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

Policy Crawl Pipeline

by Serein-81 in Serein-81/financial_rag

Guides a policy notification agent through crawling government policy sources, saving them locally, matching them to enterprise profiles and generating notifications.

No licenceAuto-check: notesLegal & Compliance

Install Policy Crawl Pipeline

skills CLI
$ npx skills add Serein-81/financial_rag --skill policy-crawl -a claude-code

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

GitHub CLI
$ gh skill install Serein-81/financial_rag policy-crawl --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/Serein-81/financial_rag.git skills-src && mkdir -p .claude/skills && cp -r skills-src/rag_backend/skills/public/policy-crawl .claude/skills/policy-crawl && 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
policy-crawl
GitHub stars
148
Token cost
~1.4k tokens
SKILL.md length
404 words
Files
2 (incl. scripts)
Skills in repo
7
Repo updated
First seen
Licence
None found

At a glance

Guides a policy notification agent through crawling government policy sources, saving them locally, matching them to enterprise profiles and generating notifications.

  • Works in 5 steps: Confirm Crawl Parameters with User → Trigger the Crawl → Cross-Reference Results → …
  • Collecting the latest tax policies from government websites
  • SKILL.md covers Overview, Prerequisites, Workflow and Error Handling, plus 1 more section
  • Runs Python scripts from its folder; calls curl and python

What it does

The skill walks an agent through the policy lifecycle of a financial RAG backend: crawl policies from government sources such as the State Taxation Administration and the Ministry of Finance, save them to the local database, match them against enterprise profiles, generate notifications and report. It starts with a health check of the Policy Notification Agent, then asks you to confirm the parameters: full sync or crawl only, keywords such as value-added tax or small-business topics, the maximum number of policies per source (default 20) and whether to notify enterprises (default yes).

The crawl runs through scripts/crawl_policies.py with a params file for the full pipeline, or through a collect endpoint for crawling only. Afterwards the agent cross-references new policies with the existing knowledge base, noting conflicts, amendments and overrides, and the system can match them to enterprise profiles and push personalized notifications over an SSE stream. The compatibility notes name a TAVILY_API_KEY for web search and a running policy crawler service.

When your agent uses it

  • Collecting the latest tax policies from government websites
  • Refreshing a policy knowledge base with newly published regulations
  • Notifying enterprises about policies relevant to their profile

Example prompts

  • “Crawl the latest value-added tax policies and save them to the local database, but do not notify anyone.”
  • “Run a full sync of new policies and match them to our registered enterprises.”
  • “Check that the policy agent is healthy and then fetch new small-business policies.”

Requirements

  • A running policy crawler service and backend API
  • A TAVILY_API_KEY for web search
  • Python to run scripts/crawl_policies.py
  • Compatibility (from SKILL.md): Requires: TAVILY_API_KEY (for web search), policy crawler service API: POST /api/v1/policy/collect (crawl), POST /api/v1/policy/sync (full pipeline) Agent API: POST /api/v1/policy-agent/status (health check)
  • Pre-approved tools (allowed-tools): Bash, Read, Write, search_web

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Confirm Crawl Parameters with User
  2. Trigger the Crawl
  3. Cross-Reference Results
  4. Match Against Enterprises (if enabled)
  5. Report Results

What it can do on your machine

Read from SKILL.md and the folder at commit 94b16cd. 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
    • Read
    • Write
    • search_web

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

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

    Shell commands in SKILL.md call:

    • curl
    • python

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

  • Network

    No URLs in SKILL.md. Its commands use curl, which can reach the network depending on how they are called.

    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.

  • Compatibility

    Requires: TAVILY_API_KEY (for web search), policy crawler service API: POST /api/v1/policy/collect (crawl), POST /api/v1/policy/sync (full pipeline) Agent API: POST /api/v1/policy-agent/status (health check)

    From compatibility in the SKILL.md frontmatter.

Context cost

Policy Crawl Pipeline loads about 1.4k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 404 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
    allowed-tools: Bash, Read, Write, search_web

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 404 words (~1,379 tokens).

“Guides the Policy Notification Agent through the complete policy lifecycle:”

— opening of SKILL.md by Serein-81
name
policy-crawl
allowed-tools
Bash, Read, Write, search_web
compatibility
Requires: TAVILY_API_KEY (for web search), policy crawler service API: POST /api/v1/policy/collect (crawl), POST /api/v1/policy/sync (full pipeline) Agent API: POST /api/v1/policy-agent/status (health check)
when_to_use
Activate when the user asks to collect, crawl, sync, or update policies from authoritative government sources (国家税务总局, 中国政府网, 财政部). Handles: trigger crawl →…
metadata.author
internal-policy-team
metadata.version
1.1
metadata.domain
public

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in rag_backend/skills/public/policy-crawl of Serein-81/financial_rag.

  • SKILL.md
  • scripts/crawl_policies.py

Open the folder on GitHubat commit 94b16cd

Compare with similar skills

Policy Crawl Pipeline 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.

Policy Crawl Pipeline compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Policy Crawl Pipeline this skillSerein-81/financial_rag148—~1.4kAutomated safety check: NotesNone
Tencent ima Knowledge Base Readerzj-unicom-ai/UniEmployee360—~1kAutomated safety check: PassMIT
Psr Coding Style Knowledgedykyi-roman/awesome-claude-code104—~2.3kAutomated safety check: PassMIT
Keirouter Web Fetchmydisha/keirouter147—~741Automated safety check: PassMIT
Firecrawl Knowledge Basefirecrawl/skills117—~612Automated safety check: PassISC
Cf Crawldavila7/claude-code-templates33k—~2.6kAutomated safety check: NotesMIT

Similar skills

  • Tencent ima Knowledge Base Reader

    zj-unicom-ai/UniEmployee

    Exports the article list and original article text from a Tencent ima knowledge base through a logged-in Chrome session, using browser automation.

    360 GitHub stars~1k tokensUpdated 3 days ago
    Knowledge ManagementAuto-check passed

  • Psr Coding Style Knowledge

    dykyi-roman/awesome-claude-code

    PSR-1 and PSR-12 coding standards knowledge base for PHP 8.4 projects.

    104 GitHub stars~2.3k tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

  • Keirouter Web Fetch

    mydisha/keirouter

    Fetch URL → markdown / text / HTML via KeiRouter /v1/web/fetch using Firecrawl / Jina Reader / Tavily Extract / Exa Contents.

    147 GitHub stars~741 tokensUpdated 1 mo ago
    Data & AnalyticsAuto-check passed

  • Firecrawl Knowledge Base

    firecrawl/skills

    Build a knowledge base from web content with Firecrawl. An agent skill from firecrawl/skills.

    117 GitHub stars~612 tokensUpdated 2 days ago
    Knowledge ManagementAuto-check passed

  • Cf Crawl

    davila7/claude-code-templates

    Crawl entire websites using Cloudflare Browser Rendering /crawl API.

    33k GitHub stars~2.6k tokensUpdated yesterday
    Knowledge ManagementAuto-check: notes

  • Kb Refresh

    techwolf-ai/ai-first-toolkit

    Add new sources to your knowledge base or re-scrape existing ones to pick up changes.

    132 GitHub stars~1.3k tokensUpdated 12 days ago
    Knowledge ManagementAuto-check passed

More from Serein-81/financial_rag

  • Enterprise Tax Profile Matching

    Serein-81/financial_rag

    Builds a six-dimension profile of a company and matches it against tax policies to find applicable incentives, obligations, risks and optimization options.

    148 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check: notes

  • Financial Data Entry

    Serein-81/financial_rag

    Guides entry of a single financial record by collecting fiscal-year figures, validating them with a script and confirming before submitting to the financial-data API.

    148 GitHub stars~1.5k tokensUpdated 4 mo ago
    Auto-check: notes

  • Legal Compliance Search

    Serein-81/financial_rag

    Looks up current company registration rules, industry licences and compliance obligations in China through live web search, tailored to the business profile.

    148 GitHub stars~1.6k tokensUpdated 4 mo ago
    Auto-check: notes

  • Tax Law Research

    Serein-81/financial_rag

    Searches current Chinese tax laws, rates and policy changes with Tavily web search, prioritizing government sources and flagging outdated or conflicting results.

    148 GitHub stars~997 tokensUpdated 4 mo ago
    Auto-check: notes

  • Chinese Corporate Income Tax Check

    Serein-81/financial_rag

    Calculates China's corporate income tax with automatic preferential-rate detection for small or high-tech enterprises, then checks compliance.

    148 GitHub stars~787 tokensUpdated 4 mo ago
    Auto-check: notes

  • VAT Calculation

    Serein-81/financial_rag

    Calculates value-added tax from a tax-inclusive sales amount, VAT rate and input tax using a calculator tool, with risk checks and filing suggestions.

    148 GitHub stars~894 tokensUpdated 4 mo ago
    Auto-check: notes

Works with

Categories

Questions about Policy Crawl Pipeline

What does Policy Crawl Pipeline do?

Guides a policy notification agent through crawling government policy sources, saving them locally, matching them to enterprise profiles and generating notifications. The skill walks an agent through the policy lifecycle of a financial RAG backend: crawl policies from government sources such as the State Taxation Administration and the Ministry of Finance, save them to the local database, match them against enterprise profiles, generate notifications and report. It starts with a health check of the Policy Notification Agent, then asks you to confirm the parameters: full sync or crawl only, keywords such as value-added tax or small-business topics, the maximum number of policies per source (default 20) and whether to notify enterprises (default yes).

When should I use Policy Crawl Pipeline?

Policy Crawl Pipeline fits situations like: collecting the latest tax policies from government websites; refreshing a policy knowledge base with newly published regulations; notifying enterprises about policies relevant to their profile.

How do I install Policy Crawl Pipeline in Claude Code?

Run `npx skills add Serein-81/financial_rag --skill policy-crawl -a claude-code`. Or copy the skill folder (rag_backend/skills/public/policy-crawl in Serein-81/financial_rag) into .claude/skills/policy-crawl in your project. Claude Code loads it when a task matches its description.

How do I install Policy Crawl Pipeline in Codex?

Run `npx skills add Serein-81/financial_rag --skill policy-crawl -a codex`. Or copy the skill folder (rag_backend/skills/public/policy-crawl in Serein-81/financial_rag) into .agents/skills/policy-crawl in your project. Codex loads it when a task matches its description.

Can I use Policy Crawl Pipeline 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 Serein-81/financial_rag --skill policy-crawl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/policy-crawl, .gemini/skills/policy-crawl, .github/skills/policy-crawl and .opencode/skills/policy-crawl in your project.

What does Policy Crawl Pipeline need to run?

Going by SKILL.md and its folder, Policy Crawl Pipeline needs Python for the scripts in its folder and the command-line tools its instructions call (curl and python). Our summary lists: A running policy crawler service and backend API; A TAVILY_API_KEY for web search; Python to run scripts/crawl_policies.py. Its frontmatter pre-approves these tools: Bash, Read, Write, search_web. Compatibility (from SKILL.md): Requires: TAVILY_API_KEY (for web search), policy crawler service API: POST /api/v1/policy/collect (crawl), POST /api/v1/policy/sync (full pipeline) Agent API: POST /api/v1/policy-agent/status (health check) .

Does Policy Crawl Pipeline access the network?

SKILL.md contains no URLs. Its commands use curl, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Policy Crawl Pipeline safe to install?

Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. 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 Policy Crawl Pipeline use?

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

How many tokens does Policy Crawl Pipeline use?

About 1.4k tokens (SKILL.md is roughly 5.5k 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 Policy Crawl Pipeline?

Skills that share tags, products or a category with Policy Crawl Pipeline: Tencent ima Knowledge Base Reader (zj-unicom-ai/UniEmployee, 360 stars), Psr Coding Style Knowledge (dykyi-roman/awesome-claude-code, 104 stars), Keirouter Web Fetch (mydisha/keirouter, 147 stars) and Firecrawl Knowledge Base (firecrawl/skills, 117 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Policy Crawl Pipeline?

Serein-81 (a GitHub user) maintains it in Serein-81/financial_rag, which has 148 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on June 5, 2026.

Source: Serein-81/financial_rag on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.