Harness · 综合市场
Harness
让 AI 的能力，落到实处。
技能、MCP 服务、提示词、助手与连接器。每一项都写明作者、版本和所需权限。
已上架21,004
- MCP 服务18,853
- 技能1,282
- 助手651
- 提示词218
共 0 项
模型专职助手，也就是子智能体。装进 Claude Code、Codex 这类智能体后，主会话会把相关的活交给它。
- AI Data Remediation Engineermsitarzewski 158kSpecialist in self-healing data pipelines — uses air-gapped local SLMs and semantic clustering to automatically detect, classify, and fix data anomalies at scale. Focuses exclusively on the remediation layer: intercepting bad data, generating deterministic fix logic via Ollama, and guaranteeing zero data loss. Not a general data engineer — a surgical specialist for when your data is broken and the pipeline can't stop.模型
- LLM finetuning architectwshobson· llm-finetuning 40kFine-tuning strategist who owns the eval gate and method/model selection. Refuses to plan training without a baselined eval harness.Opus架构模型
- Spinning Up in Deep RLalirezarezvani· spinning-up-deep-rl 28kAnswers from the knowledge base compiled from Spinning Up in Deep RL by Joshua Achiam (OpenAI). Loads the master frameworks first and reads a single chapter file on demand rather than the whole source. Refuses to answer beyond what the source covers.Opus1 个技能笔记与知识库模型
- LLM finetuning training engineerwshobson· llm-finetuning 40kFine-tuning implementation workhorse — prepares datasets, generates Unsloth-first training scripts, launches and monitors runs, and exports artifacts. Use after a training brief exists, for dataset preparation, training execution, or model export.Sonnet模型
- LLM Post-Training Engineermsitarzewski 158kEvidence-driven owner for SFT, preference optimization, RLHF/RLVR, MoE post-training, and the release gates that turn a checkpoint into a defensible model change.模型
- Wiki librarianalirezarezvani· llm-wiki 28kDispatched sub-agent that answers queries against an LLM Wiki vault. Reads index.md first, drills into 3-10 relevant pages across categories, synthesizes an answer with inline [[wikilink]] citations, and offers to file the answer back into the wiki as a new comparison or synthesis page. Spawn when the user asks a substantive question the wiki might answer, says "what does the wiki say about X", "compare A and B across my sources", or wants to explore a topic.Sonnet1 个技能笔记与知识库模型
- Prompt Engineermsitarzewski 158kSpecialist in crafting, testing, and systematically optimizing prompts for LLMs — turning vague instructions into reliable, production-grade AI behaviors.中风险测试模型
- AI Citation Strategistmsitarzewski 158kExpert in AI recommendation engine optimization (AEO/GEO) — audits brand visibility across ChatGPT, Claude, Gemini, and Perplexity, identifies why competitors get cited instead, and delivers content fixes that improve AI citations营销与 SEO模型
- Prompt engineerwshobson· llm-application-dev 40kExpert prompt engineer specializing in advanced prompting techniques, LLM optimization, and AI system design. Masters chain-of-thought, constitutional AI, and production prompt strategies. Use when building AI features, improving agent performance, or crafting system prompts.跟随主会话架构模型
- Wiki ingestoralirezarezvani· llm-wiki 28kDispatched sub-agent that ingests a new source into an LLM Wiki vault. Reads the source, proposes TL;DR and key claims, identifies which entity/concept/synthesis pages will be touched, flags contradictions with existing pages, and — after user confirmation — writes the source summary, updates cross-references across 5-15 pages, regenerates the index, and appends a standardized log entry. Spawn when the user says "ingest this", "add this paper/article/book to the wiki", or drops a file into raw/.Opus1 个技能笔记与知识库模型
- Wiki librarianalirezarezvani 28kDispatched sub-agent that answers queries against an LLM Wiki vault. Reads index.md first, drills into 3-10 relevant pages across categories, synthesizes an answer with inline [[wikilink]] citations, and offers to file the answer back into the wiki as a new comparison or synthesis page. Spawn when the user asks a substantive question the wiki might answer, says "what does the wiki say about X", "compare A and B across my sources", or wants to explore a topic.Sonnet1 个技能笔记与知识库模型
- Wiki ingestoralirezarezvani 28kDispatched sub-agent that ingests a new source into an LLM Wiki vault. Reads the source, proposes TL;DR and key claims, identifies which entity/concept/synthesis pages will be touched, flags contradictions with existing pages, and — after user confirmation — writes the source summary, updates cross-references across 5-15 pages, regenerates the index, and appends a standardized log entry. Spawn when the user says "ingest this", "add this paper/article/book to the wiki", or drops a file into raw/.Opus1 个技能笔记与知识库模型
- AI engineerwshobson· llm-application-dev 40kBuild production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations.跟随主会话智能体模型
- LLM finetuning eval engineerwshobson· llm-finetuning 40kEvaluation gatekeeper for fine-tuning — builds golden sets and graders, calibrates judges, baselines base models, and issues checkpoint promotion verdicts. Use when constructing an eval harness before training or gating a trained checkpoint. Deliberately independent from training execution.Sonnet模型
- Eval judgewshobson· plugin-eval 40kLLM judge for plugin quality assessment. Scores skills on triggering accuracy, orchestration fitness, output quality, and scope calibration using anchored rubrics.Sonnet健康模型
- Research Agentalirezarezvani· research 28kHybrid research router + fallback persona. Walks 2-4 minimal intake questions (Q1 question + Q2 output preference; Q3 disambiguation only when classification is ambiguous; Q4 only if fallback). Deterministically classifies research questions by keyword signals and routes to one of 6 specialists (pulse / grants / litreview / syllabus / patent / dossier) at ≥2-signal confidence. Falls back to own plan-decompose-search-synthesize workflow when no specialist matches. NEVER delegates silently — always surfaces routing decision and accepts override. Refuses LLM-reasoned classification (must be deterministic keyword matching). Refuses to pre-answer specialist questions (lets specialists run their own intake).Opus1 个技能研究模型
- AEO Agentalirezarezvani 28kAnswer Engine Optimization (AEO) specialist agent. Use when content needs to be optimized for citation by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) rather than for traditional search rankings. Orchestrates the aeo skill — runs E-E-A-T audit, generates optimization variants in conservative/balanced/aggressive modes, and maintains a citation tracking ledger. Industry-aware (8 industries with calibrated thresholds). Distinguishes AEO from SEO and refuses to optimize for one channel at the expense of the other. Voice — pragmatic content strategist; respects existing SEO investments; insists on real first-person evidence over fabricated authority signals.Opus1 个技能音频与语音营销与 SEO模型