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.
A set of rules for choosing the right kind of DeepSeek Harness extension before building it. It explains the differences between bundles, local patches, agent presets, skills, and temporary runtime plugins.
Retrofit an existing skills/plugins/agents repository into an APM-compliant package. Use when a repo contains SKILL.md files, a plugin.json, AGENTS.md/CLAUDE.md, MCP manifests, hooks, slash commands, or sub-agents but has no apm.yml (or has an incomplete one), and the user wants it installable via apm install…
Initialize or improve AGENTS.md files that define how coding agents operate in a repo. Use when asked to set up or replace an agent init command (Codex, Claude), standardize multi-agent behavior, or audit an existing AGENTS.md for clarity, commands, boundaries, and repo-specific context. For Claude Code, also create…
Use when an agent has many skills/tools/prompts and must cut prompt tokens by routing adaptively. Runs routing outside model context when possible, indexes metadata on disk, lazy-loads one primary plus up to four complementary support skills, and benchmarks savings across agents.
Demonstrates how to ship an Agent Skill from an npm package via skill-indexer. Use when learning how to author a skill or as a template for new skills.
A daily worklist and priority manager that stores tasks and background information in Markdown files. It separates ongoing context from individual things that need to be done.
Create new skills, modify and improve existing skills, and measure skill quality. ALWAYS use this skill when users want to create a skill from scratch, edit or optimize an existing skill, extract a skill from a conversation, test a skill, or optimize a skill's description for better triggering accuracy. Also trigger…
Distill verified engineering knowledge from incidents, debugging sessions, code reviews, and expert-model analysis into evidence-backed project rules. Use when asked to analyze an incident, convert an expert answer into a rule, create or update an ADR or external contract, promote or deprecate a rule, or scan relevant…
A Chinese-language guide for producing growth strategies. It first classifies the request, then creates a plan using models, experiments, channels, metrics, and stored working notes.
Strict autonomous delivery loop that runs deep-interview, ralplan, ultragoal, code-review, and ultraqa in order with automatic re-planning when gates are not clean. Use on "autopilot", "autonomous", "build me", "create me", "make me", "full auto", "handle it all", or "I want a/an…".
Skill for protein structure prediction and analysis with AlphaFold. Use this skill whenever a user wants to predict or fetch a protein 3D structure, download structures from the AlphaFold Database (AFDB), run ColabFold for novel proteins, parse pLDDT confidence scores or PAE (predicted aligned error) from AlphaFold…
Intelligently helps organise notes by processing a new note from the root directory, finds or creates a relevant project file, links the note, and moves it to its final destination in the vault obeying the zettelkasten method.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…
Expert knowledge for scripting in Ninox databases, preventing hallucinations and enforcing project rules. Use when writing, debugging, or explaining Ninox scripts (NX), when the user mentions Ninox, NX scripts, database scripting, or needs help with Ninox formulas, automation, or database operations.
Expert skill for designing, building, and deploying modern premium websites with advanced animations and 3D interactive experiences using Three.js, React Three Fiber, GSAP, and Framer Motion. Use this skill whenever the user wants to build a website with 3D elements, create an immersive web experience, add interactive…
Requirement-aligned development workflow. TRIGGER: whenever the user asks to build a feature, make a change, optimize/improve something, or fix a bug — especially when the requirement is vague or lacks scope/acceptance criteria. Before starting, the agent MUST detect the user's role (PM/Developer/Both), persisted…
Expert guidance for TM1py Python package for IBM Planning Analytics (TM1). Master connection management, data operations (MDX, views, DataFrames), metadata CRUD, performance optimization, and best practices. Use when working with TM1py, IBM Planning Analytics API, or when user mentions TM1, Planning Analytics, TM1…
Skill "README" from subhansh-dev/agent-maxxing, covering agent maxxing, ⚡ quick start, step 1: clone the repo, step 2: install for your agent and step 3: restart your agent.
A Chinese-language content review and editing role for short-video scripts, spoken copy, titles, product content, cover images, and videos up to 60 seconds.
Send or schedule email on the user's behalf through their auto-email-sender pipeline (Gmail + Apps Script) — the correct way to send mail once this tool is installed. Use this whenever a task involves sending, replying, following up, thanking, declining, rescheduling, delivering files by email, or outreach — even if…
Use when developing, running, or debugging Commodore 64 software (Commodore BASIC or 6510/6502 assembly) on the VICE emulator with the c64 CLI or the c64-tools MCP server. Covers the build/run/observe/debug loop, the stopped-state discipline, C64 text encodings, graphics and sprites, and the memory map.
A lightweight way to divide coding work into task groups, assign each group to a coding agent, and review the results in stages. The main agent plans and checks the work while each worker handles its assigned batch.
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: