hermes-skills

Run AI coding agents on disposable repo clones. The agent works on a clone — it can't touch your real repo. An optional container (Podman or Docker) provides build/test isolation. You review the diff and decide what (if anything) to apply.

Create Deezer playlists programmatically from any query — similar artists, genre mixes, festival lineups, mood-based collections. Four-tier data pipeline: Deezer public REST API + Last.fm scrobble data for discovery, GQL Pipe API for smart mixes and playlist creation, web search for subjective curation. Uses ARL cookie auth — no OAuth app required.

Generate compact AI-readable context maps from codebases — tools like codesight, repomix, agentic-context that pre-compute project structure to save tokens in AI coding sessions.

Research-focused query handling with multi-source synthesis, citations, and Obsidian persistence. Like a self-hosted Perplexity/Vane but CLI-native. Best for quick-to-medium lookups using Kagi. Use when the user asks factual questions, needs citations, or wants a direct answer — not a full research report (use deep-research) or social sentiment (use last30days). Triggers on: research, look into, what's the latest on, compare, explain, investigate.

Write articles, guides, blog posts, tutorials, newsletter issues, research reports, and deep research outputs in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, deep research on a topic, or a research report — especially when voice consistency, structure, and credibility matter. Triggers on: 'write an article', 'research report', 'deep research', 'long-form', 'blog post', 'guide', 'newsletter', 'white paper', 'research paper'.

Systematic research methodology for major consumer durables (appliances, HVAC, power tools, outdoor equipment) and smart garden/outdoor devices (bird feeder cameras, bird baths, smart outdoor gadgets). Emphasis on real reliability data, failure mode analysis, and head-to-head comparison. Use when the user asks to research, review, compare, or evaluate major purchases where longevity and repair risk matter, or when researching smart bird feeders, bird bath cameras, and similar connected outdoor devices. Triggers on: washer/dryer, refrigerator, dishwasher, HVAC, furnace, AC, generator, power tool, appliance reviews, appliance reliability, which [appliance] to buy, compare models, bird feeder camera, bird bath camera, smart garden devices.

Research and evaluate gray-market / cross-border products not officially sold in the user's region. Covers import smartphone and electronics purchasing: brand availability, carrier band compatibility checks, Global vs. regional ROM verification, reputable gray-market retailers, financing options, warranty realities, and pricing benchmarks. Also covers website legitimacy evaluation — vetting unfamiliar e-commerce sites for scam risk before purchase. Triggers on: import phone, buy [Xiaomi/Oppo/Vivo/Realme/Redmi] in US, gray market, international phone, will this phone work on [carrier], where to buy [product] not sold here, import electronics, is [website] legit, is [website] a scam, can I trust [website], open-ear earbuds alternatives, import earbuds, Huawei FreeClip, buy [product] outside [region].

Systematic multi-source methodology for comprehensive reports and complex, multi-faceted investigations. Use when the user asks for a deep dive, comprehensive analysis, literature-style synthesis, or formal research report. Not for quick factual answers (use answer-engine), recent social sentiment (use last30days), proprietary academic/financial datasets (use valyu), or explicit multi-model deliberation (use openrouter-fusion-research).

Read emails from Fastmail via IMAP and process them (e.g., newsletter digest). Handles HTML→text extraction for newsletters where plain text fallbacks are useless. Summarization via self-contained Python script calling Qwen 3.5 (NanoGPT) and delivery via AgentMail.

Install, configure, or explicitly operate the external Feynman research-agent CLI for paper reading, literature reviews, audits, replication, and experiments. Use only when the user names Feynman or asks to manage that tool; not for ordinary Hermes research.

Scrape top Hacker News stories, filter by topic or keyword, and return structured JSON data including titles, URLs, scores, and comment counts.

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

Guide for using the kagi-tools Hermes plugin — which tool for what, auth requirements, fallback patterns, and known quirks.

Find LLM tokens-per-second (TPS), latency, and throughput metrics. If direct API benchmarking is impossible, pivot to published third-party benchmarks and provide a manual fallback script.

Analyze external LLM system prompts — leaked, officially published, or competitor-released — to extract transferable patterns for improving your own persona/SOUL.md/skills. Triggers: user shares a leak link, new prompt leak surfaces, user asks 'what is [vendor] doing', 'analyze this prompt', 'compare system prompts', or a follow-up session wants to apply insights from a previous leak analysis.

Administer the dmv.community Mastodon instance: view and manage user reports, suspend/silence rule-breaking accounts, resolve reports, and escalate ambiguous cases to the instance owner. Use when checking or acting on Mastodon moderation reports.

Post to Mastodon via the dmv.community API. Supports text statuses, media attachments, polls, content warnings, scheduled posts, visibility control, and thread creation. Use when the user asks to post/toot to Mastodon.

Investigate whether a documented product feature is actually available for a specific user context (region, account type, plan tier, platform). Triggered when the user says things like: "can't find this feature", "docs say it exists but", "is this actually available", "when will this be available", "feature missing", "not showing up".

Automated GitHub repository discovery and monitoring - scraping, scoring, and integration patterns

Draft short-form social media posts (Mastodon, X, LinkedIn, Bluesky, Threads, etc.) for the user. Covers platform identification, char-limit verification, topic research, and character-count validation. Triggers on "write a post about X", "make a social post", "post about Y", "toot about W", "tweet about Z", "linkedin post about...".

Weekly stock recommendation digest using mixed signals - trending tickers, fundamentals, and price momentum. Scans for stocks under $20 and delivers recommendations via email.

When the user shares a TikTok URL, load this skill FIRST — before any tool calls. End-to-end workflow: scrape the URL, extract transcript, research claims, save to Obsidian, blog, and share to Mastodon. CRITICAL: Do NOT attempt nanogpt_tiktok_scraper, web_extract, or browser tools first — they all fail on TikTok URLs. The skill's CLI path is the only reliable scraper.

Ingest research outputs from other skills into the llm-wiki knowledge base. Handles answer-engine files, deep research reports, weekly blog research, and topic-monitor findings. Automatically cross-references existing wiki pages and updates navigation.

Author in-repo SKILL.md: frontmatter, validator, structure.

Compact the current session into a structured handoff document for a fresh agent or delegate_task subagent. Use when hitting context limits, switching focus, ending a work session, partitioning work across fresh contexts, or preparing a delegate_task goal that needs full session context. Triggers on: handoff, session handoff, context handoff, summarize for fresh agent, prepare for new session.

Execute plans via delegate_task subagents (2-stage review).

Teach the user a new skill or concept through a structured workspace with lessons, reference docs, and learning records. Use when the user asks to learn something new, wants lessons, says 'teach me', 'help me learn', 'I want to understand', or references ongoing learning (Spanish lessons, coding skills, exam prep). Creates a stateful workspace that persists across sessions. Triggers on: teach me, learn, lessons, study guide, learning workspace, education.

Search, filter, evaluate, and install community Hermes Agent skills, plugins, tools, and agents from the babylondreams.de community registry. Use when a user asks what's available in the community, wants to discover skills by topic/type, or mentions the babylondreams registry.

Use when looking for open-source contribution opportunities, finding repos where you can create visible value, or running a weekly contribution scan. Discovers, enriches, and analyzes GitHub repos for contribution fit.

Track flights using AviationStack API — real-time status, gate changes, delays, terminal info. Parse airline booking emails to auto-discover flights. Cron monitoring on travel days.

Log travel experiences during trips — save photos, places visited, meals, activities, and memories as structured daily entries in Obsidian. User shares updates via Discord/Telegram with text and photos; agent organizes everything into a rich travel journal.

Fetch top trending GitHub repositories for the past week, format a ranked list, and deliver via email. Designed for weekly cron jobs.

Publish files and folders to the web instantly. Static hosting for HTML sites, images, PDFs, and any file type. Use when asked to "publish this", "host this", "deploy this", "share this on the web", "make a website", "put this online", "upload to the web", "create a webpage", "share a link", "serve this site", or "generate a URL". Outputs a live, shareable URL at {slug}.here.now.

Build a weekly new releases digest for the user's favorite artists using Last.fm (top artists), MusicBrainz (release dates), and Deezer (album art, genres, popularity). Triggers on: new music digest, weekly music releases, music release report, album release radar.

Generate a twice-weekly tech news digest covering the last 48-72 hours across five categories, then email it via AgentMail. Uses multi-round web_search strategy and formatted HTML/text email output.

Production-grade frontend design guidance for AI agents. Embeds deep typography, color, layout, motion, and UX-writing intelligence into web app building sessions. Adapted from Impeccable (pbakaus/impeccable) for Hermes Agent.

Transform weak resume bullets into achievement-focused statements with metrics and impact

Track different resume versions, maintain master resume, manage tailored versions

Orchestrates the complete resume and job application workflow using specialized resume skills. Routes to the right skill based on user intent and chains multiple skills together for comprehensive career support.

Optimize resumes for software engineering, PM, and technical roles