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

/commit-push

73

DataCovey/nornweave

Command Cursor

Commit and push all changes from this chat session using Conventional Commits.

not rated 27 4d ago A 18 tokens original Apache-2.0

release

74

corv89/shannot

Command Claude Code

Merge PR, tag release, and create GitHub release with changelog notes using the release skill.

not rated 25 4mo ago A 0 tokens original Apache-2.0

refund-reply

75

bleak-ai/gcontext

Command

Draft a refund reply for a customer, following the support workflow.

not rated 24 11d ago A 12 tokens original MIT

cflx-apply

76

tumf/conflux

Command

Implement an approved OpenSpec change and keep tasks in sync.

not rated 24 2d ago A 12 tokens

audit

78

flashus/detrix

Command Claude Code

Comprehensive code audit with per-crate reports via subagents.

not rated 23 11d ago A 12 tokens original MIT

apply

79

squerne/open-career-skills

Command Claude Code

Full application pipeline for one job: fit evaluation, tailored CV + cover letter, independent review, tracker entry.

not rated 22 28d ago A 21 tokens original MIT

verify

80

zhu-kai/whodecided

Command Claude Code

Typecheck (build) and run the test suite; report the result in one line.

not rated 22 1mo ago A 17 tokens original MIT

brainstorm

81

qingyu321/Little-Claude

Command Claude Code

Guide AI through collaborative requirements discovery before implementation, optimized for AI coding workflows.

not rated 21 10d ago A 0 tokens copy · 100% Apache-2.0

ci-summary

82

ai-debugger-inc/aidb

Command Claude Code

A language-agnostic debugging interface for AI agents.

not rated 21 3mo ago A 0 tokens original Apache-2.0

decomplect-py

83

zby/llm-do

Command Claude Code

Deep architectural analysis for Python code using Rich Hickey's decomplection principles. Evaluates simplicity, functional core/imperative shell, and coupling. Use for design review and architectural assessment.

not rated 20 6mo ago A 45 tokens

mneme-record

84

MnemeHQ/mneme

Command

Record a new architectural decision into project memory.

not rated 20 yesterday A 8 tokens copy · 100% MIT

landing-publish

85

seite-sh/seite

Command Claude Code

Use this command to publish landing pages to the seite site as pages.

not rated 20 20d ago A 0 tokens original MIT

onboard

86

dshakes/compass

Command

Onboard into the current repo — detect stack, install deps, get build+test green, write a grounded CLAUDE.md, and print a codebase map.

not rated 19 4d ago A 33 tokens original MIT

engram-loop

89

staticroostermedia-arch/engram

Command

Parse a /loop input (or equivalent) per the official Grok /loop spec, call native schedulercreate directly (bare XML, never via usetool), record the schedule in Engram (quicktrace + relate to consciousness goal/tile/process), enforce sub-agent governance + subvisor, confirm per spec or scar on failure. One narrow…

not rated 18 28d ago A 77 tokens AGPL-3.0

toon

91

InDate/devharness

Command Claude Code

A lightweight data format designed to minimize token usage when passing structured data to LLMs.

not rated 16 5d ago A 0 tokens original MIT

add-api

92

alifanov/scopegate

Command Claude Code

Add a new API/service integration with OAuth flow and MCP tools to ScopeGate.

not rated 15 2d ago A 15 tokens original MIT

deslop

93

proj-airi/airi-android

Command Cursor

Check the diff against main, and remove all AI generated slop introduced in this branch.

not rated 14 7mo ago A 0 tokens copy · 100% MIT

commit

94

eddmann/obsidian-mcp

Command Claude Code

Analyze changes and create a high-quality git commit.

not rated 14 9mo ago A 9 tokens copy · 100% MIT

humanise-response

96

sonomirco/agents-and-commands

Command

Here’s a prompt to humanise AI essays and text. You can also append your writing sample to further teach ChatGPT to sound more like you.

not rated 12 6mo ago A 0 tokens original Apache-2.0

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: