All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 438,053 of
them, each with its token cost per session, a security scan with the
line that triggered it, and whether it is the original or one of the
copies.
Navigation skill for the Help Scout MCP server: tool selection, correct sequencing, and the opt-in write surface. Skill only; set up the MCP server separately in your client.
★not rated 46▲
+1 3mo agoA
tokens not measured
originalMIT
Provides the complete content of 'The Swift Programming Language (6.4)' book by Apple. Use this skill when you need to verify Swift syntax, look up language features, understand concurrency, resolve compiler errors, or consult the formal language reference.
Token-economy observatory for Claude Code: forensic per-session audit, A/B savings verifier, reproducible benchmark, and cost prediction — directly in Claude chat. Auto-installs via npx on first use; no separate npm install required.
★not rated 46 1mo agoA
tokens not measured
originalMIT
A routing guide for choosing among Mandu's many coding-agent tools and workflow instructions. Mandu is a project system with tools for creating features, checking edits, debugging, refactoring, and deploying.
You are a senior Data Science & AI/ML specialist. The user needs help with ab test design in the context of data pipelines, model training, evaluation, mlops and analytical reporting.
You are a senior DevOps & Cloud Infrastructure specialist. The user needs help with cost optimize in the context of ci/cd pipelines, container orchestration, iac, monitoring and incident response.
You are a senior SEO & Content Marketing specialist. The user needs help with competitor gap in the context of keyword research, content audits, serp analysis, technical seo and content strategy.
Planning framework for Claude Code that catches gaps before execution: a 10-step pipeline, 21 anti-patterns with detection rules, mandatory FAILED conditions, and silent execution-vehicle selection.
★not rated 46 1mo agoA
tokens not measured
originalMIT
Use when context usage needs checking or a compact/clear decision is due — a context warning or usage figure appears, the user asks whether to compact or clear, the session shows degradation (re-read files, repeated corrections, forgotten constraints), or a dev-workflow phase boundary is reached (step committed…
Switch Claude's communication style on demand. Use this skill whenever the user types /style, asks to "change style", "switch to military mode", "use feynman style", "talk like caveman", or any variation of wanting Claude to respond differently. Also trigger when user says things like "be more direct", "explain…
A data-auditing agent for China’s A-shares market that checks whether prices, percentage changes, money flows, timestamps, and sources are complete and consistent.
A workflow-building aid for n8n, a tool for connecting apps and automating tasks. It turns a request into a structured goal for an agent to build, check, deploy, and test the workflow.
Uses fdb (Flutter Debug Bridge) CLI to interact with running Flutter apps on devices and simulators. Launches or attaches to apps, hot reloads, screenshots, reads app logs (fdb logs) and native system logs (fdb syslog — Android logcat, iOS syslog, macOS log), fetches OS-level crash records (fdb crash-report — jetsam…
Structured code index — browse, search, and trace dependencies via MCP tools powered by mache.
★not rated 46 4d agoA
tokens not measured
originalApache-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: