command

Create a new release of the Roo Code extension.

not rated 76 1mo ago A 9 tokens copy · 88% Apache-2.0

security-audit

55

synadia-ai/synadia-agents

Command Claude Code

You are performing a comprehensive security audit of the codebase in the current working directory. Treat this with the rigor of a professional penetration test. Your job is to find real, exploitable vulnerabilities - not style issues.

not rated 76 6d ago B 0 tokens original Apache-2.0

context

56

Reim-developer/Sephera

Command

Build deterministic Markdown or JSON context packs for repository workflows.

not rated 76 5mo ago A 11 tokens GPL-3.0

start-review

57

melagiri/code-insights

Command Claude Code

Command "start-review" from melagiri/code-insights, covering /start-review — triple-layer code review team, step 1: get pr details, get the correct owner from git remote, step 2: select domain specialists and domain classification.

not rated 76 3mo ago A 0 tokens original MIT

pensyve

58

major7apps/pensyve

Command

Route explicit Pensyve memory requests through the bundled MCP server; supports recall, remember, observe, inspect, status, review, forget, and mention-style guidance.

not rated 75 yesterday A 33 tokens

codex

59

mathaix/OpenClawMachines

Command Claude Code

Delegate a task to OpenAI Codex CLI for review or execution.

not rated 57 1mo ago A 0 tokens original Apache-2.0

full-test

62

vertz-dev/vertz

Command Claude Code

Run the full end-to-end validation suite to ensure nothing is broken across the entire project.

not rated 45 4mo ago C 0 tokens original MIT

capture-answer

63

Gixsy95/abap_wiki

Command Claude Code

Ingests an expert's answers to an L2 questionnaire in the abapwiki knowledge base: transforms the answers (filled in the interviews/ file or given verbally) into a canonical citable expert-answer (slices/ /inputs/expert-answers/), moves gaps to 'answered' and closes the questions. Use this skill when the owner/expert…

not rated 44 4d ago A 85 tokens original MIT

lfe-session

65

StChiotis/Library-First-Engineering

Command Claude Code

You are acting as a senior framework architect helping improve the Library-First Engineering (LFE) framework. This is a META session — you are working ON the framework, not WITH it. Do NOT run the LFE pipeline (/lfe-boot, /lfe-architect, etc.) — those are for product repos that use LFE as a template.

not rated 43 1mo ago A 0 tokens original MIT

release-now

66

TOMOSIA-VIETNAM/open-pr

Command Claude Code

Create a git tag + GitHub Release for open-pr — an official release if standing on main, an RC if standing on a branch with an open PR (a dev tool specific to this repo, not shipped in the plugin).

not rated 42 +1 yesterday A 46 tokens original MIT

feature-dev

67

bearlike/Assistant

Command

Guided feature development with codebase understanding and architecture focus.

not rated 41 yesterday A 11 tokens original MIT

issue-implement

68

conorluddy/ContextPods

Command Claude Code

You are tasked with automatically implementing GitHub issues by creating branches, writing code, and opening pull requests with comprehensive solutions.

not rated 39 1y ago A 0 tokens

swarm-hybrid

69

sema-lisp/sema

Command Claude Code

You are orchestrating a multi-agent consensus analysis. You automatically select the right mix of PL designer personas and Sema-specific technical roles based on the problem type.

not rated 41 yesterday A 0 tokens original MIT

new-collection

70

untra/operator

Command Claude Code

Author a new Operator issuetype collection — a shareable AI workflow.

not rated 37 +1 yesterday A 13 tokens original MIT

commit

71

eddmann/intervals-icu-mcp

Command Claude Code

Analyze changes and create a high-quality git commit.

not rated 35 10mo ago A 9 tokens original MIT

ultracode

72

Suraj1235/open-dynamic-workflows

Command

Toggle ultracode mode — every substantive task becomes a planned multi-agent workflow.

not rated 36 +2 1mo ago A 15 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: