cli skills

8,871 tagged cli, measured the same way as everything else here.

Browse within: agent 314bun 250LLM 211ai-coding 150agentic 145coding-agent 128ml 114gemini-cli-extension 96discovery-api 95tui 93agent-swarm 82mimo 80mimo-code 80bash 78

hbg-gemini-flow-suite

457

Mr-funny/hbg-gemini-flow-suite

Skill Claude CodeCodex

Instructions for deploying, authorizing, operating, diagnosing, and updating the Docker-based HBG Gemini Flow Suite. The suite uses Gemini Web and Google Flow/Veo for image and video generation.

not rated 24 +1 29d ago A 90 tokens AGPL-3.0

ez-workflow

458

rohoswagger/ez-stack

Skill Claude CodeCodex

Use when about to run git branching, commit, push, or PR operations in a repo managed by ez-stack. Provides the complete command reference and agent-specific usage patterns.

not rated 24 +1 25d ago A 38 tokens original MIT

xiaohei-info/oh-my-multica

Skill Claude CodeCodex

Use when an architect must run the detailed-design portion of technical design, preserve the full lifecycle-stage doctrine for detailed design, and define the concrete runtime, project, flow, data, interface, non-functional, security, recovery, hardware, and implementation-plan surfaces needed for execution.

not rated 24 yesterday A SkillSpector: warn 65 tokens original MIT

Code Execution

460

winsenlabs/platos

Skill Claude CodeCodex

Run Python, Node.js, AND arbitrary shell commands in a secure E2B cloud sandbox that PERSISTS across calls within a conversation. Clone repos, install packages, run CLI tools (git, psql, ffmpeg, duckdb), and build up state turn over turn.

not rated 24 yesterday A 60 tokens original Apache-2.0

lukas-grigis/ralphctl

Skill Claude CodeCodex

Multi-phase code-quality skill — primary frame for the evaluator role in Execute, the architecture axis in Plan, and correctness/readability in Refine. Multi-axis code review with severity vocabulary. Use when you are the evaluator assessing a generator's output, and when reviewing any change before signalling…

not rated 23 yesterday A SkillSpector: warn 76 tokens original MIT

slipway-run

462

signalridge/slipway

Skill Claude Code

Explicitly start and drive Slipway's interruptible soft autopilot one structured Action at a time.

not rated 23 5d ago A SkillSpector: warn 25 tokens original BSD-3-Clause

use-whatsapp

463

envhaven/envhaven

Skill Claude Code needs its repo

Stand up a personal WhatsApp ↔ Claude Code bridge. The user messages a WhatsApp number from their phone and Claude Code (with full agent loop, file tools, bash) replies. Uses Anthropic subscription auth (no per-token charges). Per-chat session continuity, daily 5am session resets with pre-flush memory extraction…

not rated 23 1mo ago D 167 tokens original MIT

inplan

464

melly-lgtm/inplan

Skill Claude Code

Use for ANY planning, design, PRD, or spec document — always plan in inplan; the user need not say "with me" or "collaboratively". Trigger on "plan X", "let's plan …", "create/write a plan|PRD|spec|design for …", "design Y", or any request pairing planning with a topic (e.g. "plan a tic-tac-toe game"). inplan itself…

not rated 23 12d ago B 174 tokens AGPL-3.0

zotkit

465

oldantique/zotkit

Skill Claude CodeCodex

Use when the user wants to add, create, upload/attach, download/fetch, search, tag, look up by item key, export BibTeX for, or organize references (papers, PDFs) in their Zotero library via the zotkit CLI — headless Zotero management through the Web API + WebDAV, no desktop app. Covers task recipes and safety rules.…

not rated 23 22d ago A 93 tokens original MIT

optimize-skill-loop

466

astra-sh/qvr

Skill Claude Code needs its repo

Deterministic outer-loop optimizer for a skill that already carries a frozen eval (produced upstream by an eval source such as create-skill-eval). Runs the frozen eval across user-chosen agents on fresh headless sessions via a pluggable adapter, grades quality/cost/perf, keeps the pareto-best variant, and versions…

not rated 23 2mo ago A 144 tokens original MIT

ph-deep-interview

467

jyt6640/persona-harness

Skill Claude CodeCodex

(PH) Use only for an ambiguous product request; visibly activate, ask one plain-language question at a time, and wait for explicit approval.

not rated 23 changed yesterday A 35 tokens original Apache-2.0

gitpic

468

tarnish233/gitpic

Skill Claude CodeCodex

A command-line tool that uploads local or clipboard images to a GitHub repository used as image hosting, then returns a Markdown link.

not rated 22 changed 2d ago A SkillSpector: warn 107 tokens original MIT

web-reading

469

EpisodeYu/HarnessSmith

Skill Claude CodeCodex

Read complex or JavaScript-rendered web pages cleanly. When a plain URL fetch returns an empty shell, garbled HTML, or "enable JavaScript", re-fetch the page through Jina Reader (https://r.jina.ai/) to get rendered, LLM-ready Markdown. Keyless, no setup. Use whenever a fetched page looks broken or you need the real…

not rated 22 1mo ago A 82 tokens original MIT

weread

470

shiquda/weread-cli

Skill Claude CodeCodex

A reading-data assistant for WeRead, a Chinese online reading service. It works with personal bookshelves, reading progress, notes, highlights, reviews, and reading statistics.

not rated 22 1mo ago A Socket: warnSnyk: warn 124 tokens

memento

471

veerps57/memento

Skill Claude CodeCodex

How to use Memento — a local-first MCP memory layer for AI assistants — to remember and recall durable knowledge about the user, their preferences, conventions, decisions, and projects across sessions. Trigger this skill whenever the user has Memento connected and any of the following happens, even when the user does…

not rated 22 3mo ago A 275 tokens original Apache-2.0

sparebank1-context

472

magnusrodseth/sparebank1-cli

Skill Claude CodeCodex

Build and maintain a personal finance context for the sb1 CLI (SpareBank 1) by running a short onboarding interview over the user's own accounts and transactions, then saving the answers to a private, git-ignored file the agent reads at the start of future finance sessions. Captures the meaning the bank can't know …

not rated 22 2mo ago A 138 tokens original MIT

pituitary-cli

473

nantobv/pituitary

Skill Codex

Use when you need spec-aware repository analysis through the Pituitary CLI. Covers workspace status, source coverage checks, schema inspection, structured analysis requests, deterministic fix planning, and other JSON-first Pituitary workflows. Prefer request-file inputs for larger payloads and treat returned repo…

not rated 22 3mo ago A 63 tokens original MIT

zenith

474

zenitheditor/zenith

Skill Claude Code

Author, edit, and render deterministic .zen design documents (posters, decks/slides, social graphics, flyers, books, magazines, diagrams, ads) with the zenith CLI. Use when the task is to create or change a visual design as structured, editable, version-controllable source — not a flat AI image. Covers: design tokens…

not rated 22 1mo ago A 197 tokens original Apache-2.0

gomoufox-mcp

475

ehmo/gomoufox

Skill Codex

Use when an agent needs to wire or drive gomoufox MCP browser tools with compact output and guardrails.

not rated 22 13d ago A 28 tokens

jfrog

476

jfrog/jfrog-skills

Skill Claude CodeCodex

Interact with the JFrog Platform via the JFrog CLI, JFrog MCP server and REST/GraphQL APIs. Use this skill when the user wants to manage Artifactory repositories, upload or download artifacts, manage builds, configure permissions, manage users and groups, work with access tokens, configure JFrog CLI servers, search…

not rated 22 +1 7d ago A SkillSpector: fail 204 tokens original Apache-2.0

wavespeed

477

WaveSpeedAI/wavespeed-cli

Skill Claude CodeCodex

Generate or edit AI media (image, video, audio, 3D) by calling the wavespeed CLI on the user's machine. Use whenever the user asks to create, edit, animate, upscale, or transform a visual asset, generate audio/TTS/music, or produce marketing creatives. Every model on the WaveSpeed platform is one wavespeed run call.

not rated 22 +1 changed yesterday A SkillSpector: pass 79 tokens original MIT

planecli

478

cpatrickalves/plane-cli

Skill Claude Code

Manage Plane.so through the planecli CLI — work items, projects, cycles/sprints, modules, labels, states, documents, intake queue, comments. Use when the user mentions Plane, planecli, or a work-item identifier like ABC-123, or asks about tasks, sprints, or backlogs in a project where Plane is the tracker.

not rated 22 +2 19d ago A 74 tokens original MIT

handoff

479

legoambarish/portable-handoff

Skill Claude CodeCodex

Create, validate, list, and load local Portable Handoff capsules for context transfer, continuing work in a new chat, compacting current work, or loading prior work. Use whenever the user asks for a handoff, context transfer, continuation briefing, or portable work-state summary.

not rated 21 17d ago A 59 tokens original Apache-2.0

dify-workflow

480

Akabane71/dify-workflow-cli

Skill Claude Code

Build, edit, validate, and export Dify AI workflow DSL files using the dify-workflow CLI. Use when: creating Dify workflows/chatflows/chat/agent/completion apps; adding nodes and edges to workflows; configuring LLM/tool/code/if-else/question-classifier nodes; validating DSL before Dify import; auto-layout node…

not rated 21 5mo ago A 100 tokens

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: