Skills

Progressive-disclosure instructions an agent loads on demand. Cheap until invoked, which is why the per-session figure on each card is usually two digits.

ai-tips-tricks

6553

0xMulight/human-social-copy

Skill Claude CodeCodex

An automated workflow for searching the web for practical AI tips, techniques, and workflows, then writing tutorial-style Chinese posts and sending them to Telegram.

not rated 73 +50 3mo ago C 53 tokens original MIT

creating-paywall

6554

SwiftfulThinking/SwiftfulStarterProject

Skill Claude Code

Scaffold a new paywall variant view in Core/Paywall/Paywalls/ and wire it into the AB test switch. Use when the user asks to add a new paywall, create a paywall variant, add a subscription screen, or build a purchase flow. Covers custom paywalls (most common), StoreKit native paywalls, and RevenueCat paywalls. Every…

not rated 73 13d ago A 91 tokens original MIT

loom-curator

6555

rjwalters/kicad-tools

Skill Claude Code needs its repo

Enhances approved issues and prepares them for implementation.

not rated 73 changed 2d ago A 13 tokens original MIT

suno-music

6556

AceDataCloud/SunoMCP

Skill Claude CodeCodex

Use Suno through Ace Data Cloud in goose for Suno music, lyrics and covers. Use the installed service MCP tools; query the original task ID after generation. This plugin is maintained by Ace Data Cloud, not the service brand's official plugin.

not rated 73 +1 changed 7d ago A 55 tokens original MIT

verify-msp-skills

6557

Servosity/msp-skills

Skill Claude Code

Drive one msp-skills connector (skills/ , any of the 84) the way a user does and prove it with evidence: install.sh, the -cli CLI, and the -mcp server over stdio and over HTTP, in an isolated HOME against a local fake vendor. Use to check a connector's user path before or after a reprint, to compare press versions…

not rated 73 +5 changed 5d ago A 109 tokens

dependency-audit

6558

BARMPlus/locklens

Skill Codex

A security review of project dependencies managed by npm, Yarn, or pnpm. It can inspect a local project directory or a remote Git repository for known dependency risks.

not rated 72 +6 5mo ago A 56 tokens original MIT

agenticforge-agents

6559

LittleBlacky/AgenticFORGE

Skill Claude CodeCodex

Expert at selecting and configuring AgenticFORGE agents. Generates correct FunctionCallAgent, ReActAgent, PlanSolveAgent, ReflectionAgent, SimpleAgent, SkillAgent, and WorkflowAgent code with proper configuration. Use when the user wants to build an agent, choose between agent types, configure agent options, or…

not rated 72 4mo ago A 72 tokens

sheets-cli

6560

gmickel/sheets-cli

Skill Claude CodeCodex

Read, write, and update Google Sheets data via CLI. Use when the user asks to read spreadsheet data, update cells, append rows, or work with Google Sheets. Triggers on mentions of spreadsheets, sheets, Google Sheets, tabular data in the cloud, or specific sheet names like "Projects" or "Tasks".

not rated 72 9mo ago A 69 tokens

perseus_vault-memory

6561

Perseus-Computing-LLC/perseus-vault

Skill Claude CodeCodex

Self-hosted persistent memory for OpenClaw agents via Perseus Vault MCP — 30 tools, hybrid search, AES-256 encryption, zero external dependencies.

not rated 72 2mo ago D 38 tokens original MIT

arco-design-vue

6562

arco-design/arco-design-skill

Skill Claude CodeCodex

A reference for building Vue 3 interfaces with Arco Design Vue, a library of ready-made user-interface components. It covers components such as buttons, tables, forms, dialogs, navigation, and date controls.

not rated 72 +1 5mo ago A 181 tokens original MIT

ham

6563

kromahlusenii-ops/ham

Skill Claude CodeCodex

Set up Hierarchical Agent Memory (HAM) — scoped CLAUDE.md files per directory that reduce token spend. Trigger on "go ham", "set up HAM", "ham commands", "ham help", "ham route", "ham remove", "ham update", "ham status", "ham benchmark", "ham baseline start", "ham baseline stop", "ham metrics clear", "HAM savings"…

not rated 72 +1 7mo ago A 108 tokens original MIT

pivot

6564

CymChad/book-skill-generator

Skill Claude CodeCodex

A Lean Startup decision guide for changing a product's direction when data shows that its main assumption is wrong. This change of direction is called a pivot.

not rated 72 7mo ago A 38 tokens original MIT

wiki-ingest

6565

vanillaflava/llm-wiki-skills

Skill Claude CodeCodex

Process source files into synthesised wiki pages. Always use this skill when the user says /wiki-ingest, 'import these files', 'process my clippings', 'ingest this article', 'I have new articles to add', 'turn this PDF into a wiki page', 'what's in my raw/ folder', or 'what have I ingested'. Also use when the user…

not rated 72 +2 4mo ago A SkillSpector: warn 182 tokens original MIT

Jasper0122/CLI-Anything-Arcgis-Pro

Skill Claude CodeCodex

Drive ArcGIS Pro (ArcPy) from the command line — professional cartographic export (layouts + Map Series / map books), geoprocessing, batch processing, and feature-class query/edit. Also ships a live-Pro MCP bridge that lets an agent operate the OPEN ArcGIS Pro session (the closed-source counterpart to CLI-Anything's…

not rated 72 +1 4mo ago A 0 tokens

perf-review

6567

lemoncrow-lab/lemoncrow

Skill Claude Code

Verify a code change against measured performance gates — latency & tail-latency regression, profiler-confirmed hot paths, memory/leak soak, I/O & wire budgets, and scaling — by running it, not reading it. Use for 'perf review', 'did this slow down', 'check for a regression', or /perf-review. Enforces performance…

not rated 72 7d ago A 87 tokens

skeleton-development

6568

laravel/package-skeleton

Skill Claude CodeCodex ✓ vendor

Configure and apply the :packagename package in Laravel applications.

not rated 72 +1 12d ago A SkillSpector: pass 16 tokens original MIT

learn-loop

6569

cathrynlavery/agent-improvement-loop

Skill Codex

Close captured agent-improvement work: triage fleet learnings, select a bounded evidence-backed batch, implement and live-verify fixes, and record leader decisions. Use for 'learn loop', 'fix the learnings', 'process the backlog', or when asked what recurring agent/tool friction to improve.

not rated 72 +2 10d ago A SkillSpector: pass 63 tokens original MIT

renux

6570

andrianllmm/renux

Skill Claude CodeCodex

Drive the renux CLI to bulk-rename files. Covers regex patterns, placeholder tags ({counter}, {now}, {size}, EXIF/video metadata), text filters, and file exclusion. Trigger on any bulk/batch rename or filename cleanup request, even without "renux" named, e.g. "add today's date to these screenshots," "strip the IMG…

not rated 72 6d ago A SkillSpector: pass 94 tokens original MIT

cherimoya

6571

jmschrei/cherimoya

Skill Claude CodeCodex

Train, evaluate, and use Cherimoya sequence-to-function genomic models with the cherimoya command-line tools or Python API. Use when a user wants to run the end-to-end pipeline, use a trained model to do downstream tasks, or troubleshoot a run. Designed for users who may be new to Cherimoya or to sequence modeling…

not rated 72 +1 changed 1mo ago A SkillSpector: pass 106 tokens original MIT

all-deploy

6572

Hainrixz/all-deploy

Skill Claude CodeCodex

Deploys websites, web apps, APIs, and agents to the internet with a strict pre-deploy audit and a preview → health-check → prod flow. Handles plain HTML/CSS/JS pages and static sites (Astro, Hugo, Jekyll, Eleventy, Vite) as well as Next, Remix, Nuxt, SvelteKit, FastAPI, Flask, Express, MCP servers, Claude Agent SDK…

not rated 72 changed 14d ago A 242 tokens original MIT

nature-citation

6573

niuz257470-ctrl/natureskills

Skill Claude CodeCodex

Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default.…

not rated 72 6mo ago A 150 tokens original MIT

agentdebug

6574

AgentDebugX/AgentDebugX

Skill Claude CodeCodex

Use AgentDebugX for trajectory diagnosis only when the user explicitly asks to use AgentDebug, AgentDebugX, or the agentdebug skill. Do not invoke for generic debugging, diagnosis, inspection, or trajectory-review requests.

not rated 72 +1 changed 2mo ago A SkillSpector: pass 47 tokens original MIT

boredape874/mcbejsonuimasterAI

Skill Claude CodeCodex

Use when the user asks for layout, positioning, alignment, symmetry, equal spacing, or pixel-correct sizing of Bedrock JSON UI elements. Translates the user's intent (prompt or annotated image) into the IR YAML described in docs/41-ir-spec.md and schemas/ir.schema.json. Pairs with mcbe-json-ui-tools-runner to compile…

not rated 72 changed 1mo ago A 85 tokens

codex-tweaks/codex-tweaks

Skill Claude CodeCodex

Create or modify Codex Tweaks API v3 packages with lifecycle-safe Renderer code, optional fully trusted Node backends, typed UI extensions, package dependencies, priorities, and Git-installable metadata.

not rated 72 +1 5d ago A SkillSpector: warn 48 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: