메뉴
Guide for using the kagi-tools Hermes plugin — which tool for what, auth requirements, fallback patterns, and known quirks.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
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.
| name | kagi-tools-guide |
| description | Guide for using the kagi-tools Hermes plugin — which tool for what, auth requirements, fallback patterns, and known quirks. |
| version | 1 |
Guide for using the 14 tools provided by the kagi-tools Hermes plugin at ~/.hermes/plugins/kagi-tools/.
kagi_search is the primary search tool — use it instead of web_search when Kagi is the working backend. Supports region, time window, lens, verbatim, and order filters for narrowing results.kagi_quick for single-answer factual queries — returns a concise AI answer with cited references. Faster than kagi_assistant for "what is X" questions.kagi_ask_page to ask a question about a specific URL — gives you an AI summary of a page with citations. Use when you need to understand content on a single page without extracting it.kagi_assistant for open-ended research conversations — supports thread continuation (thread_id), model override, lens scoping, and web access toggles.kagi_translate to translate text — auto-detects source language, supports 100+ languages. Returns alternatives, word insights, and alignments.kagi_summarize to summarize a URL or text — defaults to subscriber mode (free with session token). Set subscriber=false with an engine (cecil/agnes/daphne/muriel) for paid API mode.kagi_news for AI-curated news — category slugs: world, usa, tech, science, business, etc. Use kagi_news_categories to list available categories first.kagi_smallweb for indie blog posts — independent personal blogs curated by Kagi.Deprecated tools (v0 API endpoints, no Kagi v1 equivalent yet):
kagi_fastgpt, kagi_enrich_web, kagi_enrich_news — return a clear error message. Use kagi_search or kagi_quick instead.| Auth | Tools | Status |
|---|---|---|
| None (public) | kagi_news, kagi_news_categories, kagi_smallweb | Always available |
KAGI_SESSION_TOKEN (env) | kagi_search, kagi_quick, kagi_ask_page, kagi_assistant, kagi_assistant_thread_list, kagi_assistant_thread_get, kagi_translate, kagi_summarize | Set via env |
KAGI_API_TOKEN (env) | kagi_fastgpt, kagi_enrich_web, kagi_enrich_news | Set, but endpoints are deprecated |
Bot auth header, not Bearer — the Rust binary at ~/.local/bin/kagi sends Authorization: Bot <token> on v0 API endpoints. Kagi's v1 API requires Authorization: Bearer <token>. The session-token path (cookie-based) still works, so kagi_search etc. function correctly./api/v0/fastgpt and /api/v0/enrich/* endpoints no longer accept new JWT-format API keys. Kagi's v1 API only offers /search and /extract.kagi auth check validates session token only. To test API token, use kagi fastgpt "test" (will fail with v0 deprecation).subscriber=true (default) to use the free web summarizer. The paid API mode requires KAGI_API_TOKEN and a summarization engine.When kagi_search returns no results:
kagi_quick for a synthesized answer from live resultskagi_assistant with web_access=true for a research conversationWhen a Kagi tool fails with auth errors:
KAGI_SESSION_TOKEN is set in envKAGI_API_TOKEN is set in ~/.hermes/.env; test with direct curl: curl -s https://kagi.com/api/v1/search -H "Authorization: Bearer $TOKEN" -H "Content-Type: application/json" -d '{"query":"test","limit":1}'