All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 439,866 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.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Binder data modeling — define entity types, fields, relations, constraints, views, and navigation. Use when asked to "create a type", "add a field", "define a schema", "set up relations", "model entities", "create a view", "set up navigation", "render entities as files", or design a binder workspace schema.
A framework for building component-based OneScript applications, a scripting language related to 1C, with automatic dependency setup and annotations. It creates objects and supplies their required constructor values.
One folder per agent. Claude Code loads .claude/agents//.md recursively, so the nesting is free; a file is only treated as an agent definition if its frontmatter carries a name:. Everything else in the folder is a co-located doc.
Estimate what Claude Cowork / Claude Code conversations would cost if run on the pay-per-token Claude API instead of the subscription. Reports token counts and cache-aware API cost in USD and EUR, for the current conversation or for the whole history (cost per conversation). Trigger when the user asks things like "how…
A setup guide for connecting a personal WeChat account to Hermes Agent through WeChat's iLink Bot API, the interface used to exchange messages with the account.
Hand-computes a system's execution with explicit state at each step. Use when debugging races, state machines, async bugs, regressions; stress-testing a fix; scoping features on existing state; or approaching unfamiliar code. Especially useful for bugs involving client/server sequencing, background refreshes, recovery…
A comprehensive workflow for researching a startup idea and generating a full startup kit including market analysis, competitor mapping, product specs, and a high-fidelity landing page.
Plan and generate visuals by preservation class: exact product, branded environment, or concept support. Uses strategy-driven shot selection and visual QA instead of generic vibe prompting.
Prepare, run, and follow up on founder peer coffee chats / networking meetings end to end (Before -> During -> After). Trigger when the user says things like "prep my coffee chat with X", "I'm meeting someone next week, help me prepare", "meeting prep", "coffee chat strategy", "networking meeting prep", "what should I…
Structured six-hats thinking sessions for debating decisions. Use when user says "six hats", "six hats debate", or wants to explore a decision through six colored-perspective lenses in sequential rounds with a final recommendation.
Coordinates custom specialists through workflow phases, artifact handoffs, approval gates, and autonomous implementation. Use when executing a workflow recipe or routing its next specialist.
Scan a target codebase for data model definitions (SQL schemas, ORM models, TypeScript interfaces, Pydantic models) and propose dataconcept, dataaggregate, and dataentity registry entries. Presents findings for review before writing files.
Use when safely initializing or hardening a newly installed or rebuilt Ubuntu/Debian server over SSH, including SSH keys, a non-root sudo user, SSH policy, server timezone, UFW, fail2ban, local SSH config, and lockout-safe verification.
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: