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21,010
- MCP 服务18,859
- 技能1,282
- 助手651
- 提示词218
共 0 项
文档专职助手，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。
- Document analysisanthropics· brand-voice 28kAnalyzes brand documents to extract voice attributes, messaging, terminology, and examples. Use this agent when processing multiple brand documents or performing cross-document pattern recognition.Sonnet文档音频与语音营销与 SEO
- Discover brandanthropics· brand-voice 28kAutonomously searches enterprise platforms to discover brand-related documents, transcripts, and design assets. Use when the user wants to build brand guidelines but doesn't know where materials are, or wants a comprehensive brand content audit.Sonnet文档营销与 SEO
- PDF Engine Architectmsitarzewski 158kArchitect and specialist in deterministic HTML-to-PDF document compilation, Playwright browser context pools, dynamic Euclidean page sizing, LayoutNG subpixel budgeting, tagged PDF (PDF/UA-1 & PDF/A-2b), and 1:1 sheet canvas editors.浏览器自动化文档架构
- AEO Foundations Architectmsitarzewski 158kExpert in AI Engine Optimization infrastructure — implements llms.txt, AI-aware robots.txt, token-budgeted content, structured Markdown availability, and agent discovery files so AI crawlers, citation engines, and browsing agents can find, parse, and act on your site文件文档架构
- Wiki linteralirezarezvani 28kDispatched sub-agent that runs a periodic health check on an LLM Wiki vault. Runs mechanical checks via scripts (orphans, broken links, stale pages, missing frontmatter, duplicate titles, log gaps), does semantic checks (contradictions, stale claims, cross-reference gaps, concepts missing their own page), and produces a markdown report with suggested actions. Spawn weekly, after batch ingests, or when the user says "check the wiki" / "lint my wiki" / "audit the vault".Opus1 个技能文档笔记与知识库健康
- ATS Validator Architectmsitarzewski 158kArchitect and validator for Applicant Tracking Systems (ATS) and resume parsers. Combines deterministic information retrieval (BM25/TF-IDF and n-grams without AI), quantified Google/IBM X-Y-Z heuristics calibrated by seniority, layout linearization and PDF text layer integrity auditing, regulatory compliance (EU AI Act, NYC LL 144), sub-5ms client-side execution, and Agent-Native BYOK architecture.文档法律架构
- Legal Document Reviewmsitarzewski 158kComprehensive legal document review specialist for contracts, litigation documents, and real estate agreements — summarizing documents, flagging risk clauses, comparing contract versions, and checking compliance across any law firm size or practice area文档法律
- Master Plan Architectmsitarzewski 158kMaster planning architect, technical educator, and ruthless plan critic who specializes in deep architectural teaching, Red Teaming / risk critique, and crafting comprehensive Implementation Plans in Markdown with ZERO code execution.文档架构
- C4 contextwshobson· c4-architecture 40kExpert C4 Context-level documentation specialist. Creates high-level system context diagrams, documents personas, user journeys, system features, and external dependencies. Synthesizes container and component documentation with system documentation to create comprehensive context-level architecture. Use when creating the highest-level C4 system context documentation.Sonnet文档技术文档架构
- Document Generatormsitarzewski 158kExpert document creation specialist who generates professional PDF, PPTX, DOCX, and XLSX files using code-based approaches with proper formatting, charts, and data visualization.文档办公数据分析
- Wiki linteralirezarezvani· llm-wiki 28kDispatched sub-agent that runs a periodic health check on an LLM Wiki vault. Runs mechanical checks via scripts (orphans, broken links, stale pages, missing frontmatter, duplicate titles, log gaps), does semantic checks (contradictions, stale claims, cross-reference gaps, concepts missing their own page), and produces a markdown report with suggested actions. Spawn weekly, after batch ingests, or when the user says "check the wiki" / "lint my wiki" / "audit the vault".Opus1 个技能文档笔记与知识库健康
- Inbox-Setup Agentalirezarezvani· email 28kOne-time email-triage onboarding persona. Conducts an 8-section interactive interview (~25-31 grill-me questions) to build a personalized knowledge base of 7 markdown files in ${WORKSPACE}/Email/ that powers the companion inbox-triage skill. Refuses to batch questions. Refuses to skip the sample-emails ask (S3). Refuses to overwrite existing files without per-file consent on re-run. Refuses to persist sensitive credentials.Opus1 个技能文件文档邮件
- Handoff Authoralirezarezvani· handoff 28kConversation-handoff author. Compacts the current session into a markdown handoff for a fresh agent. Tailors content to next-session focus. Refuses to duplicate content from PRDs/plans/ADRs/issues/commits — references them by path or URL instead. Recommends specific skills for the next session.Opus1 个技能文档
- Litreview Agentalirezarezvani· litreview 28kAcademic literature orientation persona. Walks 3 forcing intake questions (research question specificity + framework hint + tentative depth) before any search, then runs reconnaissance + targeted searches per depth tier via the free keyless lane (PubMed E-utilities + OpenAlex; Consensus MCP added only when connected), then halts at an interactive checkpoint for framework + sub-area + depth confirmation before consuming search budget. Refuses parallel search calls (1 q/sec is non-negotiable). Refuses to cite training knowledge as session results. Refuses to skip the post-Phase-2 checkpoint. Outputs an 8-section .docx research guide as a 'launching pad' for a researcher entering an unfamiliar field.Opus1 个技能文档研究
- Grants Agentalirezarezvani· grants 28kNIH grant research persona for clinical researchers. Walks 6 forcing intake questions (research idea + career stage + prelim data + environment + submission posture + known institute targets) before any search. Runs 5-facet Consensus positioning analysis + RePORTER POST queries (NEVER web_fetch for RePORTER — it's POST-only) + NOSI fetches. Refuses parallel Consensus calls (1 q/sec). Refuses mechanism recommendations based on career stage alone (scope matters). Always includes program officer recommendation (mandatory). Outputs 9-section .docx with audit log.Opus1 个技能文档研究健康
- Handoff authoralirezarezvani· handoff 28kProductivity persona for writing handoff documents. Terse, no-duplication, references-not-copies. Invoke when the user signals intent to pass work to a fresh agent ('hand this off', 'summarize this for a new session', 'I'm ending this session', 'pick this up later'), or when implicit signals appear (user switching machines, ending the day mid-task, conversation growing long without a natural stopping point). Walks the mandatory handoff_prompt.md checklist before writing; runs the redaction linter before save; suggests 3-5 skills (never more) for the next session.跟随主会话文档写作
- Dossier Agentalirezarezvani· dossier 28kDecision-grade entity research persona. Walks 6 forcing intake questions (subject identity + subject type + purpose + hypothesis-MANDATORY + depth + sensitivities). Refuses to produce a dossier without Q4 hypothesis stated. Allocates ≥30% of search budget to disconfirming evidence (refuses confirmation-biased dossiers). Tags every flag with source-reliability tier (primary/secondary/tertiary). Outputs 9-section .docx with verdict on hypothesis (SUPPORTED/PARTIALLY/DISPROVEN/INCONCLUSIVE) + 3-5 finding-tied conversation hooks.Opus1 个技能文档研究
- Markdown HTML orchestratoralirezarezvani· markdown-html 28kDensity-first markdown-to-HTML converter. Routes long markdown files (≥ 100 lines per Shihipar's threshold) to one of three converter sub-skills (md-document / md-review / md-slides) via the markdown-html-orchestrator skill. Refuses below threshold or when the design-system isn't onboarded. Forks context so the full markdown body, diffs, and slide content stay out of the parent thread. Signature forcing question — "What decision does this HTML drive — is the reader skimming, deciding, or presenting?"Sonnet文件文档办公
- Patent Agentalirezarezvani· patent 28kPatent prior-art + landscape intelligence persona. Walks 6 forcing intake questions with mandatory sub-use-case commitment (novelty / FTO / landscape / diligence / litigation). Refuses to start without a sub-use-case picked. Refuses generic "patent help" requests. Searches Google Patents + Espacenet + USPTO + optional Lens.org sequentially at 1 q/sec. Always includes legal disclaimer for novelty + FTO sub-use-cases (signal, not legal advice). Family-resolves duplicates across jurisdictions. Outputs 8-section .docx with verdict + audit log.Opus1 个技能文档法律
- Syllabus Agentalirezarezvani· syllabus 28kCourse supplementary reading list persona. Walks 3 forcing intake questions (syllabus input format + course audience + year range) before parsing. Halts at grouping checkpoint after Phase 2 (proceed/merge/split/add/remove). Searches Consensus sequentially at 1 q/sec with applied-domain weaving (e.g., 'enzyme kinetics food processing' not just 'enzyme kinetics'). Calibrates summary jargon to audience (undergrad defines every term; grad assumes technical fluency). Writes Bloom higher-order discussion questions tied to learning outcomes. Generates .docx via bundled JS script.Opus1 个技能文档教育
- Company Architectalirezarezvani· arquiteto-de-empresa 28kCompany Architect — a senior chief of staff who builds a business from scratch as an OKF (Open Knowledge Format) bundle: a tree of version-controllable .md files with frontmatter type, links forming a graph, and reserved index.md/log.md. Guides the founder through a 12-phase interview (foundation, strategy, market, financial, sales, marketing, product, operations, tech, people, legal, governance), one phase at a time, at most 3-5 questions per block, confirming before generating each concept. Trigger when the user wants to create, structure, or document an entire company as folders and markdown files, or mentions company as code, company knowledge base for AI, OKF, or knowledge bundle. Works in English. Never dumps the company all at once — it interviews, validates, and builds phase by phase.Opus1 个技能文件文档笔记与知识库
- Human Gate Agentalirezarezvani· human-gate 28kRuns the human-verification lane of an agent loop. Builds a single-file review page for a Markdown or HTML artifact, hands the reviewer a path and ends the turn (never blocks polling for a human), collects batched feedback as structured batch.v1 data, and runs a gate that refuses to close while a BLOCKER is open, the reviewer is unnamed, or nobody has reviewed at all. Use before shipping a plan, spec, RFC, report, or any irreversible action, and whenever the user says "let me review that", "get sign-off", or "don't ship until I've seen it".Opus1 个技能文档