New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Kagi Assistant

by Microck in Microck/kagi-cli

Use Kagi Assistant for conversational answers, thread continuity, attachments, streaming, model selection, or custom assistants.

MITAuto-check passed

Install Kagi Assistant

skills CLI
$ npx skills add Microck/kagi-cli --skill kagi-assistant -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Microck/kagi-cli kagi-assistant --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Microck/kagi-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/kagi-assistant .claude/skills/kagi-assistant && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
kagi-assistant
GitHub stars
178
Token cost
~655 tokens
SKILL.md length
220 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Use Kagi Assistant for conversational answers, thread continuity, attachments, streaming, model selection, or custom assistants.

  • The task benefits from an account-backed conversation rather than direct search
  • SKILL.md covers Start a conversation, Continue a thread, Attach local context and Stream responses, plus 2 more sections
  • Needs KAGI_SESSION_TOKEN
  • Page extraction

What it does

Kagi Assistant is an agent skill from Microck/kagi-cli. Use Kagi Assistant for conversational answers, thread continuity, attachments, streaming, model selection, or custom assistants. Use when the task benefits from an account-backed conversation rather than direct search or page extraction.

Its SKILL.md is about 660 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: terminal CLI for Kagi that gives you command-line access to search, lenses, assistant, summarization, feeds, and paid API commands. The licence is MIT.

When your agent uses it

  • The task benefits from an account-backed conversation rather than direct search
  • Page extraction

Example prompts

  • “/kagi-assistant”

Requirements

  • A credential in KAGI_SESSION_TOKEN
  • Pre-approved tools (allowed-tools): Bash(kagi:*)

What it can do on your machine

Read from SKILL.md and the folder at commit 99ce2be. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(kagi:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • KAGI_SESSION_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Kagi Assistant loads about 655 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 220 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~63
When it runs · the whole SKILL.md, loaded when a task matches
~655

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Microck/kagi-cli at commit 99ce2be, republished under its MIT licence (© Microck). 220 words, ~655 tokens.

Download SKILL.mdSave it as .claude/skills/kagi-assistant/SKILL.md (or your agent's skills folder).
name
kagi-assistant
description
Use Kagi Assistant for conversational answers, thread continuity, attachments, streaming, model selection, or custom assistants. Use when the task benefits from an account-backed conversation rather than direct search or page extraction.
allowed-tools
Bash(kagi:*)

Kagi Assistant

Use Assistant for conversation mechanics and continuity. Use kagi-ai to choose when to spend AI allowance, and kagi-usage for direct search or page work.

Assistant commands require KAGI_SESSION_TOKEN.

Start a conversation

bash
kagi auth status
kagi assistant "draft a migration checklist" --format markdown
kagi assistant "compare these options" --format toon

State the deliverable, constraints, and audience in the prompt. Never rebuild the output structure in follow-up shell processing when the Assistant can produce it directly.

Continue a thread

bash
kagi assistant --thread-id THREAD_ID "add rollback steps"
kagi assistant thread list
kagi assistant thread get THREAD_ID
kagi assistant thread export THREAD_ID --format markdown

Reuse a thread only when its prior context still belongs to the task. Start a new thread when stale context could bias the answer.

Delete a thread only when the user asks for it:

bash
kagi assistant thread delete THREAD_ID

Attach local context

bash
kagi assistant \
  --attach ./notes.md \
  "turn these notes into a decision record" \
  --format markdown

Attach only files the task needs. Name the file's role in the prompt so the Assistant knows whether it is evidence, a template, or background.

Stream responses

Use human streaming for interactive terminal work. Use structured streaming when another program consumes events.

bash
kagi assistant --stream "explain the tradeoffs"
kagi assistant \
  --stream \
  --stream-output json \
  "produce a release checklist"

Never parse human streaming output as a machine contract.

Custom assistants

bash
kagi assistant custom list
kagi assistant custom get "Researcher"
kagi assistant custom create \
  "CLI Researcher" \
  --web-access \
  --model gpt-5-mini

Inspect an existing custom assistant before changing the workflow around it. Account configuration belongs in kagi-account-config.

Completion criteria

Assistant work is complete when:

  • you used the correct thread or a clean new one;
  • you supplied the required files and constraints;
  • the output format matches its consumer;
  • the final response answers the current prompt, not stale thread context; and
  • you deleted a thread only when the user asked for it.

© Microck, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/kagi-assistant of Microck/kagi-cli.

Open the folder on GitHubat commit 99ce2be

Compare with similar skills

Kagi Assistant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Kagi Assistant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Kagi Assistant this skillMicrock/kagi-cli178—~655Automated safety check: PassMIT
Assistant UI Streamingcompozy/compozy2.8k—~813Automated safety check: PassMIT
Continuetelegramdesktop/tdesktop33k2 repos~9.4kAutomated safety check: PassGPL-3.0
Continuous Learningaffaan-m/ECC275k—~1.1kAutomated safety check: PassMIT
Continuous Learningaffaan-m/ECC275k—~1.2kAutomated safety check: PassMIT
Conversation Archivegarrytan/gbrain31k—~5.6kAutomated safety check: PassMIT

Similar skills

  • Assistant UI Streaming

    compozy/compozy

    Guide for assistant-stream package and streaming protocols. An agent skill from compozy/compozy.

    2.8k GitHub stars~813 tokensUpdated today
    DevelopmentAuto-check passed

  • Continue

    telegramdesktop/tdesktop

    Continue autonomous Telegram Desktop development from the shared ai-tdesktop repository.

    33k GitHub starsUsed in 2 repos~9.4k tokens
    Productivity & AutomationAuto-check passed

  • Continuous Learning

    affaan-m/ECC

    [DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor.

    275k GitHub stars~1.1k tokensUpdated 3 days ago
    Auto-check passed

  • Continuous Learning

    affaan-m/ECC

    [OBSOLETO - usar continuous-learning-v2] Extractor de skill por hook Stop v1 heredado.

    275k GitHub stars~1.2k tokensUpdated 3 days ago
    Auto-check passed

  • Conversation Archive

    garrytan/gbrain

    Import AI-assistant chat exports (ChatGPT, Claude, Perplexity) and agent session transcripts into the brain as one dated page per conversation under conversations/, validate each page against the…

    31k GitHub stars~5.6k tokensUpdated today
    Productivity & AutomationAuto-check passed

  • Modeling Conversion Metrics

    PostHog/posthog

    Official

    Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project.

    40k GitHub stars~1.4k tokensUpdated today
    Data & AnalyticsAuto-check passed

More from Microck/kagi-cli

  • Kagi Account Config

    Microck/kagi-cli

    Configure Kagi CLI credentials, profiles, lenses, custom bangs, redirects, site preferences, and account-backed assistants.

    178 GitHub stars~695 tokensUpdated yesterday
    Auto-check passed

  • Kagi AI

    Microck/kagi-cli

    Use Kagi's paid AI allowance for reasoning, coding, research, file analysis, structured generation, or model comparison.

    178 GitHub stars~1k tokensUpdated yesterday
    Auto-check passed

  • Kagi Monitoring

    Microck/kagi-cli

    Automate repeated Kagi queries with batch search, watches, notifications, history, caching, and MCP.

    178 GitHub stars~690 tokensUpdated yesterday
    Auto-check passed

  • Kagi Usage

    Microck/kagi-cli

    Search the web, extract or summarize a page, translate it, or check the news with the kagi CLI instead of WebSearch or WebFetch.

    178 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

Questions about Kagi Assistant

What does Kagi Assistant do?

Use Kagi Assistant for conversational answers, thread continuity, attachments, streaming, model selection, or custom assistants. Kagi Assistant is an agent skill from Microck/kagi-cli. Use Kagi Assistant for conversational answers, thread continuity, attachments, streaming, model selection, or custom assistants.

When should I use Kagi Assistant?

Kagi Assistant fits situations like: the task benefits from an account-backed conversation rather than direct search; page extraction.

How do I install Kagi Assistant in Claude Code?

Run `npx skills add Microck/kagi-cli --skill kagi-assistant -a claude-code`. Or copy the skill folder (skills/kagi-assistant in Microck/kagi-cli) into .claude/skills/kagi-assistant in your project. Claude Code loads it when a task matches its description.

How do I install Kagi Assistant in Codex?

Run `npx skills add Microck/kagi-cli --skill kagi-assistant -a codex`. Or copy the skill folder (skills/kagi-assistant in Microck/kagi-cli) into .agents/skills/kagi-assistant in your project. Codex loads it when a task matches its description.

Can I use Kagi Assistant in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Microck/kagi-cli --skill kagi-assistant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/kagi-assistant, .gemini/skills/kagi-assistant, .github/skills/kagi-assistant and .opencode/skills/kagi-assistant in your project.

What does Kagi Assistant need to run?

Going by SKILL.md and its folder, Kagi Assistant needs credentials named KAGI_SESSION_TOKEN. Our summary lists: A credential in KAGI_SESSION_TOKEN. Its frontmatter pre-approves these tools: Bash(kagi:*).

Does Kagi Assistant access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Kagi Assistant safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Kagi Assistant use?

Kagi Assistant is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Kagi Assistant use?

About 655 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Kagi Assistant?

Skills that share tags, products or a category with Kagi Assistant: Assistant UI Streaming (compozy/compozy, 2.8k stars), Continue (telegramdesktop/tdesktop, 33k stars), Continuous Learning (affaan-m/ECC, 275k stars) and Continuous Learning (affaan-m/ECC, 275k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Kagi Assistant?

Microck (a GitHub user) maintains it in Microck/kagi-cli, which has 178 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.

Source: Microck/kagi-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.