agentmods.dev

a-share-market-commentary

a-share-market-commentary is a skill for Claude Code, Codex from microwind/ai-prompt. It costs 84 tokens per session (917 once invoked), scanned A, original, MIT.

A writing skill for producing factual summaries of China's A-share stock market at three fixed points: shortly after opening, after the midday close, or at the end of the day. A-shares are stocks traded on mainland Chinese exchanges.

In plain words
What is it for?
Use it to write morning, midday, or closing market commentary from index data, trading volume, advancing and declining stocks, and strong or weak sectors.
Why use it?
It turns supplied market figures into a consistent update without making investment recommendations or unsupported predictions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 53repo 4mo ago A scan 84 tokens original MIT

Good fit Use it to write morning, midday, or closing market commentary from index data, trading volume, advancing and declining stocks, and strong or weak sectors.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/microwind/ai-prompt/a-share-market-commentary
View source ↗ microwind/ai-prompt
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 microwind/ai-prompt --skill a-share-market-commentary
Clone the repo
git clone --depth 1 https://github.com/microwind/ai-prompt

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.

agentmods badge for a-share-market-commentary

README.md
[![agentmods](https://agentmods.dev/badge/skills/microwind/ai-prompt/a-share-market-commentary/github.svg)](https://agentmods.dev/skills/microwind/ai-prompt/a-share-market-commentary)
Your own site
<a href="https://agentmods.dev/skills/microwind/ai-prompt/a-share-market-commentary"><img src="https://agentmods.dev/badge/skills/microwind/ai-prompt/a-share-market-commentary/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.

agentmods 80×15 button for a-share-market-commentary

Your own site · 80×15
<a href="https://agentmods.dev/skills/microwind/ai-prompt/a-share-market-commentary"><img src="https://agentmods.dev/badge/skills/microwind/ai-prompt/a-share-market-commentary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 917 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.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00084 $0.00917
Opus 5 $0.00042 $0.00458
Sonnet 5 $0.00017 $0.00183
Haiku 4.5 $0.00008 $0.00092

Measured 11d ago against content hash 15e255fa466a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

a-share-market-commentary 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 11d 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.

Prompt-Practice/04-stock-market-commentary-skill/a-share-market-commentary/SKILL.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

A-Share Market Commentary

Purpose

Generate concise, structured A-share market commentary for:

  1. morning_open_30m
  2. midday_close
  3. market_close

This skill is for market observation and content generation. It is not for investment advice.

When To Use

Use this skill when the user wants:

  • a morning market opening commentary
  • a midday market summary
  • an end-of-day market review
  • structured A-share market content based on supplied market data

Do not use this skill when:

  • the input data is too incomplete for a factual summary
  • the user asks for direct stock recommendations
  • the user asks for certain market predictions
  • the user asks you to invent facts not present in the input

Required Inputs

  • session_type
    • one of: morning_open_30m, midday_close, market_close
  • trade_date
  • index_summary
    • shanghai_composite
    • shenzhen_component
    • chinext
    • optional star50
  • turnover
    • market_total
    • optional estimated_total
  • advancers_decliners
    • up_count
    • down_count
    • optional limit_up_count
    • optional limit_down_count
  • hot_sectors
  • weak_sectors

Optional Inputs

  • main_themes
  • divergent_themes
  • leading_stocks
  • weak_stocks
  • capital_flow
  • market_sentiment
  • special_events
  • extra_notes

Session Focus

morning_open_30m

Focus on:

  • opening index behavior
  • early breadth and turnover
  • first-wave sector rotation
  • initial capital preference
  • what to watch next

midday_close

Focus on:

  • first-half market structure
  • whether morning themes are strengthening or diverging
  • breadth and turnover by noon
  • what to watch in the afternoon

market_close

Focus on:

  • full-day market summary
  • leading and weak themes
  • capital flow and sentiment confirmation
  • next-session watch points

Working Rules

  1. Use only the supplied data.
  2. Never fabricate facts or hidden causes.
  3. Never give buy or sell advice.
  4. Never promise market direction or returns.
  5. Use a professional, calm, neutral tone.
  6. Prefer synthesis over raw data dumping.
  7. If input is incomplete, state that cautiously and narrow the conclusion.

Read the full file on GitHub · 162 lines

Files

What ships with it

3 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.

  1. 11d ago First seen · 162 lines · 0 tokens per session scan A 15e255fa466a

Subscribe to this mod's changes

a-share-market-commentary is a skill published in the GitHub repository microwind/ai-prompt (53 stars, last pushed 4mo ago), licensed MIT. It adds 84 tokens to every session and 917 once invoked, about $0.0004 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.

Finance and fintechai-agentsai-programmingai-prompt-engineeringai-promptsprompt
Related

Other skills, from other repositories

shaman-buffett

A value-investing analysis method based on selecting, analysing, valuing, deciding and holding. Value investing means judging an investment by the worth of the underlying business and taking a long-term view.

linkerlin/PUAX · 17 tokens

ecom-pricing

Set competitive prices and model profitability. Use for Buy Box pricing analysis, profit margin calculation, breakeven analysis, or multi-marketplace pricing strategy.

kangise/ecommerce-ai-skills · 35 tokens

finance-oracle

Activates FinanceOracle — the most comprehensive institutional finance intelligence agent ever built for Claude. Use when you need Goldman Sachs + Bridgewater + Citadel-level analysis: Black-Scholes options pricing, Black-Litterman portfolio construction, fixed income duration/ convexity, hedge fund strategy design…

vignesh2027/Claude-Agentic-Skills2.0-version · 102 tokens

StartupLegalShield

Complete legal intelligence for startups — incorporation, cap table, IP protection, employment law, fundraising docs, SaaS agreements, regulatory compliance, and avoiding the 10 legal mistakes that kill startups.

vignesh2027/Claude-Agentic-Skills2.0-version · 41 tokens

BoardDeckBuilder

Complete board meeting intelligence — board deck design, narrative construction, financial reporting, board management, difficult conversation prep, and building board relationships that accelerate your company.

vignesh2027/Claude-Agentic-Skills2.0-version · 34 tokens

CloudCostOptimizer

Complete FinOps and cloud cost intelligence — AWS/GCP/Azure cost optimization, reserved instance strategy, rightsizing, spot instances, cost allocation, and achieving 30-60% cloud savings without sacrificing reliability.

vignesh2027/Claude-Agentic-Skills2.0-version · 45 tokens