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.
Guidance for making safe changes in the SiMa Neat core repository. Use when modifying Neat framework code, public headers, pipeline/runtime behavior, Model/archive/MPK-contract handling, Nodes/NodeGroups, Graph, Tensor/Sample contracts, Python bindings, tutorials, docs, or tests in the core repo.
Create, audit, or migrate a project-bound local Harness for reliable AI coding. Use when a project needs ECL Change planning, layered project knowledge, local Codex/Claude worktree coordination, PR-like Integration, Harness Evolution, greenfield guidance, or reference-source maps. Do not use for ordinary feature…
A Chinese-language reading assistant that turns highlights, notes, and questions from WeRead or other reading sources into traceable plans and knowledge cards in Obsidian, a note-taking application.
Fetches and reports the user's Garmin Connect health and workout data (sleep, HRV, stress, Body Battery, resting HR, steps, calories, HR zones, per-km splits, strength-training exercise sets with reps/weight) via the local garminpipeline CLI, writing markdown/CSV files into data/library/. Use when the user asks to…
Code-reviews Pluggy API integrations against Pluggy's official documentation (queried in real time via the Pluggy MCP, with a web fallback to docs.pluggy.ai when the MCP isn't connected) and returns a diagnostic report (✅/❌/⚠️) with file, line, and the code fix for each issue. Use WHENEVER the dev uploads integration…
Run one YASDEF ASDLC worker planning iteration for an assigned step. Use when yasdef or the user asks to create, update, validate, or finish a step plan artifact under .asdlcworker/stepplans after design is complete.
Write an Eva extension that runs on the same machine as the session — a script (.exs) compiled into Eva's VM, or a Mix project on its own local node. Use when asked to create, modify, or debug a local Eva extension.
Run an Amazon-style Correction of Errors (COE) post-mortem on a development process failure. Produces a structured document with summary, timeline, five-whys root cause analysis, lessons learned, and typed action items — then offers to implement the fixes. Use this whenever something goes wrong in the dev process: a…
Extract structured product data from e-commerce URLs using the Zyte API and generate side-by-side comparison tables with intelligent purchase recommendations. Use this skill whenever the user wants to compare products from different e-commerce websites, asks "which product should I buy", wants a product comparison…
Read academic papers from a provided PDF, URL, text, DOI, title, or citation and produce a teaching-first structured interpretation report, usually saved to a user-specified directory as a PDF with a Markdown source copy. Use when the user wants to genuinely understand, learn, summarize, deconstruct, critique…
The team-synergy-coach skill registry provides a comprehensive framework for registering, resolving, executing, and validating skills within the esports team training and coordination coaching harness. This document explains the complete skill lifecycle, from registration to execution and quality enforcement.
ADHD-Friendly Home Space Optimization Advisor (Environmental Psychology) — ADHD environmental-design and cognitive-ergonomics analysis and decision-support harness. Use this skill when the user mentions ADHD home design, ADHD-friendly spaces, sensory-friendly environment, ADHD workspace optimization, ADHD bedroom…
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
Read, view, and edit 3D model files (.3mf, .stl, .obj, .ply, .glb). Use this skill whenever the user uploads, mentions, or asks about any 3D model file — even casually ("look at this model", "scale my print file", "what's in this 3MF", "convert to STL"). Also covers detecting which CAD/slicer produced a file and…
An MCP (Model Context Protocol) server that provides access to Sefaria's library of Jewish texts — Torah, Talmud, Mishnah, Midrash, and thousands of commentaries.
Check and resize images for social media platforms. Run scripts/check.js to validate any image against specs for Instagram, Facebook, X (Twitter), LinkedIn, TikTok, YouTube, Pinterest, Snapchat, and Threads — get a ranked match list with exact resize commands. Run scripts/resize.js to export a correctly-sized copy.…
Interview the user about a plan, design, topic, or decision while checkpointing every answer to a durable markdown capture file. Use when the user says "grill-me-checkpoint", "grill me with checkpoints", asks to be grilled without losing context, wants a discovery session saved to disk, or needs messy thinking…
Guides users through a complete GSA Multiple Award Schedule (MAS) application, focused on SIN 54151S (IT Professional Services). Walks first-time applicants through every phase — eligibility, registration, technical proposal drafting, pricing, and eOffer submission — producing staged deliverables at each step. Use…
Create, edit, and organize notes in an Octarine workspace by writing Markdown files directly to disk. Use when the user asks an agent to save notes, daily notes, meeting notes, plans, research, attachments, tags, wiki links, templates, or any other content into Octarine.
A skill to query Tableau data sources, the "last mile" of analytics in an organization. When business users think about company data they often think of a visualization or data set on the BI platform, curated to their needs with useful semantics instead of raw data in a warehouse.
Create, test, and optimize Grok skills. Use when creating a skill from scratch, editing one, testing if a skill works, optimizing skill triggering, benchmarking performance, or packaging a .skill file. Triggers: "create skill", "new skill", "edit skill", "test skill", "skill not triggering", "optimize description"…
★not rated 6 1mo agoA116 tokens
originalMIT
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: