Agent skill

Agentic Search

by benchen4395 in benchen4395/alpha_agentic_search

当用户提问需要联网检索(最新新闻、技术资料、人物事件等)或明确说"搜一下/查一下/帮我找…"时触发。本技能会自动改写 query 并通过 DuckDuckGo 检索,再用 DeepSeek 综合回答,引用来源序号。

No licenceAuto-check passed

Install Agentic Search

skills CLI
$ npx skills add benchen4395/alpha_agentic_search --skill agentic-search -a claude-code

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

GitHub CLI
$ gh skill install benchen4395/alpha_agentic_search agentic-search --agent claude-code

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

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

Facts

Skill name
agentic-search
GitHub stars
486
Token cost
~140 tokens
SKILL.md length
43 words
Files
120 (incl. scripts)
Skills in repo
1
Repo updated
First seen
Licence
None found

At a glance

当用户提问需要联网检索(最新新闻、技术资料、人物事件等)或明确说"搜一下/查一下/帮我找…"时触发。本技能会自动改写 query 并通过 DuckDuckGo 检索,再用 DeepSeek 综合回答,引用来源序号。

  • Works in 2 steps: 调用 python scripts/search.py "<原始 query>" → 解析返回 JSON,把 answer 给用户,并附上 results 中的…
  • SKILL.md covers 触发条件, 不触发, 执行步骤 and 示例
  • Runs Python scripts from its folder; calls python

What it does

Agentic Search is an agent skill from benchen4395/alpha_agentic_search. 当用户提问需要联网检索(最新新闻、技术资料、人物事件等)或明确说"搜一下/查一下/帮我找…"时触发。本技能会自动改写 query 并通过 DuckDuckGo 检索,再用 DeepSeek 综合回答,引用来源序号。

Its SKILL.md is about 140 tokens, which your agent loads only when the skill is triggered. The skill folder holds 125 other files, including scripts (for example `README.md`, `README_en.md` and `data/README.md`).

It works with DeepSeek. The repository describes itself as: Alpha Agentic Search — 分层记忆 RAG 检索问答系统.

Example prompts

  • “搜一下/查一下/帮我找…”
  • “/agentic-search”

Requirements

  • Python 3

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. 调用 python scripts/search.py "<原始 query>"
  2. 解析返回 JSON,把 answer 给用户,并附上 results 中的 URL 作为引用

What it can do on your machine

Read from SKILL.md and the folder at commit 964492b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • python

    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 no API keys, tokens, secrets or passwords.

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

Context cost

Agentic Search loads about 140 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 43 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~140

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); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 43 words (~140 tokens).

name
agentic-search

Read the full SKILL.md on GitHub

Files

SKILL.md and 119 other files (scripts) in the repository root of benchen4395/alpha_agentic_search.

  • SKILL.md
  • .gitignore
  • README.md
  • README_en.md
  • data/README.md
  • data/qa_cache/_embeddings/cache.db
  • data/qa_cache/_meta/cache.db
  • data/qa_cache/cache.db
  • data/search_cache/cache.db
  • evals/README.md
  • evals/__init__.py
  • evals/compare_vs_commit.py
  • evals/datasets.py
  • evals/run_multihop_eval.py
  • evals/run_parallel_eval.py
  • … and 105 more

Open the folder on GitHubat commit 964492b

Compare with similar skills

Agentic Search 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.

Agentic Search compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agentic Search this skillbenchen4395/alpha_agentic_search486—~140Automated safety check: PassNone
ModLens Image Vision Bridgeliustack/modlens4.2k1 repos~1.3kAutomated safety check: NotesMIT
Vision SkillsAnionex/agent-vision-toolkit1.2k1 repos~4kAutomated safety check: PassMIT
Distilly Person Profile Buildertitanwings/distilly25k—~15kAutomated safety check: NotesMIT
Evals Contextzgsm-ai/costrict4.4k1 repos~1.9kAutomated safety check: PassApache-2.0
J SpaceTiger3807861189/J-Space-Cognition-Suite3k—~3kAutomated safety check: PassApache-2.0

Similar skills

  • Gives text-only models sight by running the modlens CLI on an image path or URL and returning structured JSON evidence with transcribed text, layout and semantics.

    4.2k GitHub starsUsed in 1 repo~1.3k tokens
    AI & LLM EngineeringAuto-check: notes
  • Vision Skills

    Anionex/agent-vision-toolkit

    Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and…

    1.2k GitHub starsUsed in 1 repo~4k tokens
    Productivity & AutomationAuto-check passed
  • Distills source material about a colleague, a relationship or a celebrity into reusable Person Profiles that an agent can later work from, in English or Chinese.

    25k GitHub stars~15k tokensUpdated 16 days ago
    Agent WorkflowsAuto-check: notes
  • Evals Context

    zgsm-ai/costrict

    Provides context about the CoStrict evals system structure in this monorepo.

    4.4k GitHub starsUsed in 1 repo~1.9k tokens
    AI & LLM EngineeringAuto-check passed
  • J Space

    Tiger3807861189/J-Space-Cognition-Suite

    Operate a selective workspace for complex reasoning, long tasks, repository engineering, coordinated agents, and authorized security analysis.

    3k GitHub stars~3k tokensUpdated 25 days ago
    Frontend & DesignAuto-check passed
  • Modsearch

    liustack/modsearch

    Plug-in web search, X (Twitter) search, and page fetch for models without native web access.

    603 GitHub starsUsed in 1 repo~2.6k tokens
    Productivity & AutomationAuto-check: notes

Works with

Questions about Agentic Search

What does Agentic Search do?

当用户提问需要联网检索(最新新闻、技术资料、人物事件等)或明确说"搜一下/查一下/帮我找…"时触发。本技能会自动改写 query 并通过 DuckDuckGo 检索,再用 DeepSeek 综合回答,引用来源序号。. Agentic Search is an agent skill from benchen4395/alpha_agentic_search.

How do I install Agentic Search in Claude Code?

Run `npx skills add benchen4395/alpha_agentic_search --skill agentic-search -a claude-code`. Or copy the skill folder (the benchen4395/alpha_agentic_search repository) into .claude/skills/agentic-search in your project. Claude Code loads it when a task matches its description.

How do I install Agentic Search in Codex?

Run `npx skills add benchen4395/alpha_agentic_search --skill agentic-search -a codex`. Or copy the skill folder (the benchen4395/alpha_agentic_search repository) into .agents/skills/agentic-search in your project. Codex loads it when a task matches its description.

Can I use Agentic Search 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 benchen4395/alpha_agentic_search --skill agentic-search -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agentic-search, .gemini/skills/agentic-search, .github/skills/agentic-search and .opencode/skills/agentic-search in your project.

What does Agentic Search need to run?

Going by SKILL.md and its folder, Agentic Search needs Python for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3.

Does Agentic Search 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 Agentic Search 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Agentic Search use?

No licence was found for Agentic Search or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Agentic Search use?

About 140 tokens (SKILL.md is roughly 560 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 Agentic Search?

Skills that share tags, products or a category with Agentic Search: ModLens Image Vision Bridge (liustack/modlens, 4.2k stars), Vision Skills (Anionex/agent-vision-toolkit, 1.2k stars), Distilly Person Profile Builder (titanwings/distilly, 25k stars) and Evals Context (zgsm-ai/costrict, 4.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agentic Search?

benchen4395 (a GitHub user) maintains it in benchen4395/alpha_agentic_search, which has 486 GitHub stars. The repository was last updated on September 15, 2026.

Source: benchen4395/alpha_agentic_search on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.