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 CodeCodex
Emulates Evangelion's MAGI trinity by splitting decisions into three persona cores — MELCHIOR (scientist/logic), BALTHASAR (mother/safety), CASPER (individual/intuition) — each dispatched as parallel subagents that recursively decompose into variable-sized judgment nodes (10–20 total, groups of 3), self-verify…
Skill Claude Code
Teach the user a new skill or concept, within this workspace.
alphaparkinc/genpark-skill-guide-mentor
Skill Claude CodeCodex
Guide Mentor — Proactive project management agent that provides high-stakes guidance, iterative feedback, and strategic oversight for complex, long-running projects.
CaseyLabs/kc-secure-repo-template
Skill Claude CodeCodex
Use when changing or reviewing the Terraform-backed GitHub repository hardening workspace under config/infra, including provider pins, rulesets, default branch protection, required checks, secret scanning, Dependabot security updates, token handling, plan/apply behavior, and infra documentation. Do not use for…
Skill Claude CodeCodex
Scans extensions, skills, and code for security threats: prompt injection, malicious code, obfuscation, data exfiltration. Also scans inbound messages for injection patterns automatically.
Skill Codex
Use this skill when a user wants Codex CLI or another MCP-compatible coding client to work through a harness-engineering loop with explicit execution contracts, persistent local knowledge/RAG, durable traces, structured verification evidence, project-local governance policy, PASS/FLAG/BLOCK governance audits…
Skill Codex
Deterministic, self-hosted long-term memory for AI agents. Trigger when the user wants persistent memory, MCP-backed assistant memory, or wants to integrate ai-knot into Python, CrewAI, LlamaIndex, AutoGen, the OpenAI Agents SDK, PydanticAI, LangChain/LangGraph, TypeScript, or HTTP services. This is the default…
Skill Claude CodeCodex
Builds complete, compliant NimbleBrain Upjack apps from natural language descriptions. Generates manifest, entity schemas, skills, context, seed data, and server entry point. Use when creating a new Upjack app, building an AI-native app, or scaffolding a domain-specific application. Triggers include "create me a todo…
marianfoo/sap-api-policy-skill
Skill Codex
Evidence-based assessment of whether an SAP API/interface usage scenario aligns with the SAP API Policy (v.4.2026a). Use whenever someone asks whether a way of calling SAP is allowed/compliant — e.g. Published API vs internal/private/"confidential" API status, "Documented Use", whether a third-party tool / iPaaS /…
jayelbotvibe-web/hermes-pentest-lab
Skill Claude CodeCodex needs its repo
Pentest finding interpretation encyclopedia — maps tool output to finding severity, CVSS scoring rules, and report-ready language. Answers 'What severity is this? What's the CVSS? How do I write this up?'.
Skill Claude CodeCodex
Use Fetchira for current web search, URL reading, deep research, JavaScript page reading, image generation, and provider quota routing. Prefer its listed MCP tools and use the CLI only when MCP is unavailable.
Skill Codex
Use when debugging Cities: Skylines II mod build failures, packaging failures, runtime errors, game logs, UI debugger issues, or mod behavior that does not work in game.
Skill Claude CodeCodex
Structured multi-step reasoning tool for complex problem solving with branching, hypothesis testing, and evidence tracking.
Skill Claude CodeCodex
You are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. Based on Wikipedia's "Signs of AI writing" guide + crowd-sourced YouTube research from creators with 2.2M+ combined views.
Skill Claude Code
Use when the user asks for a recap, status readout, or check-in across Ideate ideas (a logical work item; "session" is one facet of an idea, not the unit). Scope is the local Ideate workspace exposed by the ideate MCP. Use work-idea instead when the user wants to focus on or switch into a single idea.
lvpiggyqq/xcatcher-mcp-manifest
Skill Codex
Fetch fresh or recent public X (Twitter) posts from one or many named account handles through Xcatcher, with structured JSON results and optional x402 v2 USDC pay-per-crawl access on Base. Use for account monitoring, social intelligence, OSINT, tweet/post collection, timeline snapshots, or requests to scrape, crawl…
kasperjunge/agent-resources-legacy
Skill Claude Code
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.
dfdfb160-ui/relationship-support-agent
Skill Codex
A support skill for discussing attraction, unclear dating situations, relationship quality, emotional dependence, and breakups with attention to feelings and available evidence.
Skill Claude CodeCodex
Migrate Riverpod from 2.0 to 3.0; automatic retry, paused listeners, legacy providers import, Ref simplification, FamilyNotifier removal, ProviderException, updateShouldNotify. Use when the user asks about Riverpod 3 migration, upgrading to Riverpod 3, or breaking changes in 3.0.
Skill Claude CodeCodex
Perform architecture- and maintainability-focused code reviews. Use when the user asks for code review, style review, refactoring feedback, or review of architecture, cohesion, coupling, TypeScript rigor, naming, tests, responsibility boundaries, or unnecessary abstractions.
Skill Claude CodeCodex
Execute privacy and sensitive leakage guarding before output. As long as context contains sensitive information, must trigger this skill even if user only requests explanation/summary. Default to downgrade expression for tool conclusions not multi-source verified.
Skill Claude Code
Instant website conversion copywriter for AI agents. Generates high-converting website copy (Landing Pages, Homepages, Hero sections, Feature grids, Value Propositions, Social Proof, and CTAs) with zero setup required. Produces 3 conversion angles (Direct, Pain-Driven, Transformation) using psychological frameworks…
Skill Claude CodeCodex
Chaos agent for skills — a vigilance-training layer that keeps humans reviewing AI output instead of rubber-stamping it. Consult this skill on EVERY substantive request (code, analysis, writing, SQL, configs, explanations — anything with a checkable answer). 95% of requests get your genuine best work; a deterministic…
Skill Claude CodeCodex
Engineering rules for JAX/Equinox scientific computing; API stability, docs, CI, serialization.
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: