菜单
这个仓库中的 skills
SkillsMP 已收集 lukemcqueen/hermes-cortex 中的 311 个 Skill。打开任一 Skill 可查看来源和详情。
lukemcqueen/hermes-cortex已展示 40 / 311 个已收集 Skill。
Analyzes campaign performance with multi-touch attribution, funnel conversion analysis, and ROI calculation for marketing optimization. Use when analyzing marketing campaigns, ad performance, attribution models, conversion rates, or calculating marketing ROI,…
原文语言：英语
Deprecated redirect skill that routes legacy 'content creator' requests to the correct specialist. Use when a user invokes 'content creator', asks to write a blog post, article, guide, or brand voice analysis (routes to content-production), or asks to plan…
原文语言：英语
Makes AI-generated content sound genuinely human — not just cleaned up, but alive. Use when content feels robotic, uses too many AI clichés, lacks personality, or reads like it was written by committee. Triggers: 'this sounds like AI', 'make it more human',…
原文语言：英语
Full content production pipeline — takes a topic from blank page to published-ready piece. Use when you need to execute content: write a blog post, article, or guide end-to-end. Triggers: 'write a post about', 'draft an article', 'create content for', 'help…
原文语言：英语
When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," or "content…
原文语言：英语
Consolidate, dedupe, and prune the skill library — merge overlapping skills into one (absorbed_into), delete truly dead skills, and keep the manifest honest. Use when the doctor flags skill drift, two skills overlap, or a lifecycle run surfaces consolidation…
原文语言：英语
Vet third-party code before it enters the repo or runs on a host — upstream patches, vendored scripts, installer snippets, peer-submitted cron scripts. Use when integrating external code of any kind.
原文语言：英语
When the user wants to plan a product launch, feature announcement, or release strategy. Also use when the user mentions 'launch,' 'Product Hunt,' 'feature release,' 'announcement,' 'go-to-market,' 'beta launch,' 'early access,' 'waitlist,' 'product update,'…
原文语言：英语
When the user wants help with paid advertising campaigns on Google Ads, Meta (Facebook/Instagram), LinkedIn, Twitter/X, or other ad platforms. Also use when the user mentions 'PPC,' 'paid media,' 'ad copy,' 'ad creative,' 'ROAS,' 'CPA,' 'ad campaign,'…
原文语言：英语
Shopify Admin & Storefront GraphQL APIs via curl. Products, orders, customers, inventory, metafields.
原文语言：英语
Monitor and analyze brand mentions, sentiment, share of voice, and competitive positioning across web/social/review platforms.
原文语言：英语
Design and run recurring automated reports: define cadence, metrics, sources, and delivery; wire to cron; verify delivery.
原文语言：英语
Add, fix, or optimize schema markup and structured data. Use when the user mentions schema markup, structured data, JSON-LD, rich snippets, schema.org, FAQ schema, product schema, review schema, or breadcrumb schema.
原文语言：英语
Use when the user wants to audit, review, or diagnose SEO issues on a site: rankings, technical SEO, on-page, backlinks, Core Web Vitals, site speed.
原文语言：英语
Social media campaign analysis and performance tracking. Calculates engagement rates, ROI, and benchmarks across platforms. Use when analyzing social media performance, calculating engagement rate, measuring campaign ROI, comparing platform metrics, or…
原文语言：英语
Use when planning video content strategy, writing video scripts, optimizing YouTube channels, building short-form video pipelines (Reels, TikTok, Shorts), or repurposing long-form content into video. Triggers: 'start a YouTube channel', 'video content…
原文语言：英语
X/Twitter growth engine for building audience, crafting viral content, and analyzing engagement. Use when the user wants to grow on X/Twitter, write tweets or threads, analyze their X profile, research competitors on X, plan a posting strategy, or optimize…
原文语言：英语
Design, author, and iterate an agent's identity/persona — the SOUL.md that defines who the agent is, what it values, and how it operates. Trigger: asked to 'develop a personality', 'create a persona', 'write a SOUL.md', 'decide who you want to be', or when…
原文语言：英语
Complete auto-remediation ecosystem setup, configuration, and maintenance for production systems. Covers deployment of all auto-remediation components, integration with existing server administration workflows, monitoring, troubleshooting, and production…
原文语言：英语
Set up, configure, and troubleshoot the auto-remediation system. Covers passwordless sudo prerequisites, verification scripts, troubleshooting workflows, and best practices for deploying the auto-remediation pipeline across different environments.
原文语言：英语
ORCHESTRATORS ONLY — message the orchestrator via the bus MCP client (inbox_send). Workers use contact-orchestrator.sh (HTTP).
原文语言：英语
Agent Bus polling setup — MCP tools, cron, verification.
原文语言：英语
Protocol for non-orchestrator agents to request cron job creation, updates, or removal via the agent inbox. Only orchestrators have the cronjob MCP tool in all contexts; other agents route requests to the orchestrator inbox (inbox_orchestrator) using this…
原文语言：英语
Fleet-level agent management for Hermes Cortex — agent registry, fleet ready score, fleet-audit CLI, adding/removing agents, and multi-slice fleet upgrades (S1-S4 pattern). Covers the 5 fleet concerns (identity, topology, choreography, economics, sovereign…
原文语言：英语
Diagnose, configure, and maintain Hermes messaging gateway platforms (Telegram, Discord, WhatsApp, etc.). Covers connectivity troubleshooting, secret/token setup, gateway state inspection, and common failure patterns.
原文语言：英语
Use when cleaning ~/.hermes or ~/.hermes-cortex. Verify.
原文语言：英语
Auto-remediate hermes-cortex issues reported by peer agents via the Agent Bus. Scans pending remediation markers every 10 minutes, reads the original message, applies the fix, and marks the request as done.
原文语言：英语
Transform user corrections and system warnings into permanent guardrails. Covers zero-ask discipline, doctor-warnings-as-required, session-end self-audit, dogfooding, and the full correction-to-guardrail feedback loop.
原文语言：英语
Use when a credential leaks — verify live, scrub, rotate.
原文语言：英语
Audit documentation for stale file paths, broken cross-references, and correctness gaps. Systematic approach for identifying, verifying, and reporting stale references in docs directories.
原文语言：英语
Trace remediation sensor reports to their source, cross-reference live state, and distinguish transient from chronic cron failures.
原文语言：英语
Use when collectors can't send. Diagnoses bus, paths, crons.
原文语言：英语
Multi-faceted system scan to discover work, issues, and improvement opportunities when the user gives an open-ended request like "find work" or "look for things that need doing." Runs doctor, cron health, git status, system health, and governance checks in…
原文语言：英语
Five-wave session orchestration: Discovery → Impl-Core → Impl-Polish → Quality → Finalization. Quality gates between each wave enforce handoff schemas, adversarial verification, and governance ledger entry.
原文语言：英语
Mandatory verification checklist that every agent MUST load before closing a governance cycle (end_change). Referenced by AGENTS.md as a pre-close requirement.
原文语言：英语
Use when hardening orchestrator identity or unlock tokens.
原文语言：英语
Debugging data transformation bugs in legacy Rails apps — tracing heuristic text-splitting, internationalisation helpers, and CPLEX/CSV import pipelines.
原文语言：英语
Break features into user-visible, testable stories using vertical slicing patterns.
原文语言：英语
Host modded Minecraft servers (CurseForge, Modrinth).
原文语言：英语
Play Pokemon via headless emulator + RAM reads.
原文语言：英语