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.
Skill Claude Code
A workflow for analyzing branch changes and creating a draft pull request, including a screenshot step when the changes affect the user interface.
Skill Claude CodeCodex
Records and replays agent execution traces for debugging, optimization, and regression analysis.
Skill Claude CodeCodex
Detect prompt injection, jailbreaks, and adversarial attacks in LLM inputs before processing. 5 analysis layers, F1 84.4% internal / 98.87% external, 24ms, runs offline.
Skill Claude CodeCodex
Query and modify NetBox (DCIM/IPAM) from the shell with the nbox CLI — look up devices, interfaces, IPs, prefixes, VLANs, sites, racks, circuits, VRFs, tenants, VMs, and clusters; run cross-object search; use IPAM helpers (next free IP/prefix, prefix utilization, cable-path traces); and safely write (reserve…
Skill Claude CodeCodex
Use this skill whenever a user wants to execute operations against Algolia indices or accounts — deleting records, copying/migrating indices, backing up data, importing/exporting records, managing API keys, editing synonyms, configuring rules, changing settings like facets, clearing indices, or automating Algolia in…
Skill Codex
Choose the lightest Mastermind workflow that fits the risk, then create an evidence-grounded verified or strict task contract for delegated implementation. Direct work deliberately uses no task spec.
Skill Claude CodeCodex needs its repo
Codebase intelligence and evidence-driven governance with the indexed ctx CLI. Use when exploring an unfamiliar repository, locating symbols or callers, checking for existing implementations, estimating change impact, enforcing architecture rules, scoring a branch, finding hotspots or duplication, or analyzing…
Skill Claude Code
Archive merged feature specs into project memory with provenance, sweep discovery, and gated cleanup.
Skill Claude CodeCodex
Use when creating, changing, or validating a Cordis composition for this harness — writing or editing an agent preset, adding or removing a plugin row, deciding whether something belongs to the host composition or to one session, checking whether a preset you authored actually mounts, or diagnosing a row that mounted…
Skill Claude Code
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Skill Claude CodeCodex
Decode any set of competitors into their ICP (ideal customer profile), their funnel (how a stranger becomes a customer), and their monetization (every revenue stream and price point). Researches each competitor against real sources and synthesizes a cross-competitor comparison. Use whenever the user wants to research…
Skill Claude Code
A Chinese-language assistant for turning a Melodie agent-based model design into code, test data, and documentation. Melodie is a framework for building simulations whose individual entities interact over time.
mohamed-benoughidene/openreview-cli
Skill Claude CodeCodex
Use when a user wants to review, compare, search, or analyze legal/contract documents (PDF/DOCX) locally — produce review memos, compare two versions, search indexed clauses, run negotiation analysis, manage LLM gateway slots/playbooks, or audit/delete stored PII mappings. This is the local openreview CLI, NOT the…
Skill Claude Code
A command for showing stock or cash balances from 1C, a business accounting and inventory system.
Skill Claude Code
Set up dcc-mcp-houdini for an agent or operator: install Houdini Python dependencies with hython, generate MCP host configuration, guide the user through the Houdini package / 123.py autostart load step, and run a first live-tool smoke prompt.
Skill Claude Code
Error handling patterns for API endpoints. Use when implementing error handling, writing middleware, or reviewing how errors are caught and formatted in API code.
Skill Claude CodeCodex
A skill for multi-writing-skills from the yuesf project. A skill is a reusable set of instructions that an agent can apply when its trigger conditions are met.
Skill Claude CodeCodex
A development guide for using Baidu Maps on HarmonyOS NEXT, Huawei’s newer operating-system platform. It covers map display, location search, route planning, navigation, map overlays, and foreground or background location.
Skill Claude Code
Clojure/ClojureScript/ClojureDart development skill. Activates when working with .clj, .cljs, .cljc, .cljd, .edn, .bb files. Provides structural search and editing of S-expressions, nREPL evaluation, runtime queries via cider-nrepl, and static navigation via clojure-lsp.
Skill Claude CodeCodex
Async email-style messaging with the human user via a GitHub issue used as a mailbox. Reach for the nobox tools whenever the user wants to be reached asynchronously (they're stepping away, the task will take a while, they ask to "leave a note", "ping me later", "check messages", or "email me when you're done").…
Skill Claude CodeCodex
A guided workflow for writing long, structured technical documents in Chinese, such as project applications, technical proposals, tender documents, and feasibility reports. It covers planning, section writing, image handling, review, and DOCX layout.
Skill Claude CodeCodex
A set of rules and templates for creating and reviewing product design documents in the ued/ directory. It covers documents ranging from strategy and requirements to architecture, detailed design, and validation.
Skill Claude CodeCodex
Enrich an existing PKUP report directory — group commits into tasks, filter out non-creative groups, and write Polish descriptions. Use when the user has already generated a PKUP report and wants to clean it up or add "Zaprojektowałem..." descriptions.
Skill Claude CodeCodex
Repository-local meta-skill for generating a control reference page inside an existing skill under an Avalonia control library plugin. Does not produce a standalone skill.
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: