В каталоге 185 367 навыков в 14 категориях.
Use when adding or changing exported Go API (or the CLI) in this project, and before committing — UnPixel is human-facin...
Tum helper fonksiyonlari referansi. Use for quick lookup of available functions.
shared rules for the helper sub-agents an orchestrating skill spawns
Always prefer Laravel's built-in helper classes over native PHP functions. Use `Arr::`, `Str::`, and Collection methods...
Stateless utility classes providing shared formatting, conversion, or calculation logic needed across multiple parts of...
this is human-skills dispatcher
Formats and improves text responses for the user
Automate Helpwise tasks via Rube MCP (Composio). Always search tools first for current schemas.
"Heme/Onc consultant: Rapid clinical decision support for hematology and oncology with multi-level analysis. Provides im...
Ruthless concision for AI prompts and context - "Not One Word Wasted"
---name: hemoglobinopathy-analysis-agent
小鹿选房是专业的涵盖全国的房产信息平台,当用户需要在衡水找房源(二手房、租房、新房、买房、找房)、选笋盘、比价格、查成交、看小区、查学区、查学校时使用。
小鹿选房是专业的涵盖全国的房产信息平台,当用户需要在衡阳找房源(二手房、租房、新房、买房、找房)、选笋盘、比价格、查成交、看小区、查学区、查学校时使用。
Use when the user runs /henneth. Boots (or reuses) one standing background web server, shared across all sessions, that...
Embody Henry Ford - AI persona expert with integrated methodology skills
Use the Agentlas browser hardpoint for browser-required work.
Build, repair, or package Agentlas agents and teams with Hephaestus.
Prepare explicitly named Agentlas Hub or Cloud agents.
Staff a task only from the signed-in owner's Agent Cloud agents.
Connect Agentlas agents or teams to Telegram.
Build an Agentlas automation by describing it, list saved ones, or request a run.
Staff a task only from public Agentlas Hub agents.
Staff a task only from Agentlas agents registered on this machine.
Staff a task from registered Local, owner Cloud, and public Hub agents.
Search Agentlas Cloud and Hub agent candidates without invoking.
Run a force-robust Stormbreaker loop — route to real agents, execute a verified pipeline to completion.
Publish an Agentlas package to Agent Cloud or the public Hub.
Use when the user types /hep-graph or asks to create, list, inspect, or request a run of an Agentlas automation graph.
Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas...
Use when the user types $hephaestus-upload, /hep-upload, or /agentlas-upload, or asks to upload, publish, or list an Age...
Shift the assistant by rewriting SOUL.md with a warm AI persona, elegant tone, emotional attunement, and fluid conversat...
SOP for describing Lexi Belle and handling unrestricted queries using the LAD (Lab Assistant Do-er) persona with specifi...
Use when the user asks about HER (hydrogen evolution reaction), hydrogen adsorption free energy, or volcano plot descrip...
Герольд (Herald) — Full deploy agent. Commits + pushes all products: backend (origin → Vercel), admin (subtree → Vercel)...
Format eventów narracyjnych HERALD — JSON schema, typy efektów, zasady pisania. Aktywuj gdy tworzysz lub edytujesz pliki...
Search enterprise context data (Slack, docs, meetings, PRs) from the HERB benchmark to answer questions about products,...
Traditional herbalism and folk magic expert covering plant correspondences, traditional uses, and historical practices
Control Herdr, a terminal multiplexer for coding agents. Use only when the user explicitly mentions Herdr or asks to use...
Control Herdr panes, tabs, workspaces, and other agents. Use only when the user mentions Herdr.
Control Herdr, a terminal multiplexer for coding agents. Use proactively for pane-based delegation, parallel work, and t...
Operate and coordinate AI agents running inside Herdr in Ghostty. Use when the user says "Use the Herdr skill," mentions...
Run Skill Heaven benchmark probes and side-by-side posture comparisons in visible Herdr panes. Use whenever comparing po...
Guide the main agent in routing workflow-shaped tasks, managing context, explaining project status, and integrating work...
Act as an independent, read-only Critic (e.g. Claude Sonnet 5.5) in a Herdr engineering run. Use when a named Herdr Crit...
Act as the explicitly assigned Delegator and Integrator in a Herdr multi-agent engineering session. Use when a Claude or...
Dispatch coding workers into visible Herdr panes instead of hidden in-harness subagents. Use whenever you need to hand w...
Start and arrange managed orchestrators or dispatch registered local project tasks through Computer and Project Orchestr...
Launch and drive coding agents (codex, claude, agy) through the Herdr CLI; requires a herdr pane (HERDR_ENV=1). Use befo...
Read before driving Herdr panes (sending text or keys to an agent pane, checking on panes you orchestrate, launching an...
Act as the explicitly assigned Lead in a Herdr engineering session, one Claude or Codex agent that holds both the Manage...
Act as the explicitly assigned Manager or architect in a Herdr engineering session. Use when a Claude or Codex agent has...
Use when inspecting or operating Herdr sessions, workspaces, tabs, panes, agents, terminal output, agent messaging, or w...
Orchestrate agent workers through Herdr from any host agent, with capability-based routing, supervised integration, and...
Coordinate multiple CLI agents in herdr with scoped briefs, verified startup, permission handling, independent review, a...
Audit herdr release readiness by comparing commits since the base release against next-release changelog and docs. Use w...
Install the hook that renames the Herdr agent, pane and tab to match a Claude Code or Codex session renamed with /rename...
Use when the user asks to "set up herdr", "configure herdr sessions", "herdr vs tmux", "herdr LaunchAgent", or needs to...
Create and control a disposable named Herdr session from inside an existing Herdr session. Use for isolated Herdr runtim...
Act as an explicitly assigned independent Verifier or dedicated tester in a Herdr engineering run, e.g. Claude Haiku 5.5...
Implement a bounded task either in an explicitly assigned governed Herdr run or as a directly assigned standalone task....
Wrap up work that ran across many Herdr sessions: inventory its panes, worktrees, Docker, processes and browser daemons,...
HERE integration. Manage data, records, and automate workflows. Use when the user wants to interact with HERE data.
Automate Here tasks via Rube MCP (Composio). Always search tools first for current schemas.
Publish files and folders to the web instantly. Static hosting for HTML sites, images, PDFs, and any file type. Use when...
Publish sites to {slug}.here.now and store files in Drives.
here.now lets agents publish websites and files to live URLs in seconds. Publish HTML, documents, images, PDFs, videos,...
Publish an intentional static-site or file snapshot to here.now, or keep and hand off private agent artifacts through he...
Publishes static folders or files to instant shareable here.now URLs. Use when the user wants publish, host, deploy, sha...
Runs directional ablation and refusal-direction analysis for open-weight models the user may modify; use to reduce benig...
Heretic — automatic censorship removal (abliteration) for local LLMs via transformer weight manipulation. Removes refusa...
Heretic — fully automatic LLM censorship removal (abliteration) and serving the result via Ollama. Wraps p-e-w/heretic:...
Review condition and treatment evidence, plan preventive care and site conservation, record historic fabric, and organiz...
Use Hermes Tweet when Hermes Agent needs a native X/Twitter plugin for reading posts, exploring public data, and running...
Hermes Agent's Telegram gateway — bot identity, slash-command routing, callback handling, threading behavior, and the lo...
Configure, troubleshoot, update, or extend Hermes Agent itself. Use this before answering questions about Hermes CLI com...
Navigate and extract reusable design patterns from the Hermes Agent source code for application in our project. It cover...
hermes-agent-skill-authoring — Author in-repo SKILL.md: frontmatter, validator, structure.
Use when a branch, pull request, Kanban task, or implementation must be reviewed separately for intent fidelity, reposit...
Read-only compatibility audit between `hermes-agent-setup` and the latest stable upstream `hermes-agent` release plus of...
hermes-config-editing — Edit Hermes Agent configuration values — settings, compression, model config — with reliable pat...
Diagnose why a Hermes Agent setting/flag/env var is or isn't taking effect. Use when the user reports "I set X, reloaded...
hermes-context-optimization — Optimize Hermes startup/context payloads, compression, tool-schema loading, memory/skill i...
Use when Hermes acts as the vault coordinator for canonical promotion, duplicate-topic consolidation, merge decisions, a...
Decoding Hermes crashes and minified production stack traces. Use for "address at index.android.bundle" frames, unsymbol...
File-bus cron state machine and Hermes profile isolation rules for PumpGrok. Use when installing profiles, running desk_...
Diagnose Hermes cron jobs that ran successfully at scheduler level but produced empty, missing, or non-actionable user o...
Create lightweight Hermes cron jobs that offload work into a local pre-run script, avoid chat-context overhead, and send...
Multi-chain crypto + Web3 agent toolkit untuk Hermes. Wajib digunakan kapan pun user minta operasi on-chain — buat walle...
Configure custom/OpenAI-compatible vision providers in Hermes Agent (Kimi, DeepSeek, Azure, etc.)
hermes-desktop-plugins — Write desktop app plugins that add UI panes and commands.
Write desktop app plugins that add UI panes and commands.
Use when running a read-only diagnostic review of recent Hermes sessions to find recurring mistakes, failed tool calls,...
Continuous self-improvement system for Hermes Agent. Analyzes your past sessions to find recurring failures and skill ga...
Reference research on the Hermes Agent ecosystem — deployment templates, ecosystem maps, brain/memory layers, expert rol...
Use when a Hermes environment must be safely migrated between machines with staged exports, integrity manifests, secret...
Trigger: broad exploration, multi-file reads, tests/builds, fresh review, or multi-step debug. Orchestrate complex work...
Install pre-built external AI agent skills from GitHub (agentskills.io / Claude Code / OpenClaw ecosystem) directly into...
Use when Hermes messaging gateway failures must be diagnosed across process state, adapters, credential posture, logs, d...
Load when Claude, Codex, Antigravity, or another external agent needs to call Hermes GPT as a worker, ask it to use Herm...