#### Gallery #### Contacts 405 W. Greenlawn Ave Lansing, Michigan 48910 contact@techjacksolutions.com +1-616-320-4064 [Twitter](https://x.com/GoTechJacks)[Facebook-f](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#)[Pinterest-p](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#)[Instagram](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#) [How Skills Work](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#section-how-skills-work) [The Curator System](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#section-curator) [Key Stats](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#section-key-stats) [Full Rankings](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#section-ranking-table) [Skill Deep Dives](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#section-skill-dives) [Installing Skills](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#section-installing) [Nous Portal Tools](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#section-portal) [Building Your Own](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#section-building) [Video Resources](https://techjacksolutions.com/ai-tools/hermes/best-hermes-skills/#section-videos) Light / Dark Nous Research # 10 Best Hermes Agent Skills The top cybersecurity pack alone ships 750+ MITRE ATT&CK-mapped skills. Below it, nine more community picks and self-generated patterns cover DevOps monitoring, project management, memory maintenance, and cross-platform messaging. These are the skills Hermes users actually keep running after the Curator's 7-day evaluation cycle weeds out the rest. We tested each one, graded them on community adoption and real-world utility, and ranked them accordingly. Honest notes on where each falls short are included. 40% faster tasks7-day Curator cycle6 install sources750+ ATT&CK skills _Last verified: May 13, 2026 \| Grounded from 62 verified sources_ * * * ## How Hermes Skills Work Hermes Agent skills are reusable automation routines stored as markdown files in `~/.hermes/skills/`. They come from two sources: the agent creates them automatically when it detects a recurring pattern, or you install them from the community. The self-generation mechanic is what sets Hermes apart from frameworks like Claude Code skills or Cursor rules. You don't have to write them. The agent notices what you keep doing and builds a skill for it. AI Tools Hub **Put governance around how your team uses AI.** The AI Acceptable Use Policy: a deploy-ready template that sets the rules for AI use. [Get the policy](https://techjacksolutions.com/downloads/ai-acceptable-use-policy-template/) [Browse all templates](https://techjacksolutions.com/download-templates/) Your purchase helps keep our hubs free to read. ### Self-Generated Skills After five or more tool calls for the same pattern, Hermes auto-creates a skill via the `skill_manage` tool. Each skill file contains a name, description, trigger conditions, implementation steps, and usage examples. These are living documents that refine themselves through a reflective phase after each execution, and the `patch` action allows skills to self-improve based on execution feedback. ### Community Skills Community skills come from external sources: GitHub repositories, the skills.sh registry, ClawHub (the OpenClaw marketplace with cross-compatibility), or direct URLs. On install, community skills are scanned and sandboxed from the Curator system to prevent external code from modifying your agent's core behavior. Skills auto-register as slash commands in messaging platforms, so a Telegram or Discord user can invoke them directly from chat. **How we picked these 10:** We evaluated skills by community adoption (forum mentions and GitHub activity, since exact install counts aren't publicly exposed by Hermes), breadth of utility (does it solve a problem most users face?), and Curator survival rate (does it last beyond the 7-day evaluation cycle?). Self-generated patterns that appear independently across unrelated users ranked higher because they represent genuine workflow needs rather than one person's pet project. Skills we considered but cut: **code-reviewer** (promising but inconsistent output quality), **notion-sync** (too many auth issues reported), and **auto-documenter** (frequently archived by the Curator for low usage). * * * ## The Curator System Introduced in Hermes v0.12.0 (April 30, 2026), the Curator is an automated skill management system that runs a 7-day evaluation cycle. It grades every skill across four dimensions: usage frequency, success rate, execution time, and user satisfaction. Based on those grades, the Curator takes one of three actions: - **Promote:** increase the skill's priority so it surfaces more readily in relevant contexts - **Consolidate:** merge duplicate or overlapping skills into a single, refined version - **Archive:** move underused skills to `.archive/` where they stop executing but remain recoverable If a skill is critical to your workflow, pin protection keeps it safe: `hermes skills pin` prevents the Curator from archiving it. Community skills are automatically shielded from Curator modification as a security boundary. External code cannot be altered by your agent's internal optimization loop. * * * ## Hermes Skills at a Glance 40% Faster Tasks kanban-orchestrator users 7-Day Curator Cycle v0.12.0 (April 30, 2026) 6 Install Sources Official, skills.sh, GitHub, ClawHub, URL, well-known 750+ ATT&CK Skills Anthropic-Cybersecurity-Skills pack * * * FREE TEMPLATE Agentic AI Compliance Assessment Compliance checklist for autonomous agent deployments [Download Free →](https://techjacksolutions.com/downloads/free-agentic-ai-compliance-assess/) ## Full Rankings AllSecurityDevOpsProductivityDevelopmentResearchCommunication | #↑ | Name | Type | Category | Key Feature | | --- | --- | --- | --- | --- | | 1 | Anthropic-Cybersecurity-Skills | Community | Security | 750+ MITRE ATT&CK-mapped skills | | 2 | mission-control | Self-Gen | DevOps | Multi-instance dashboard monitoring | | 3 | kanban-orchestrator | Self-Gen | Productivity | Persistent kanban boards with auto-categorization | | 4 | memory-hygiene | Self-Gen | Productivity | Automated memory file cleanup on schedule | | 5 | hermes-skill-factory | Community | Development | Meta-skill: templates + quality scoring | | 6 | git-workflow | Self-Gen | DevOps | Context-aware commits + auto PR creation | | 7 | research-synthesizer | Self-Gen | Research | Multi-source research with citation chains | | 8 | docker-orchestrator | Self-Gen | DevOps | Container lifecycle + resource limits | | 9 | scheduled-reports | Self-Gen | Productivity | Daily/weekly/monthly activity summaries | | 10 | platform-bridge | Community | Communication | Cross-platform message routing | * * * ## Skill Deep Dives #1 Anthropic-Cybersecurity-Skills CommunitySecurity If you only install one skill from this list, make it this one. The pack ships 750+ individual skills mapped directly to the MITRE ATT&CK framework, covering tactics from initial access through exfiltration. SOC teams use it for automated threat analysis, incident triage, and detection rule generation. The skills are sourced from a security-verified GitHub repository and undergo community review before each release. The reason this beats everything else on the list is sheer coverage. You point Hermes at an indicator of compromise and the relevant ATT&CK skills activate automatically, with no manual selection. It turns a general-purpose agent into a security analyst that already knows the playbook. Still, 750+ skills is a lot of context for the agent to carry. Initial load time is noticeable on slower machines, and you will want to pin the subset you actually use rather than loading the entire pack every session. The pack also assumes you have some SOC familiarity. If you don't know what a T1059 technique is, the skill output won't mean much to you without additional context. **Install:**`hermes skills install github:anthropics/anthropic-cybersecurity-skills` Best ForYou run a SOC and want Hermes to draft detection rules from IOC feeds, or you do threat analysis and want ATT&CK mapping without manual lookup. #2 mission-control Self-GeneratedDevOps This is the one that surprised us. It's not a community skill. It's self-generated. Users running Hermes on a VPS with multiple platform gateways (Telegram, Discord, Slack) keep asking the agent the same thing: "what's running, is anything broken?" After five or more of those checks, Hermes creates mission-control on its own. The pattern is so universal that unrelated users end up with nearly identical versions of this skill. It surfaces active gateways, memory usage, skill execution stats, and error rates in a single dashboard view. Think of it as `htop` for your Hermes fleet. The fact that it's self-generated means it adapts to your specific instance layout rather than following a one-size-fits-all template. The downside: since every user's version is slightly different, there's no standardized output format. If you're feeding mission-control data into external monitoring (Grafana, Datadog), you'll need to normalize the output yourself. Best ForYou're running Hermes on a VPS with two or more gateways and you're tired of checking each one manually. #3 kanban-orchestrator Self-GeneratedProductivity This one solves the biggest pain point of using any AI coding agent: it forgets what you were working on. kanban-orchestrator creates persistent kanban boards backed by Hermes memory files, auto-categorizes tasks from conversation context, and tracks them across sessions. Users report 40% faster task completion with structured kanban workflows because the agent stops losing track of where things stand between sessions. The skill ranks above git-workflow and research-synthesizer because it addresses a more fundamental problem. You can work around bad commit messages; you can't work around an agent that doesn't remember your project has 12 open tasks. The catch: all the kanban data lives in Hermes memory files on a single machine. There's no cloud sync, no export to Jira or Linear, and if your memory files get corrupted the board is gone. For personal task tracking it's great; for team-wide project management you'll outgrow it quickly. Best ForYou're a solo developer juggling multiple projects and your agent keeps forgetting what you asked it to do yesterday. #4 memory-hygiene Self-GeneratedProductivity Automatically reviews and cleans MEMORY.md and USER.md files by removing stale entries, consolidating duplicates, and reorganizing content by topic. It runs as scheduled maintenance at a configurable interval. Without it, memory bloat gradually degrades agent performance as context windows fill with outdated information from weeks-old conversations. Anyone who has watched an agent get slower and less coherent over a month of heavy use knows why this matters. Fair warning: the skill is aggressive by default. It sometimes removes entries you actually wanted to keep because it scored them as stale. Pin important memory entries before running it, or adjust the staleness threshold if you find yourself re-teaching the agent things it used to know. Best ForYour Hermes instance has been running for weeks and the agent is getting slower or repeating itself. #5 hermes-skill-factory CommunityDevelopment A meta-skill: a skill for building better skills. It provides templates, a testing framework, and a quality scoring system that evaluates how well your custom skills follow Hermes conventions. If you're writing skills for a team, this standardizes output quality before distribution. The quality scoring is opinionated: it sometimes flags perfectly functional skills as low-quality because they don't follow its preferred markdown structure. You'll need to decide whether to conform or ignore the score. Still, the templates alone save enough boilerplate time to justify the install. Best ForYou're writing custom skills and want a template that saves you from guessing the expected file structure. #6 git-workflow Self-GeneratedDevOps Handles git branching, committing, and PR creation. Context-aware: it reads project structure and matches existing naming conventions instead of imposing its own. Commit messages come from diff analysis, so they reflect what actually changed rather than a generic "update files" placeholder. Useful, but not transformative. Most coding agents already handle basic git, and this skill mostly smooths out the rough edges rather than adding new capabilities. Best ForYou want Hermes to commit and push without you babysitting the message format every time. #7 research-synthesizer Self-GeneratedResearch Chains web search, content extraction, synthesis, and citation into a single workflow. Uses Firecrawl (via Nous Portal) or built-in web tools for scraping, then outputs structured research briefs with citation chains. Solid for turning a broad question into a sourced brief without opening dozens of tabs, but the citation accuracy depends entirely on the underlying scraping quality. Without a Firecrawl subscription, the fallback web tools produce noticeably rougher results. Best ForYou do research-heavy work and want the agent to handle source gathering so you can focus on analysis. #8 docker-orchestrator Self-GeneratedDevOps Manages Docker container lifecycle for the Docker terminal backend: creating, monitoring, and cleaning up execution containers with resource limits and networking. If you run Hermes in sandboxed mode (code execution inside disposable containers), this prevents resource exhaustion. If you don't use Docker backend, this skill does nothing for you. It's ranked #8 precisely because its audience is narrow, but for that audience it's essential. #9 scheduled-reports Self-GeneratedProductivity Generates periodic activity reports (daily, weekly, monthly) from Hermes logs, summarizing tasks completed, skills used, and errors hit. Output goes to markdown or through your messaging gateway. Answers the question "what did the agent actually do this week?" without digging through raw logs. Useful for accountability, though the reports tend to be verbose. Expect to skim rather than read them word for word. #10 platform-bridge CommunityCommunication Routes messages between Telegram, Discord, and Slack gateways while preserving threading and user attribution. Niche, but if your team is split across messaging platforms and you want Hermes to relay conversations, it works. The forwarding is one-directional per rule, so setting up bidirectional sync requires configuring two separate routing rules. It made the list because cross-platform teams keep asking for it, not because it's polished. * * * ## Installing Skills The `hermes skills install` command accepts six source types. Community skills are scanned on install and sandboxed from the Curator to prevent external code from modifying your agent's internal optimization. Official Packs Vetted skill packs from Nous Research. Pre-tested, security-reviewed, and supported. skills.sh Registry Community-maintained skill registry with search, versioning, and install-count rankings. GitHub Install directly from any public or private GitHub repository containing skill files. ClawHub OpenClaw marketplace with cross-compatible skills. Same skill format works across both frameworks. Direct URL Point to any hosted skill file by URL. No registry required. Direct download and install. Well-Known URL Auto-discovery via `/.well-known/hermes-skills.json` on any domain. * * * ## Nous Portal Premium Tools Beyond community and self-generated skills, Nous Research offers a subscription-based tool suite through the Nous Portal. These premium tools extend Hermes with capabilities that require infrastructure Nous maintains on your behalf: - **Firecrawl:** web scraping and crawling for structured data extraction - **FLUX 2 Pro:** image generation from text prompts - **Browser Use:** browser automation for interacting with web applications - **OpenAI TTS:** text-to-speech conversion for audio output The research-synthesizer skill (#7 on this list) can use Firecrawl for its web extraction stage, but falls back to Hermes built-in web tools if you don't have a Portal subscription. For a full walkthrough of Hermes architecture including these tools, see the [Hermes Agent Breakdown](https://techjacksolutions.com/ai-tools/hermes/hermes-breakdown/). * * * ## Building Your Own Skills You don't have to wait for the agent to auto-generate a skill or find one in the community. The skill file format is straightforward markdown with structured sections for name, description, trigger conditions, implementation steps, and usage examples. Store custom skills in `~/.hermes/skills/` and they register immediately. The hermes-skill-factory (#5 on this list) provides templates and quality scoring to help standardize your custom skills. For environment setup and first-time configuration, the [Hermes Setup Guide](https://techjacksolutions.com/ai-tools/hermes/hermes-setup-guide/) covers the full installation path including skill directory structure. **Tip:** Pin any skill you rely on with `hermes skills pin` to prevent the Curator from archiving it during evaluation cycles. This is especially important for custom skills with low usage frequency but high business value. * * * ## Video Resources Hermes Agent Skills Deep Dive Community Tutorial Walkthrough of skill creation, Curator configuration, and community skill installation. Building Custom Hermes Skills Nous Research Official guide covering skill file structure, trigger conditions, and the patch action for self-improvement. Hermes for Security Teams Security Conference Talk How SOC teams use the Anthropic-Cybersecurity-Skills pack for automated threat analysis with Hermes. Related Reading [Breakdown\\ Hermes Agent by Nous Research\\ \\ How it works, who uses it, and what to watch. Full architecture walkthrough with limitations.](https://techjacksolutions.com/ai-tools/hermes/hermes-breakdown/) [Guide\\ Hermes Setup Guide\\ \\ Install, configure, harden, and connect your first Hermes Agent instance.](https://techjacksolutions.com/ai-tools/hermes/hermes-setup-guide/) [Comparison\\ Hermes vs OpenClaw\\ \\ Two open-source agent frameworks compared across architecture, security, and skill ecosystems.](https://techjacksolutions.com/ai-tools/hermes/hermes-vs-openclaw/) Before You Use AI Your Privacy Hermes Agent runs locally or on your own VPS. Conversation data stays on your infrastructure unless you connect to external LLM APIs (Anthropic, OpenAI, OpenRouter), in which case prompts are sent to those providers' servers. Nous Portal premium tools (Firecrawl, FLUX 2 Pro, Browser Use, OpenAI TTS) route through Nous Research infrastructure. Review each provider's data processing terms before connecting. Enterprise agreements may offer different retention and processing commitments than free-tier accounts. Mental Health & AI Dependency AI agents are productivity tools, not replacements for human judgment or professional support. Over-reliance on automated decision-making can erode critical thinking skills and create single points of failure in your workflows. If you or someone you know is in crisis: - 988 Suicide & Crisis Lifeline: call or text **988** - SAMHSA Helpline: **1-800-662-4357** - Crisis Text Line: text **741741** AI systems can produce plausible-sounding but incorrect guidance. For mental health, medical, legal, or financial decisions, always consult a qualified professional. [NIST AI Risk Management Framework](https://www.nist.gov/itl/ai-risk-management-framework) Your Rights & Our Transparency Under GDPR (EU) and CCPA (California), you have the right to access, correct, and delete your personal data held by AI service providers. These rights apply to data processed by the LLM providers Hermes connects to, not to data stored locally on your own infrastructure. The EU AI Act classifies AI systems by risk tier and imposes transparency obligations on general-purpose AI providers. This article is editorially independent. Tech Jacks Solutions is not affiliated with Nous Research. Rankings reflect our editorial assessment of community adoption and utility. Where affiliate relationships exist, they are disclosed. [TJS Privacy Policy](https://techjacksolutions.com/privacy-policy/) [Terms of Service](https://techjacksolutions.com/terms-of-service/) [EU AI Act Compliance](https://techjacksolutions.com/eu-ai-act/) ### Go Deeper Resources from across Tech Jacks Solutions [Agent Frameworks Compared\\ \\ Side-by-side analysis of LangChain, CrewAI, AutoGen, and more](https://techjacksolutions.com/ai/agentic-ai/build/agent-frameworks-compared/) [Agent Threat Landscape\\ \\ Security risks specific to autonomous AI agents](https://techjacksolutions.com/ai/agentic-ai/secure/agent-threat-landscape/) [FREEAgentic AI Compliance Assessment\\ \\ Compliance checklist for autonomous agent deployments](https://techjacksolutions.com/downloads/free-agentic-ai-compliance-assess/) [PREMIUMPre-Deployment Safety Gate\\ \\ 27-point checklist before any AI tool goes live](https://techjacksolutions.com/downloads/pre-deployment-ai-safety-gate-tool/) [IAPP AIGP Certification\\ \\ The AI governance certification for privacy professionals](https://techjacksolutions.com/it-certifications/iapp/aigp/) Verified • May 2026 • Sources: Nous Research Documentation, GitHub, Community Reports Hermes Agent is a trademark of Nous Research, Inc. MITRE ATT&CK is a registered trademark of The MITRE Corporation. OpenClaw and ClawHub are trademarks of their respective owners. All other trademarks are the property of their respective holders. Tech Jacks Solutions is not affiliated with any of these organizations. **We value your privacy** We use cookies for analytics and advertising. [Privacy Policy](https://techjacksolutions.com/privacy-policy/) · [Cookie Policy](https://techjacksolutions.com/cookie-policy/) Show details **Strictly Necessary** Always active Essential for the site to function. Can't be turned off. **Analytics** Helps us understand which pages are visited and how users navigate. Aggregated and anonymous via Google Analytics. **Advertising** Measures campaign performance via Google Ads. May share data with Google for ad personalization. Accept AllAnalytics OnlyReject Non-Essential