← Back to Skills Marketplace
warriorfan

Ashare Fund Intel

by warriorfan · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
291
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install ashare-fund-intel
Description
Produce scheduled A-share and fund intelligence reports with bullish and bearish signals, source-backed analysis, and position-adjustment suggestions. Use wh...
README (SKILL.md)

A-Share Fund Intel

Overview

This skill creates robust A-share and fund monitoring reports at fixed times:

  • Pre-open briefing (before 09:00)
  • Post-close review (after 15:00)
  • NAV/earnings confirmation report (after 21:00)

Inputs To Confirm

When first used, confirm these and persist in session memory:

  • Risk preference: conservative / balanced / aggressive
  • Position style: index funds / sector funds / mixed / stock-heavy
  • Watchlist: indices, sectors, funds, and key holdings
  • Delivery format: concise / detailed

If user did not provide a watchlist, use default broad market + mainstream fund buckets from references/sources.md. If user already provided holdings, read references/portfolio-current.md and treat it as highest-priority personalization input.

Data Collection Rules

  1. Use source-backed content only.
  2. Prefer official and primary sources first, then mainstream media, then blogger views.
  3. If web_search is unavailable, continue via browser + web_fetch; do not stop.
  4. If a source is blocked/paywalled, state it explicitly and switch to an alternate source.
  5. For each major claim, attach at least one URL.

Source Priority

Read references/sources.md and follow this order:

  1. Regulators/exchanges/official disclosures
  2. Financial reports and company announcements
  3. Authoritative finance media
  4. Well-known finance bloggers/opinion leaders (sentiment reference only)

Three Report Modes

Read references/report-template.md and render by mode:

  1. PRE_OPEN (before 09:00)
  • Overnight macro and policy signals
  • Futures/ADR/major index context
  • Today's A-share and fund key catalysts
  • Suggested opening risk posture and position tilt
  1. POST_CLOSE (after 15:00)
  • Market breadth, turnover, northbound flow, sector rotation
  • Fund-relevant winners/losers and style shift
  • Bullish vs bearish factors from today's tape and news
  • Next-session position-adjustment playbook
  1. NIGHT_CONFIRM (after 21:00)
  • Fund NAV/profit confirmation and attribution
  • Earnings/announcements impact scan
  • Policy/news digest after close
  • Risk check and next-day tentative allocation range

For all three modes, include a personalized holdings section:

  • Per-fund impact scan (event -> affected fund -> direction)
  • Per-fund action tag: increase / hold / reduce
  • Simple suggested allocation change range (percentage points)

Output Constraints

  • Use the template structure and keep section titles stable.
  • Include:
    • Bullish factors (>=3)
    • Bearish factors (>=3)
    • Position suggestion with explicit range (e.g., equity 55-65%)
    • Top risks for next window (>=3)
    • Personalized holdings actions for each held fund
  • Separate facts from opinions clearly.
  • End with:
    • This is not investment advice.

Trigger Phrases

This skill should activate when user asks for:

  • A-share/China market daily monitoring
  • Fund briefing or NAV confirmation report
  • Bullish/bearish signal summary for position adjustment
  • Timed finance reports (morning close night)
Usage Guidance
This skill appears internally consistent and does not request credentials. Before installing: (1) confirm you are comfortable with the agent fetching public web sources (it will use web_search/browser + web_fetch and include URLs in reports); (2) avoid pasting any sensitive credentials into the conversation—none are required; (3) clarify the holdings precedence behavior (it currently suggests the shipped portfolio file may override user-provided holdings); and (4) treat outputs as informational (the skill explicitly states 'This is not investment advice'), verify before acting on allocation recommendations.
Capability Analysis
Type: OpenClaw Skill Name: ashare-fund-intel Version: 1.0.0 The ashare-fund-intel skill is a financial analysis tool designed to generate market reports and portfolio suggestions for the Chinese A-share and fund markets. It uses standard web browsing and search capabilities to aggregate data from legitimate financial sources (e.g., CSRC, EastMoney, Caixin) and processes user-provided portfolio data (references/portfolio-current.md) to offer personalized insights. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the logic is consistent with its stated purpose.
Capability Assessment
Purpose & Capability
Name/description (A-share & fund intelligence) align with the actual behavior: timed reports, source-backed signals, per-fund actions. The declared footprint (no binaries, no env vars, no external installs) is proportionate to the stated purpose.
Instruction Scope
Runtime instructions stick to collecting public market sources and building reports using bundled reference files. It requires web access (web_search, browser + web_fetch fallback) and instructs attaching URLs for claims — this is expected for a sourcing skill. One minor inconsistency: the SKILL.md says 'If user already provided holdings, read references/portfolio-current.md and treat it as highest-priority personalization input' which could override a user's own holdings; that is a behavioral/design oddity (not a direct security issue) and should be clarified with the author if you expect the agent to always honor user-provided holdings.
Install Mechanism
No install spec and no code files beyond static references; nothing will be written to disk or fetched during install. This is the lowest-risk install profile.
Credentials
The skill declares no environment variables, no credentials, and no config paths. There are no requests for unrelated secrets or tokens.
Persistence & Privilege
always is false and the skill requests only session-memory persistence of user preferences (risk profile, watchlist, etc.), which is appropriate for personalization. Autonomous invocation is allowed by default but not combined with elevated privileges or credentials.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install ashare-fund-intel
  3. After installation, invoke the skill by name or use /ashare-fund-intel
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
ashare-fund-intel v1.0.0 - Initial release with automated, scheduled A-share and fund intelligence reports. - Supports pre-open, post-close, and night NAV/earnings report modes. - Personalized based on user risk, position style, watchlist, and preferred format. - Strictly source-backed analysis with explicit URL references and source priority rules. - Provides bullish/bearish signal summaries, position adjustment suggestions, and risk highlights per report. - Triggered by user requests for China market/fund briefs, NAV confirmation, or position review.
Metadata
Slug ashare-fund-intel
Version 1.0.0
License
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Ashare Fund Intel?

Produce scheduled A-share and fund intelligence reports with bullish and bearish signals, source-backed analysis, and position-adjustment suggestions. Use wh... It is an AI Agent Skill for Claude Code / OpenClaw, with 291 downloads so far.

How do I install Ashare Fund Intel?

Run "/install ashare-fund-intel" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Ashare Fund Intel free?

Yes, Ashare Fund Intel is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Ashare Fund Intel support?

Ashare Fund Intel is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Ashare Fund Intel?

It is built and maintained by warriorfan (@warriorfan); the current version is v1.0.0.

💬 Comments