Agent skill

Local Search Fallback

by taxueseek in taxueseek/argo

Zero-cost fallback for the argo search skill, wrapping 29 local engines for web, news, academic, code and reference queries when paid API quota should be saved.

MITAuto-check passedProductivity & Automation

SKILL.md written in Chinese; this summary is our English description.

Install Local Search Fallback

skills CLI
$ npx skills add taxueseek/argo --skill local-search -a claude-code

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

GitHub CLI
$ gh skill install taxueseek/argo local-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).

Manual copy
$ git clone --depth 1 https://github.com/taxueseek/argo.git skills-src && mkdir -p .claude/skills && cp -r skills-src/sub-skills/local-search .claude/skills/local-search && 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
local-search
GitHub stars
188
Token cost
~949 tokens
SKILL.md length
250 words
Files
9
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Zero-cost fallback for the argo search skill, wrapping 29 local engines for web, news, academic, code and reference queries when paid API quota should be saved.

  • Searching Chinese-language pages, news and reference sites without paid APIs
  • Runs Python scripts from its folder; calls python3
  • Falling back to local scraping when SearXNG is down
  • Running argo in fast or budget mode to save API quota

What it does

This is a sub-skill of argo, not a standalone one: it does not react to trigger words and is called only when argo runs with the --local-first option. It wraps 29 search engines that read public pages, HTML, RSS, JSON or the ddgs command-line tool, 27 of them enabled by default, so no paid API keys are spent.

It is preferred in fast and budget modes and takes over when SearXNG is unavailable. The engines cover general web search (Bing, Yandex, DuckDuckGo, Brave, Yahoo), Chinese sites (Baidu, Sogou, 360, Jisilu), news feeds, academic sources (arXiv, PubMed, Crossref, Semantic Scholar), code sources (GitHub, StackOverflow, GitLab, npm) and reference sites (Wikipedia, Wiktionary, Wikiquote). IMDb and Goodreads are off by default. Output follows the main skill's schema with results, engines_used, errors and elapsed_ms, so it feeds straight into evidence collection.

When your agent uses it

  • Searching Chinese-language pages, news and reference sites without paid APIs
  • Falling back to local scraping when SearXNG is down
  • Running argo in fast or budget mode to save API quota

Example prompts

  • “Use argo with local-first to search Baidu and Sogou for recent news on lithium batteries.”
  • “Search arXiv and Semantic Scholar for papers on retrieval ranking, local engines only.”
  • “SearXNG is down, so run this query on the local engines instead.”

Requirements

  • The parent argo search skill
  • The ddgs command-line tool
  • Python to run the bundled scripts

What it can do on your machine

Read from SKILL.md and the folder at commit a6657b0. 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 script files (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    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

Local Search Fallback loads about 949 tokens when it runs. Until then it costs about 27 tokens; SKILL.md has 250 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~27
When it runs · the whole SKILL.md, loaded when a task matches
~949

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 taxueseek/argo at commit a6657b0, republished under its MIT licence (© taxueseek). 250 words, ~949 tokens.

Download SKILL.mdSave it as .claude/skills/local-search/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.
name
local-search
description
argo 的本地/零成本兜底子技能。封装基于公开页面/HTML/RSS/JSON/CLI 的 29 个本地搜索引擎,不单独响应触发词,仅由 argo 通过 --local-first 调用。
parent
argo
version
1.1.0

Local Search 子技能

Local Search 是 argo 的「零成本兜底适配器」,用于:

  • 在 --mode fast / --mode budget 下优先使用本地抓取引擎,避免消耗付费 API 配额。
  • 当 SearXNG 不可用时,回退到本地 HTML/JSON 解析。
  • 对中文网页、新闻、代码问答、学术、参考百科等垂直域提供补充结果。
设计原则
  • 不单独响应触发词:仅作为 argo 的子能力,由 --local-first 调用。
  • 输出与主 skill 同 schema:results[] / engines_used / errors / elapsed_ms,可直接进 evidence 与 RRF。
  • local_X 与主清单的 X 是别名,不是备份:local_arxiv/local_crossref/local_semantic_scholar/local_github/local_npm/local_wikipedia/local_stackoverflow/local_google_news 与主清单同名项打同一个上游端点(主清单走官方 API、这里走免密钥直取),不存在「API 挂了抓取版兜底」。同上游同格式由 tests/test_local_search_registry.py 锁定。
本地引擎列表(29 个,27 个默认启用)
unified 名称类型默认启用类别说明
local_bingcli(ddgs)✅web_generalBing 网页结果(ddgs -b bing + JSON)
local_yandexcli(ddgs)✅web_general/japaneseYandex 搜索(ddgs -b yandex)
local_duckduckgocli(ddgs)✅web_generalDuckDuckGo(ddgs 默认)
local_bravecli(ddgs)✅web_generalBrave 搜索(ddgs -b brave,实测稳定)
local_yahoocli(ddgs)✅web_generalYahoo 搜索(ddgs -b yahoo,实测稳定)
local_baiduhtml✅chinese百度搜索
local_sogouhtml✅chinese搜狗搜索
local_360html✅chinese360 搜索
local_jisiluhtml✅finance/chinese集思录
local_ddgs_newscli(ddgs)✅newsddgs news 默认后端(带日期)
local_bing_newsrss✅newsBing 新闻 RSS
local_google_newsrss✅newsGoogle News RSS
local_duckduckgo_newscli(ddgs)✅newsddgs news 备用后端
local_ddgs_imagescli(ddgs)✅imagesddgs images(bing TLS 偶发,已自动重试)
local_ddgs_videoscli(ddgs)✅videosddgs videos
local_arxivxml✅academicarXiv API
local_pubmedjson✅academicPubMed/EUtils
local_crossrefjson✅academicCrossref API
local_semantic_scholarjson✅academicSemantic Scholar API
local_githubjson✅codeGitHub Search API
local_stackoverflowjson✅codeStackOverflow 问题
local_gitlabjson✅codeGitLab API
local_npmjson✅codeNPM Registry
local_wikipediajson✅referenceMediaWiki API(ddgs wikipedia backend 结果过少)
local_wiktionaryjson✅referenceWiktionary API
local_wikiquotejson✅referenceWikiquote API
local_imdbhtml❌verticalIMDb 搜索
local_goodreadshtml❌verticalGoodreads 搜索
local_openstreetmapjson✅verticalNominatim API

CLI 引擎(ddgs 9.14.4)统一走 -o json 结构化输出 + 失败自动重试 1 次; 错误信号(DDGSException/ConnectError 等)在 rc=0 时也会被识别并上报,不静默吞错。

调用方式
bash
# 直接调用子技能(单引擎)
python3 sub-skills/local-search/local_search_adapter.py "query" --engine local_bing

# 批量调用多个本地引擎
python3 sub-skills/local-search/local_search_adapter.py "query" \
  --engine local_bing,local_baidu,local_duckduckgo

# 由 argo 调用
python3 scripts/search.py "query" --local-first --mode fast
两条不显然的约定
  • engine_registry.py 是本地引擎注册中心(唯一真源,读本目录 config.yaml 与 parse_maps.yaml)。
  • local_health_check.py 用 local_ 前缀,避免与 scripts/health_check.py 同名冲突。
输出 schema

与 argo 主 skill 一致:

json
{
  "query": "string",
  "engine": "local_search",
  "engines": ["local_bing", "local_baidu"],
  "engines_combo": ["local_bing", "local_baidu"],
  "cached": false,
  "cache_level": null,
  "domain": null,
  "elapsed_ms": 1234,
  "tfidf_scores": [],
  "results": [
    {"title": "...", "url": "...", "snippet": "...", "score": 0.8, "source": "local_bing"}
  ],
  "count": 10,
  "engines_used": ["local_bing", "local_baidu"],
  "errors": []
}

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

Files

SKILL.md and 8 other files in sub-skills/local-search of taxueseek/argo.

  • SKILL.md
  • bm25.py
  • config.yaml
  • engine_registry.py
  • local_health_check.py
  • local_search_adapter.py
  • parse_maps.yaml
  • search_v3.py
  • smart_router.py

Open the folder on GitHubat commit a6657b0

Compare with similar skills

Local Search Fallback 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.

Local Search Fallback compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Local Search Fallback this skilltaxueseek/argo188—~949Automated safety check: PassMIT
Rival Search MCPdamionrashford/RivalSearchMCP132—~796Automated safety check: PassMIT
Literature ReviewK-Dense-AI/scientific-agent-skills48k1 repos~3.2kAutomated safety check: NotesMIT
PaperSeek Literature SearchMingfengHong/paperseek0—~1.6kAutomated safety check: PassApache-2.0
Academic Research HubLeoYeAI/openclaw-master-skills2.2k1 repos~4.8kAutomated safety check: PassProprietary
Literature Searchgaasher/Agent-Loop-Skills174—~1.5kAutomated safety check: PassMIT

Similar skills

  • Rival Search MCP

    damionrashford/RivalSearchMCP

    Deterministic deep research via RivalSearchMCP. An agent skill from damionrashford/RivalSearchMCP.

    132 GitHub stars~796 tokensUpdated yesterday
    Research & ScienceAuto-check passed
  • Literature Review

    K-Dense-AI/scientific-agent-skills

    Runs systematic, scoping or narrative literature reviews across PubMed, arXiv, bioRxiv and Semantic Scholar, with citation checks and Markdown or PDF output.

    48k GitHub starsUsed in 1 repo~3.2k tokens
    Research & ScienceAuto-check: notes
  • PaperSeek Literature Search

    MingfengHong/paperseek

    Routes literature searches through the PaperSeek launcher, picks suitable scholarly sources, parses JSON output and keeps API keys out of the chat.

    0 GitHub stars~1.6k tokensUpdated 2 days ago
    Research & ScienceAuto-check passed
  • Academic Research Hub

    LeoYeAI/openclaw-master-skills

    A skill your agent uses when users need to search academic papers, download research documents, extract citations, or gather scholarly information.

    2.2k GitHub starsUsed in 1 repo~4.8k tokens
    Research & ScienceAuto-check passed
  • Literature Search

    gaasher/Agent-Loop-Skills

    A skill your agent uses when a loop needs scholarly literature — paper discovery, novelty checks, full-text snippet search, citation-graph traversal, single-paper reads, or experimental-result…

    174 GitHub stars~1.5k tokensUpdated 3 mo ago
    Research & ScienceAuto-check passed
  • Insane Search

    fivetaku/gptaku-plugins-codex

    Adaptive access for blocked websites — tries every method until one works.

    128 GitHub stars~5.6k tokensUpdated 1 mo ago
    Research & ScienceAuto-check passed

More from taxueseek/argo

  • Ego Browser Search

    taxueseek/argo

    Searches and fetches pages through a real logged-in Chromium session when ordinary API or HTML retrieval cannot get past login walls, scripts or anti-bot checks.

    188 GitHub stars~2.1k tokensUpdated 5 days ago
    Auto-check passed
  • Unified web search, page fetching and evidence checking across hundreds of sources, with result verification, a research-dossier mode and vertical search engines.

    188 GitHub stars~1.2k tokensUpdated 5 days ago
    Auto-check passed
  • Searches local files and code through one script, seek.py, that picks between rg, fd and macOS Spotlight and works in three layers: locate, context, close reading.

    188 GitHub stars~1.1k tokensUpdated 5 days ago
    Auto-check passed
  • Runs web-page JavaScript without a browser, in a V8 sandbox with a browser-environment shim, for scripts that only probe the environment and compute a result.

    188 GitHub stars~400 tokensUpdated 5 days ago
    Auto-check passed

Questions about Local Search Fallback

What does Local Search Fallback do?

Zero-cost fallback for the argo search skill, wrapping 29 local engines for web, news, academic, code and reference queries when paid API quota should be saved. This is a sub-skill of argo, not a standalone one: it does not react to trigger words and is called only when argo runs with the --local-first option. It wraps 29 search engines that read public pages, HTML, RSS, JSON or the ddgs command-line tool, 27 of them enabled by default, so no paid API keys are spent.

When should I use Local Search Fallback?

Local Search Fallback fits situations like: searching Chinese-language pages, news and reference sites without paid APIs; falling back to local scraping when SearXNG is down; running argo in fast or budget mode to save API quota.

How do I install Local Search Fallback in Claude Code?

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

How do I install Local Search Fallback in Codex?

Run `npx skills add taxueseek/argo --skill local-search -a codex`. Or copy the skill folder (sub-skills/local-search in taxueseek/argo) into .agents/skills/local-search in your project. Codex loads it when a task matches its description.

Can I use Local Search Fallback 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 taxueseek/argo --skill local-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/local-search, .gemini/skills/local-search, .github/skills/local-search and .opencode/skills/local-search in your project.

What does Local Search Fallback need to run?

Going by SKILL.md and its folder, Local Search Fallback needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: The parent argo search skill; The ddgs command-line tool; Python to run the bundled scripts.

Does Local Search Fallback 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 Local Search Fallback 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 Local Search Fallback use?

Local Search Fallback 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 Local Search Fallback use?

About 949 tokens (SKILL.md is roughly 3.8k 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 Local Search Fallback?

Skills that share tags, products or a category with Local Search Fallback: Rival Search MCP (damionrashford/RivalSearchMCP, 132 stars), Literature Review (K-Dense-AI/scientific-agent-skills, 48k stars), PaperSeek Literature Search (MingfengHong/paperseek, 0 stars) and Academic Research Hub (LeoYeAI/openclaw-master-skills, 2.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Local Search Fallback?

taxueseek (a GitHub user) maintains it in taxueseek/argo, which has 188 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on October 6, 2026.

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