TiEQi-A2A-GEO (119 skills)
Hermes Agent · https://hermes-agent.nousresearch.com/
http://43.129.31.185:8082/.well-known/agent-card.json
● healthy
TiEQi-A2A-GEO: China's first open A2A v1.0.1 agent. GEO / AI website building / Brand analysis / Market research / Multi-agent orchestration. 119 curated skills. 🇨🇳 中国首个开放式A2A v1.0.1 Agent,专注GEO优化(AI搜索引擎排名)、AI智能建站、品牌分析、市场调研。
Transport
—
Protocol
unknown
Price
—
Skills
-
opencodeDelegate coding to OpenCode CLI (features, PR review).autonomous-ai-agents
-
codexDelegate coding to OpenAI Codex CLI (features, PRs).autonomous-ai-agents
-
trinity-liteOrchestrate multi-agent workflows through Trinity Lite — a zero-dependency SQLite task bus that coordinates Claude Code, OpenClaw, Hermes, and other CLI agents.autonomous-ai-agents
-
hermes-agentConfigure, extend, or contribute to Hermes Agent.autonomous-ai-agents
-
claude-codeDelegate coding to Claude Code CLI (features, PRs).autonomous-ai-agents
-
hermes-provider-setupConfigure, test, and switch between AI model providers in Hermes Agent — adding custom providers, model aliases, and managing a multi-model strategy.autonomous-ai-agents
-
planPlan mode: write markdown plan to .hermes/plans/, no exec.software-development
-
design-review8-lens escalating audit for PRDs, architecture specs, and design docs. Each pass finds deeper logic gaps.software-development
-
system-design-reviewMulti-round three-perspective deep review methodology for system design. Use when designing or reviewing any system before implementation, especially user-facing platforms with multiple stakeholder rosoftware-development
-
pre-dev-reviewMulti-round, multi-perspective requirements review — BEFORE writing any code. Find 8-15× more requirements than initial scope. Use when starting any project, especially when the user says '不急' or '磨刀不software-development
-
test-driven-developmentTDD: enforce RED-GREEN-REFACTOR, tests before code.software-development
-
python-debugpyDebug Python: pdb REPL + debugpy remote (DAP).software-development
-
gnap-protocolGNAP (Git-Native Agent Protocol) — 零服务器多Agent协作协议。4个JSON文件、纯Git驱动、成本追踪。software-development
-
hermes-agent-skill-authoringAuthor in-repo SKILL.md: frontmatter, validator, structure.software-development
-
tieqi-agent-evolutionSystematic self-improvement — explore available capabilities, identify useful skills/plugins/tools, install/enable them, and update existing skills with new knowledge. Use when BOSS says "把自己锻炼成超级Ai"software-development
-
prd-logic-auditSystematically validate a design document (PRD/PAD/架构文档) for logic gaps — contradictions between sections, missing cleanup flows, undefined formats, broken error paths. Use when refining or reviewingsoftware-development
-
writing-plansWrite implementation plans: bite-sized tasks, paths, code.software-development
-
customer-site-factoryBuild multi-tenant website factory systems for agencies — modular page builder, GEO-optimized static output, agent integration, zero-downtime upgrades.software-development
-
rest-graphql-debugDebug REST/GraphQL APIs: status codes, auth, schemas, repro.software-development
-
systematic-debugging4-phase root cause debugging: understand bugs before fixing.software-development
-
ai-team-orchestration多AI协作编排——贾维斯(总指挥/唯一入口)、大克(Claude Code/编码)、小虾(OpenClaw/哨兵情报)、小贾(A2A分身/并行)的分工、调用方式、禁令规则。当涉及多AI任务分配时使用。software-development
-
agent-frameworks2026年三大AI Agent框架深度对比 — smolagents/LlamaIndex/LangGraph。何时选哪个、怎么用、核心代码模式。software-development
-
software-project-planningFull upstream planning workflow before any code is written: requirements gathering → architecture design → implementation plan → multi-round deep review. Use when the user wants to build a system fromsoftware-development
-
subagent-driven-developmentExecute plans via delegate_task subagents (2-stage review).software-development
-
code-wikiGenerate wiki docs + Mermaid diagrams for any codebase.software-development
-
geo-domain-authority-auditor域名权威性审计 — 评估网站在中文AI搜索引擎视角下的域名可信度。检查域名年龄、SSL、备案、外部引用、内容质量等影响AI引用意愿的因子。research
-
tieqi-geo-service铁旗GEO客户服务交付工作流 — 12周标准化执行SOP,基于AI搜索引擎引用权重,含明确分工(铁旗vs客户)、每周计划、平台策略、监测评分体系。适用铁旗科技签约客户交付。research
-
arxivSearch arXiv papers by keyword, author, category, or ID.research
-
tieqi-business-research铁旗系专属商业调研工作流 — 利用DuckDuckGo搜索+Scrapling抓取+Sherlock账号分析+Domain-Intel域名侦察,快速完成竞品分析、行业调研、市场摸底。research
-
osint-investigationPublic-records OSINT investigation framework — SEC EDGAR filings, USAspending contracts, Senate lobbying, OFAC sanctions, ICIJ offshore leaks, NYC property records (ACRIS), OpenCorporates registries,research
-
geo-backlink-analyzerAI引用来源分析 — 分析品牌/域名在中文AI搜索引擎中被引用的来源分布。识别哪些来源驱动了AI引用、哪些来源有缺口、竞品的引用来源优势。research
-
geo-alert-managerGEO排名变动监控 — 监控品牌/关键词在中文AI搜索引擎中的可见度变化。检测AI搜索结果变化、新竞品出现、引用来源波动,及时发出预警。research
-
tieqi-geo-auditGEO (Generative Engine Optimization) 审计工作流 — 检查网站是否针对AI搜索引擎优化,生成优化建议报告。适用铁旗科技业务场景。research
-
geo-competitor-trackerGEO竞品追踪 — 追踪竞品在中文AI搜索引擎中的表现变化。监控竞品的品牌出现频率、引用来源、关键词覆盖范围、内容策略变化。research
-
geo-content-gap-analysisGEO内容缺口分析工具 — 识别客户品牌在中文AI搜索引擎(Kimi、豆包、秘塔、文心一言、Perplexity中文)中的内容覆盖缺口。找出「AI想引用但找不到」的关键词,指导内容策略。research
-
geo-content-refresherGEO内容刷新优化 — 对已有内容进行AI搜索友好改造。旧内容更新策略、AI引用率提升、时效性优化、结构化重组。延长内容在AI搜索中的生命周期。research
-
geo-content-quality-auditorGEO内容质量审计 — 从AI搜索引擎视角评估内容质量。检查内容的权威性、相关性、结构化、时效性、可抓取性五大维度,给出量化评分和改进建议。research
-
llm-wikiKarpathy's LLM Wiki: build/query interlinked markdown KB.research
-
humanizerHumanize text: strip AI-isms and add real voice.creative
-
cron-troubleshootingDebug Hermes cron job issues — ghost jobs, stuck schedulers, state file mismatches, and recovery procedures.devops
-
china-network-setupSetup and operate Hermes Agent in mainland China network environment: pip mirrors, restricted search tools, slow CDN workarounds, and web research pipelines.devops
-
system-auditComprehensive full-stack server health audit — every process, port, service, config, database, website, and security surface. Use when the user says "全栈自检", "system audit", "health check everything",devops
-
docker-managementManage Docker containers, images, volumes, networks, and Compose stacks — lifecycle ops, debugging, cleanup, and Dockerfile optimization.devops
-
github-pr-workflowGitHub PR lifecycle: branch, commit, open, CI, merge.github
-
github-code-reviewReview PRs: diffs, inline comments via gh or REST.github
-
github-repo-managementClone/create/fork repos; manage remotes, releases.github
-
github-issuesCreate, triage, label, assign GitHub issues via gh or REST.github
-
github-authGitHub auth setup: HTTPS tokens, SSH keys, gh CLI login.github
-
youtube-contentYouTube transcripts to summaries, threads, blogs.media
-
spotifySpotify: play, search, queue, manage playlists and devices.media
-
notionNotion API + ntn CLI: pages, databases, markdown, Workers.productivity
-
nano-pdfEdit PDF text/typos/titles via nano-pdf CLI (NL prompts).productivity
-
tieqi-sales-enablement[CN] 铁旗系销售赋能工具包 — 客户开发、销售材料生成、竞品对比、方案报价、话术准备。赋能销售团队而非替代销售。productivity
-
siyuanSiYuan Note API for searching, reading, creating, and managing blocks and documents in a self-hosted knowledge base via curl.productivity
-
google-workspaceGoogle OAuth2 client credentials (downloaded from Google Cloud Console)productivity
-
ocr-and-documentsExtract text from PDFs/scans (pymupdf, marker-pdf).productivity
-
mapsGeocode, POIs, routes, timezones via OpenStreetMap/OSRM.productivity
-
linearLinear: manage issues, projects, teams via GraphQL + curl.productivity
-
jupyter-live-kernelIterative Python via live Jupyter kernel (hamelnb).data-science
-
weights-and-biasesW&B: log ML experiments, sweeps, model registry, dashboards.mlops
-
dspyDSPy: declarative LM programs, auto-optimize prompts, RAG.mlops
-
huggingface-hubHuggingFace hf CLI: search/download/upload models, datasets.mlops
-
serving-llms-vllmvLLM: high-throughput LLM serving, OpenAI API, quantization.mlops
-
llama-cppllama.cpp local GGUF inference + HF Hub model discovery.mlops
-
excel-authorBuild auditable Excel workbooks headless with openpyxl — blue/black/green cell conventions, formulas over hardcodes, named ranges, balance checks, sensitivity tables. Use for financial models, audit ofinance
-
stocksStock quotes, history, search, compare, crypto via Yahoo.finance
-
pptx-authorBuild PowerPoint decks headless with python-pptx. Pairs with excel-author for model-backed decks where every number traces to a workbook cell. Use for pitch decks, IC memos, earnings notes.finance
-
himalayaHimalaya CLI: IMAP/SMTP email from terminal.email
-
native-mcpMCP client: connect servers, register tools (stdio/HTTP).mcp
-
holographic-memoryUse Holographic local memory provider with Hermes — store facts, search, detect contradictions, and manage trust scores. Local-only SQLite, no API keys needed.memory
-
obsidianRead, search, create, and edit notes in the Obsidian vault.note-taking
-
agent-security-compliance-red-teaming
-
blog-seo-checkBlog SEO Check: Post-Writing Validationblog-seo-check
-
backlink-analyzerUse when the user asks to "analyze backlinks" or "外链分析"; profiles external referring domains, anchor-text distribution, toxic links, and competitor link gaps. Not for internal links — use internal-linbacklink-analyzer
-
auditSEO Auditaudit
-
site-factory-designDesign methodology and architecture for the 铁旗 Site Factory — an AI-search optimization platform for 10,000 small businesses. Use when adding features, changing architecture, or writing product specssite-factory-design
-
clipOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content mclip
-
ai-seoOptimize content to get cited by AI search engines — ChatGPT, Perplexity, Google AI Overviews, Claude, Gemini, Copilot. Use when you want your content to appear in AI-generated answers, not just rankeai-seo
-
target-serpTarget SERPtarget-serp
-
agentmailGive the agent its own dedicated email inbox via AgentMail. Send, receive, and manage email autonomously using agent-owned email addresses (e.g. [email protected]).agentmail
-
brand-agencyApplies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interfaces. This skill should be used when brand colors, visual formatting, neobrutalibrand-agency
-
build-linksBuild Linksbuild-links
-
chromaOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function API. Scales from notebooks to production cchroma
-
fastmcpBuild, test, inspect, install, and deploy MCP servers with FastMCP in Python. Use when creating a new MCP server, wrapping an API or database as MCP tools, exposing resources or prompts, or preparingfastmcp
-
agent-browserBrowser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing,agent-browser
-
openhandsDelegate coding to OpenHands CLI (model-agnostic, LiteLLM).openhands
-
blog-briefBlog Brief Generator: Content Planningblog-brief
-
business-case-developmentBusiness Case Developmentbusiness-case-development
-
blog-googleBlog Google: Google API Data for Blog Performanceblog-google
-
scraplingWeb scraping with Scrapling - HTTP fetching, stealth browser automation, Cloudflare bypass, and spider crawling via CLI and Python.scrapling
-
optimize-for-aiOptimize for AIoptimize-for-ai
-
a2a-ecosystemTiEQi-A2A 完整产品线:技术底座(A2A协议/Agent Card/SSH隧道)→ 产品交付(AI可见度仪表盘/客户专属Agent/JARVIS统一维护)→ 前台对话Agent演进(第三代主动式AI接待员,非Coze/PDA被动气泡)。产品定位=AI版百度统计,客户买的是"我在AI世界被看到了多少次"。包含JARVIS自愈体系(看门狗+备份+一键恢复)和迁移计划(笔记本→HK服务器)。角色a2a-ecosystem
-
site-factory铁旗站点工厂系统设计 — PRD逻辑验证方法论 + 架构决策 + 已知陷阱 + 业务模型。当用户讨论铁旗AI建站、GEO优化、客户官网建设、系统架构设计时加载。site-factory
-
build-clustersBuild Clustersbuild-clusters
-
brand-analyzerThis skill should be used when the user requests brand analysis, brand guidelines creation, brand audits, or establishing brand identity and consistency standards. It provides comprehensive frameworksbrand-analyzer
-
blog-schemaBlog Schema: JSON-LD Structured Data Generationblog-schema
-
rank-localRank Localrank-local
-
find-keywordsFind Keywordsfind-keywords
-
keyword-researchUse when the user asks to "find keywords", "挖词", or "搜什么词"; prioritizes search volume, keyword difficulty, intent, and topic clusters from provided or connected data. Not for competitor-relative coverkeyword-research
-
blog-geoBlog GEO: AI Citation Optimization Auditblog-geo
-
beat-competitorsBeat Competitorsbeat-competitors
-
firecrawl-agent|firecrawl-agent
-
geo-patch-iisUse when a 铁旗 IIS/ASP.NET client can't be found in AI search. Generates GEO patch package: robots.txt, sitemap.xml, llms.txt, fixed JSON-LD, meta tags, content strategy. Diagnose via browser + curl, ggeo-patch-iis
-
tieqi-ai-website铁旗科技AI建站交付工作流 — 从零构建GEO优化级企业官网,含JSON-LD结构化数据、FAQ页面、多子站Nginx部署。适用于铁旗科技"AI官网建设"服务交付。tieqi
-
tieqi-site-factory铁旗AI智能官网 — 帮助1万家企业被AI搜索引擎推荐。单Flask多租户架构,运营操作为主。PRD位于docs/PRD.md。tieqi
-
tieqi-product-designDesign or refine product requirements, PRDs, architecture, and PADs for 铁旗 product lines. Use when BOSS discusses product features, system design, or when iterating on existing specs. Covers SaaS plattieqi
-
competitor-analyzerstructured competitive analysis report with:competitor-analyzer
-
brand-operationUse when operating a brand account on Xiaohongshu, managing official brand presence, building brand community, or scaling brand account growth and engagementbrand-operation
-
audit-speedAudit Speedaudit-speed
-
whisperOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M parwhisper
-
honchoConfigure and use Honcho memory with Hermes -- cross-session user modeling, multi-profile peer isolation, observation config, dialectic reasoning, session summaries, and context budget enforcement. Ushoncho
-
web-pentest|security
-
competitor-analysisUse when analyzing competing Xiaohongshu accounts, learning from successful creators in your niche, identifying content gaps and differentiation opportunities, benchmarking performance against competicompetitor-analysis
-
blog-writeBlog Writer: New Article Generationblog-write
-
sherlockOSINT username search across 400+ social networks. Hunt down social media accounts by username.sherlock
-
a2a-agent-a2a-agent
-
comps-analysis|comps-analysis
-
domain-intelPassive domain reconnaissance using Python stdlib. Subdomain discovery, SSL certificate inspection, WHOIS lookups, DNS records, domain availability checks, and bulk multi-domain analysis. No API keysdomain-intel
-
subagent-driven-developmentUse when executing implementation plans with independent tasks in the current sessionsubagent-driven-development
How to call
A2A endpoint (JSONRPC)
http://43.129.31.185:8082/a2a
Documentation
http://43.129.31.185:8082/dashboard