All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 432,381 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.
Standalone (no-MCP) version of the Ansvisor AEO Coach. Use this only when the user's Claude client cannot connect to the Ansvisor MCP server (e.g. claude.ai web without a Connector configured). Fetches live data from the Ansvisor REST API directly with the user's API key via code execution — visibility, competitors…
★not rated 238▲
+7
changed 3d agoASkillSpector: pass148 tokens
originalMIT
Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics…
In a project that uses Keep the Why (a .keep-the-why file at the workspace root, or a legacy keep-the-why:config block in AGENTS.md), load the keep-the-why skill first. Anywhere else, leave the skill alone.
Use when writing or editing DataSQRL scripts (.sqrl) for data processing, transformation, aggregation, or serving logic. Use for any pipeline logic implementation. Contains SQRL language spec.
Build a RAG (retrieval-augmented generation) pipeline using railtracks. Use when the user wants to ingest documents into a vector store and retrieve relevant passages to answer questions.
Fast code-navigation toolkit for LLM agents. Use to explore codebases without reading whole files — get file shapes, public APIs, dependency graphs, call graphs, blast-radius analysis, and token-budgeted context.
A tool guide for turning video or audio into written text and extracting the main points. It covers transcripts and subtitles, including content from YouTube and Bilibili.
NERV Operations Console aesthetic for web interfaces — Evangelion-inspired instrumentation UI with black void backgrounds, sparse high-contrast color coding (orange headers, green nominal data, cyan wireframes, red alerts), dense monospaced data readouts, measurement overlay grids, hex scanner patterns, CRT/VHS…
Analyzes events through sociological lens using social structures, institutions, stratification, culture, norms, collective behavior, and multiple theoretical perspectives (functionalist, conflict, symbolic interactionist). Provides insights on social patterns, group dynamics, inequality, socialization, social change…
API specification linting and security validation using Stoplight's Spectral with support for OpenAPI, AsyncAPI, and Arazzo specifications. Validates API definitions against security best practices, OWASP API Security Top 10, and custom organizational standards. Use when: (1) Validating OpenAPI/AsyncAPI specifications…
MCP server "homelab-monitor" as configured in SikamikanikoBG/homelab-monitor. Runs in Docker (docker.io/sikamikaniko123/homelab-monitor:0.14.2). Needs 2 environment variables to run.
★not rated 235▲
+3 todayA
tokens not measured
originalMIT
Cria e evolui a animação de um slide como METÁFORA visual animada (o M de MIRA): destila o conceito, acha uma analogia concreta do cotidiano e a anima com loop interno obrigatório, em D3.js v7+ ou CSS 3D, no padrão dos decks de mira-templates/decks/ (glass-card, icon-hero, attribute-pills, replay-btn). Dois modos…
Turn what the owner has into governed knowledge in knowledge/ — a document, a page, pasted text, notes, or something nobody ever wrote down that they tell you. Use when the owner shares material to add, says "add this to the knowledge base", asks how to get existing content in, or wants to write down what they know…
Runtime evidence that helps agents trace, profile, and burn down hotspots in application and native code, GPU kernels, and inference stacks. Runs locally from the flameox Python package.
★not rated 237▲
+2 yesterdayA
tokens not measured
originalMIT
Define, sharpen, or audit a North Star metric and its input metrics tree, and decide which product metrics actually matter (leading vs. lagging, guardrails, vanity vs. actionable, AARRR pirate metrics funnel). Use when the user says "define our north star metric", "what metric should we track", "what should we…
Deep-propagate one or more ingested sources across the wiki — update concept/entity/question pages, flag contradictions, create new pages where warranted. Optional step after ingest to ensure claims ripple through the full wiki.
Modern Swift/SwiftUI development toolkit with TCA support. Provides agents for planning, implementing, testing, documenting, and building Swift features.
★not rated 233 9mo agoA
tokens not measured
originalMIT
Applies Galactic engineering rules for work in the galactic-ide repository. Use when implementing, reviewing, or refactoring repo code and you need the canonical standards for testing, versioning, React/Tailwind conventions, toasts, storage, OS-aware logic, and git-service boundaries.
Map this codebase into project memory — a code graph of every symbol and how they connect, plus a written profile of stack, layout, conventions and workflows. Re-run any time to refresh both in place. Use when memory is newly installed on an existing project, or when the project has changed enough that the stored map…
Translates an image (or a set of image references — screenshots, mockups, Figma URLs, live websites) into two mirrored design-system artifacts: docs/design.md (YAML tokens + prose, following Google's open design.md format, for the coding agent) and docs/design.html (a self-contained, token-driven style guide rendering…
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: