What is yao-deepseek-crawler?

A crawler for collecting repeated answers from DeepSeek's web AI-search service and turning them into structured data and a GEO report.

Use it when you have DeepSeek questions, repeat counts, and a target person, company, or product, and need raw crawl JSON plus Markdown and HTML analysis.

It supports fresh-window sampling, target-versus-competitor recognition, resumable collection, and semantic review for formal reports.

yao-deepseek-crawler — Skill for Claude Code and Codex by yaojingang

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add yaojingang/yao-geo-skills --skill yao-deepseek-crawler

Clone the repo

git clone --depth 1 https://github.com/yaojingang/yao-geo-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-deepseek-crawler/github.svg)](https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-deepseek-crawler)

Your own site

<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-deepseek-crawler"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-deepseek-crawler/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-deepseek-crawler"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-deepseek-crawler.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 543 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00067	$0.00543
Opus 5	$0.00034	$0.00271
Sonnet 5	$0.00013	$0.00109
Haiku 4.5	$0.00007	$0.00054

Measured 13d ago against content hash 921e5c52f62f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

yao-deepseek-crawler scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 13d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/yao-deepseek-crawler/SKILL.md · 30 lines

How it starts

The opening of the file, as written. The whole thing — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Yao DeepSeek Crawler

Inputs

Standard inputs: keywords/questions, repeat count, target entity, entity type (人/person, 公司/company, 产品/product), browser profile, and optional output directory. Competitors must match the target type. Reports default to Simplified Chinese with an English summary toggle.

Workflow

Read references/user-setup-and-usage.md for install, prerequisites, and user-facing steps.
Read references/deepseek-crawl-workflow.md for crawler setup, preflight, delay, resume, and batch rules.
Read references/report-contract.md for JSON schema, metrics, target/competitor recognition, and report rules.
Run node scripts/preflight.mjs --profile <profile> before fresh crawling.
Stage 1: run scripts/deepseek_batch_crawl.mjs with questions, repeat, profile, target entity/type, --safe-random-delay, and output dir.
Stage 2: run scripts/analyze_deepseek_results.py on any crawl JSON with target entity/type, optional brands file, report output dir, and semantic review mode. Use --semantic-review auto by default; use --semantic-review required for formal delivery when AI review must pass.
Return the raw crawl JSON, structured Markdown, structured Excel workbook, HTML report, summary JSON, semantic-review cache when present, and failed logs. Reports include AI semantic labels for entity recognition, target-vs-best-3 radar, click-to-reveal bubbles, Chinese source names, clickable citations, title intent, compact treemap, and GEO actions.

Honest Boundaries

Do not use for generic website crawling, DeepSeek API chat, SEO copywriting, or one-off answer generation.
Reuses local DeepSeek web automation; does not bypass login, CAPTCHA, bot checks, or hidden data.
Probability metrics are repeated-sample estimates, not ground truth.
Inferred competitors are heuristic unless --semantic-review required passes. AI semantic review is an audit enhancement and never replaces hard-rule gates or answer-body evidence.
Review aliases, semantic labels, excluded candidates, and competitor tables before external use.
Preserve raw answers, reference titles, URLs, and logs.

Read the full file on GitHub · 30 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

13d ago First seen · 30 lines · 67 tokens per session scan A 921e5c52f62f

Subscribe to this mod's changes

yao-deepseek-crawler is a skill published in the GitHub repository yaojingang/yao-geo-skills (742 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 543 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Research ai-agent automation cli codex geoflow skills

pipefy-process-intelligence

Use this skill when the user wants to analyze an existing pipe for improvement opportunities — automation gaps, manual bottlenecks, missing AI agents, field conditions, or adjacent processes. Acts as a process analyst: investigates, diagnoses, and improves the pipe in progressive rounds — each round delivers visible…

pipefy/ai-toolkit · 65 tokens

yao-deepseek-crawler