Explore

How one can create llm skill and publish it to llmskillhub.com

Route a prompt to the right Venice text model based on privacy tier (anonymized / private / TEE / E2EE), modality (vision / audio / video input), capability (reasoning, code, function calling, web search, large context, structured output), and cost. Use when a local agent (Claude Code, Hermes, NanoClaw, Codex CLI, etc.) needs to decide whether to handle a prompt locally or escalate to Venice, and if escalating, which Venice text model to call. Sits one level above venice-models (model discovery) and before venice-chat (the call surface).

Call POST /chat/completions on Venice. Covers the OpenAI-compatible request shape, Venice-only venice_parameters (web search, E2EE, characters, thinking control, X search), multimodal inputs (images/audio/video), tool calls, reasoning controls, streaming, prompt caching, structured output, and model feature suffixes.

Run the additional paper-compatible optimization workflow with a frozen benchmark repository. Use only when the user asks to generate or reuse an eval set, establish a baseline, improve probe or PR-validation scores, compare a Skill against a benchmark, or reproduce the evaluation loop described in the SkillHone paper. Do not use for a single defect observed during normal Agent work; use skillhone-auto-optimization for the default path.

Mandatory interception workflow for a reproducible defect encountered while any Agent is using a skill. Invoke this before editing implementation files or installing dependencies when a referenced script is missing, a documented command or repository test fails, or another target-skill defect is confirmed. First create or reuse a sanitized local Issue, then let SkillHone dispatch the repair into a tested Git-backed pull request. This applies regardless of the Agent, current working directory, or the user's original task. No eval repo or benchmark data is required.

Local Issue, pull-request, and Wiki workbench for agent skills. Use when a user asks what skill problems, Issues, PRs, repair trajectories, work records, completed optimizations, pending fixes, or pending synchronization exist; when an Agent needs to report a reproducible skill defect; or when the user wants to initialize, inspect, optimize, review, merge, or synchronize a local skill repair. If a managed Skill has a missing referenced file, failing test, or broken command, invoke skillhone-auto-optimization before editing implementation files or installing dependencies. Uses a local SQLite/Git backend and DeepSeek Harness for optimization, with no hosted Git service.

**WORKFLOW SKILL** — Iteratively improve skill frontmatter compliance using the Ralph loop pattern. WHEN: "run sensei", "sensei help", "improve skill", "fix frontmatter", "skill compliance", "frontmatter audit", "score skill", "check skill tokens". INVOKES: token counting tools, test runners, git commands. FOR SINGLE OPERATIONS: use token CLI directly for counts/checks.

Create and push reusable skills to SkillNote from Codex when repeated instructions are detected or the user says "create a skill", "save this pattern", "push a skill". Guides drafting, review, collection selection, and publishing.

Run the research/audit handoff loop between an agentic coding harness and a slow, non-agentic frontier reasoning model (GPT Pro on the ChatGPT web UI, or equivalent) with the codebase pre-loaded as split zip bundles. Author a high-signal prompt, then later take the returned report, verify every finding against the LIVE codebase, and implement what holds up. Use whenever the operator wants to send something to a deep external model, prep a prompt or report, scope an issue for deep research, bug-hunting, or optimization analysis, OR when a report comes back and needs checking against the code before anything is implemented. This is the WORKFLOW skill — to build or refresh the zip bundles themselves, use the separate `gptpro` export skill.

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.

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

After you give a substantive answer or draft that the user may act on — advice or recommendations, drafted artifacts such as goals, plans, pitches, proposals, or emails, estimates or projections, analysis or interpretation of data, factual claims they may rely on, or a multi-step argument — invoke this skill BEFORE finalizing your reply and then, if it applies, append 2-3 short follow-up questions, each tied to something specific in what you just produced, that help the user check key facts, probe the reasoning or assumptions, and notice missing context. Do this at most once per conversation. Skip it when the user asked a trivial how-to or simple lookup, wants a purely educational explanation, asked you only to format, convert, or assemble a file from content they provided, is writing code they will run, is doing creative writing or casual chat, or already asked you to double-check, cite, or review — the skill file explains these boundaries and the exact output format.

Use when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'. Validates agent configuration files against 456 rules across 10+ AI tools.