Apocdata
ApocData/ApocData-skill
A-share data service with structured announcement parsing: every announcement carries an AI summary, category, importance level and sentiment, fully traceable to source.
Use only for current stock/share prices, ticker quotes, and financial market movers (gainers, losers, most-traded shares).
Install Market Data
$ npx skills add zhongkaifu/TensorSharp --skill market-data -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install zhongkaifu/TensorSharp market-data --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/zhongkaifu/TensorSharp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/TensorAgent/skills/market-data .claude/skills/market-data && rm -rf skills-srcUse ~/.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/
Install the "market-data" agent skill from https://github.com/zhongkaifu/TensorSharp/tree/main/TensorAgent/skills/market-data into .claude/skills/market-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "market-data", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/zhongkaifu/TensorSharp/tree/main/TensorAgent/skills/market-dataType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add zhongkaifu/TensorSharp --skill market-data -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install zhongkaifu/TensorSharp market-data --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zhongkaifu/TensorSharp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/TensorAgent/skills/market-data .agents/skills/market-data && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "market-data" agent skill from https://github.com/zhongkaifu/TensorSharp/tree/main/TensorAgent/skills/market-data into .agents/skills/market-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "market-data", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zhongkaifu/TensorSharp --skill market-data -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install zhongkaifu/TensorSharp market-data --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zhongkaifu/TensorSharp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/TensorAgent/skills/market-data .cursor/skills/market-data && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "market-data" agent skill from https://github.com/zhongkaifu/TensorSharp/tree/main/TensorAgent/skills/market-data into .cursor/skills/market-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "market-data", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/zhongkaifu/TensorSharp.git --path TensorAgent/skills/market-data--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add zhongkaifu/TensorSharp --skill market-data -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install zhongkaifu/TensorSharp market-data --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zhongkaifu/TensorSharp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/TensorAgent/skills/market-data .gemini/skills/market-data && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "market-data" agent skill from https://github.com/zhongkaifu/TensorSharp/tree/main/TensorAgent/skills/market-data into .gemini/skills/market-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "market-data", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install zhongkaifu/TensorSharp market-dataInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add zhongkaifu/TensorSharp --skill market-data -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/zhongkaifu/TensorSharp.git skills-src && mkdir -p .github/skills && cp -r skills-src/TensorAgent/skills/market-data .github/skills/market-data && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "market-data" agent skill from https://github.com/zhongkaifu/TensorSharp/tree/main/TensorAgent/skills/market-data into .github/skills/market-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "market-data", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add zhongkaifu/TensorSharp --skill market-data -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install zhongkaifu/TensorSharp market-data --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/zhongkaifu/TensorSharp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/TensorAgent/skills/market-data .opencode/skills/market-data && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "market-data" agent skill from https://github.com/zhongkaifu/TensorSharp/tree/main/TensorAgent/skills/market-data into .opencode/skills/market-data/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "market-data", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
market-data- GitHub stars
- 568
- Token cost
- ~1k tokens
- SKILL.md length
- 615 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- BSD-3-Clause
At a glance
Use only for current stock/share prices, ticker quotes, and financial market movers (gainers, losers, most-traded shares).
- Tasks that involve Stock and market analysis
- SKILL.md covers Putting it in a deck and What it will not do
- Runs Python scripts from its folder; calls python3
- Tasks that involve LLM inference and serving
What it does
Market Data is an agent skill from zhongkaifu/TensorSharp. Use only for current stock/share prices, ticker quotes, and financial market movers (gainers, losers, most-traded shares). Needs the app's Network switch on; no API key.
Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/market_movers.py`).
It sits in Business, Finance & HR, covering Stock and market analysis and LLM inference and serving. It works with CUDA, DeepSeek, llama.cpp and MiniMax. The repository describes itself as: A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interface, iPhone App, and…. The licence is BSD-3-Clause.
When your agent uses it
- Tasks that involve Stock and market analysis
- Tasks that involve LLM inference and serving
Example prompts
- “/market-data”
Requirements
- Python 3
What it can do on your machine
Read from SKILL.md and the folder at commit 4f57d37. 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 1 file in scripts/ (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
Market Data loads about 1k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 615 words of instructions outside code blocks.
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); the scripts in this folder are not scanned.
SKILL.md
The full file from zhongkaifu/TensorSharp at commit 4f57d37, republished under its BSD-3-Clause licence (© zhongkaifu). 615 words, ~1,041 tokens.
Download SKILL.mdSave it as
.claude/skills/market-data/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- market-data
- description
- Use only for current stock/share prices, ticker quotes, and financial market movers (gainers, losers, most-traded shares). Needs the app's Network switch on; no API key.
Market data
One script. It asks a JSON endpoint for rows that are already typed and ranked, so nothing has to be parsed out of a page or remembered.
python3 scripts/market_movers.py --movers gainers --count 10
python3 scripts/market_movers.py --movers losers --count 5
python3 scripts/market_movers.py --movers actives --count 10
python3 scripts/market_movers.py --quote AAPL MSFT NVDAIt prints a heading naming the source and the data's own timestamp, then a markdown table. That output is the answer: copy the rows as printed. Do not round them, re-order them, or add a column the table does not have.
| Option | Effect |
|---|---|
--movers gainers|losers|actives | the day's movers, ranked by the endpoint |
--quote SYM ... | quote named symbols instead |
--count N | how many rows, 1-50 (default 10) |
--any-instrument | include funds and trusts, not only ordinary shares |
--json FILE | also write the rows as objects, for a follow-up script |
--spec FILE | also write a make_pptx.py spec for these rows |
--title TEXT | title for --spec |
Putting it in a deck
--spec writes a spec the documents skill accepts as it stands, so the whole
request is two commands:
python3 scripts/market_movers.py --movers gainers --count 10 --spec spec.json --title "Top 10 gainers today"
python3 ../documents/scripts/make_pptx.py --spec spec.json --out gainers.pptxThe spec splits at twelve rows per slide, which is what a table slide holds.
Return the .pptx to the user as the downloadable artifact.
What it will not do
It never fills a gap. A row has to carry a symbol, a name, a price, a change, a percentage and a volume, with numbers where numbers belong. A row missing any of them is dropped, so asking for ten can return eight — and eight real rows is the answer, not a reason to invent two. If nothing usable comes back the script exits non-zero and prints why; say that, and do not answer the question from memory. Prices you remember are wrong by definition.
It does not say why a price moved. The response carries prices, not reasons. A number here supports "ROIV is up 18.75% today"; it supports no sentence containing "because", "on news of", or "driven by". If the user asks why, say the data does not carry it.
Read the Currency column. --movers is US shares and prints USD, but
--quote takes any symbol the source knows, and those are priced in their own
market's unit — a London line comes back in GBp, which is PENCE, so 1,574.80
is £15.75 and not £1,574.80. The unit is a column in the table for that reason.
Never compare two rows' prices without it, and never drop it when you quote a row.
Show full SKILL.md (227 more words)Show less
Read the heading too. It says when the rows were stamped, and it says "rows stamped between" when they do not share a moment, which they will not across exchanges. If the session is not open it says so — "last market closed price" — and then "today" in a title means the last close, not a live price.
A long --quote can run out of time. Each symbol is its own request, and the
run keeps a budget inside the tool's timeout so a few slow symbols cannot cost you
the whole answer. If it runs out, the table holds the symbols that answered and a
note names the ones left out; ask for those in a second run rather than repeating
the whole list.
One moment, not a history. These are prices as the source last stamped them. It is not a portfolio, a history, a forecast, or advice, and nothing here should be presented as any of those.
Where the data comes from. Two JSON endpoints Yahoo publishes for its own front end. They are undocumented and unofficial: they can change or start refusing without notice, which is what the non-zero exits are for. Attribute the source in your answer, as the printed heading does. Do not present the figures as a licensed market feed, and do not build anything that depends on them staying available.
© zhongkaifu, BSD-3-Clause. 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 1 other file (scripts) in TensorAgent/skills/market-data of zhongkaifu/TensorSharp.
- SKILL.md
- scripts/market_movers.py
Open the folder on GitHubat commit 4f57d37
Compare with similar skills
Market Data 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Market Data this skillzhongkaifu/TensorSharp | 568 | — | ~1k | Automated safety check: Pass | BSD-3-Clause | |
| ApocdataApocData/ApocData-skill | 104 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Add Modelguoqingbao/xinfer | 334 | — | ~4.2k | Automated safety check: Notes | MIT | |
| Add New ModelJakeATX/llamAmpere | 166 | — | ~4.1k | Automated safety check: Pass | MIT | |
| Code ReviewJakeATX/llamAmpere | 166 | — | ~5.6k | Automated safety check: Pass | MIT | |
| Update Ollama Cloud Modelsheypinchy/pinchy | 182 | — | ~3.9k | Automated safety check: Notes | AGPL-3.0 |
Similar skills
Add Model
guoqingbao/xinfer
Adapt and port new LLM model architectures to this xinfer project.
Add New Model
JakeATX/llamAmpere
Guided workflow for adding a new model architecture to llama.cpp.
Code Review
JakeATX/llamAmpere
Review llama.cpp changes against project conventions and common reviewer pitfalls before a PR.
Update Ollama Cloud Models
heypinchy/pinchy
A skill your agent uses when a new Ollama Cloud model is announced or available (e.g.
App
JakeATX/llamAmpere
Opinionated app components building on top of ./ui primitives
More from zhongkaifu/TensorSharp
Documents
zhongkaifu/TensorSharp
Read and write real documents on the device - PDF, XLSX, DOCX, PPTX and CSV.
Research
zhongkaifu/TensorSharp
A skill your agent uses for web searches and current information lookups, finding sources, fact-checking, researching questions, comparing sources, or summarising web pages.
Related
Questions about Market Data
What does Market Data do?
Use only for current stock/share prices, ticker quotes, and financial market movers (gainers, losers, most-traded shares). Market Data is an agent skill from zhongkaifu/TensorSharp. Use only for current stock/share prices, ticker quotes, and financial market movers (gainers, losers, most-traded shares).
When should I use Market Data?
Market Data fits situations like: tasks that involve Stock and market analysis; tasks that involve LLM inference and serving.
How do I install Market Data in Claude Code?
Run `npx skills add zhongkaifu/TensorSharp --skill market-data -a claude-code`. Or copy the skill folder (TensorAgent/skills/market-data in zhongkaifu/TensorSharp) into .claude/skills/market-data in your project. Claude Code loads it when a task matches its description.
How do I install Market Data in Codex?
Run `npx skills add zhongkaifu/TensorSharp --skill market-data -a codex`. Or copy the skill folder (TensorAgent/skills/market-data in zhongkaifu/TensorSharp) into .agents/skills/market-data in your project. Codex loads it when a task matches its description.
Can I use Market Data 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 zhongkaifu/TensorSharp --skill market-data -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/market-data, .gemini/skills/market-data, .github/skills/market-data and .opencode/skills/market-data in your project.
What does Market Data need to run?
Going by SKILL.md and its folder, Market Data needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Market Data 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 Market Data 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Market Data use?
Market Data is published under the BSD-3-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Market Data use?
About 1k tokens (SKILL.md is roughly 4.2k 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 Market Data?
Skills that share tags, products or a category with Market Data: Apocdata (ApocData/ApocData-skill, 104 stars), Add Model (guoqingbao/xinfer, 334 stars), Add New Model (JakeATX/llamAmpere, 166 stars) and Code Review (JakeATX/llamAmpere, 166 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Market Data?
zhongkaifu (a GitHub user) maintains it in zhongkaifu/TensorSharp, which has 568 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 11, 2026.
Source: zhongkaifu/TensorSharp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.