China Market Open Data Search
OpenSenseNova/SenseNova-Skills
Researches Chinese market, macro, trade, procurement, listed-company and regulatory information from free official sources that need no sign-up or API key.
Runs multi-step finance research as a tracked goal with acceptance criteria and linked evidence, strictly for research and never for placing trades.
Install Goal-Driven Finance Research
$ npx skills add HKUDS/Vibe-Trading --skill research-goal -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install HKUDS/Vibe-Trading research-goal --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/HKUDS/Vibe-Trading.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent/src/skills/research-goal .claude/skills/research-goal && 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 "research-goal" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/research-goal into .claude/skills/research-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-goal", 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/HKUDS/Vibe-Trading/tree/main/agent/src/skills/research-goalType 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 HKUDS/Vibe-Trading --skill research-goal -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install HKUDS/Vibe-Trading research-goal --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agent/src/skills/research-goal .agents/skills/research-goal && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "research-goal" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/research-goal into .agents/skills/research-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-goal", 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 HKUDS/Vibe-Trading --skill research-goal -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install HKUDS/Vibe-Trading research-goal --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agent/src/skills/research-goal .cursor/skills/research-goal && 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 "research-goal" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/research-goal into .cursor/skills/research-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-goal", 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/HKUDS/Vibe-Trading.git --path agent/src/skills/research-goal--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 HKUDS/Vibe-Trading --skill research-goal -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install HKUDS/Vibe-Trading research-goal --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agent/src/skills/research-goal .gemini/skills/research-goal && 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 "research-goal" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/research-goal into .gemini/skills/research-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-goal", 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 HKUDS/Vibe-Trading research-goalInstalls 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 HKUDS/Vibe-Trading --skill research-goal -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .github/skills && cp -r skills-src/agent/src/skills/research-goal .github/skills/research-goal && 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 "research-goal" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/research-goal into .github/skills/research-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-goal", 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 HKUDS/Vibe-Trading --skill research-goal -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install HKUDS/Vibe-Trading research-goal --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agent/src/skills/research-goal .opencode/skills/research-goal && 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 "research-goal" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/research-goal into .opencode/skills/research-goal/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "research-goal", 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
research-goal- GitHub stars
- 35k
- Token cost
- ~813 tokens
- SKILL.md length
- 425 words
- Files
- 1
- Skills in repo
- 89
- Repo updated
- First seen
- Licence
- MIT
At a glance
Runs multi-step finance research as a tracked goal with acceptance criteria and linked evidence, strictly for research and never for placing trades.
- Works in 6 steps: Call start_research_goal with a concise… → Include 3-5 acceptance criteria when the… → Before continuing an existing task, call… → …
- Comparing several strategies or assets where each conclusion needs supporting evidence
- SKILL.md covers When to Attach a Goal, Tool Flow, Criteria Template and Evidence Rules, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill attaches a research-only goal to larger finance tasks, such as comparisons, audits and thesis reviews, that need several criteria before a conclusion is credible or that continue across turns. It uses a set of goal tools: one to start the goal with a short objective and usually three to five acceptance criteria, one to read the current goal, one to add evidence, and one to update the status once every required criterion has been audited.
Evidence is added after each market-data lookup, backtest, document read, web source or reasoning step, linked to a criterion, and kept short and concrete. Artifact-backed evidence is preferred, with fields such as run ID, artifact path, source provider, symbol universe, benchmark and data date included when known, and the exact tool call ID copied from the result it came from. Completion needs verified evidence from an existing run or an allowed artifact with a matching hash, and live trading instructions are refused or reframed as research. The excerpt is cut off before the completion rules.
When your agent uses it
- Comparing several strategies or assets where each conclusion needs supporting evidence
- Running a thesis review that will continue across several conversation turns
- Auditing a finished piece of finance research against its stated criteria
Example prompts
- “Start a research goal to compare a momentum and a value strategy on US large caps, with evidence for each criterion.”
- “Pick up the existing research goal and tell me which criteria still lack evidence.”
- “Audit my sector thesis against the goal criteria and mark it complete only if the evidence checks out.”
Requirements
- The research goal tools provided by the host runtime
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Call start_research_goal with a concise research-only objective.
- Include 3-5 acceptance criteria when the user provided enough context.
- Before continuing an existing task, call get_research_goal.
- After a market-data lookup, backtest, document read, web source, or manual reasoning step, call add_goal_evidence.
- Link evidence to a criterion using criterion_id or criterion_index.
- When all required criteria have been audited, call update_research_goal_status.
What it can do on your machine
Read from SKILL.md and the folder at commit 8e43007. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Goal-Driven Finance Research loads about 813 tokens when it runs. Until then it costs about 40 tokens; SKILL.md has 425 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from HKUDS/Vibe-Trading at commit 8e43007, republished under its MIT licence (© HKUDS). 425 words, ~813 tokens.
Download SKILL.mdSave it as
.claude/skills/research-goal/SKILL.md (or your agent's skills folder).- name
- research-goal
- description
- Goal-driven finance research workflow: attach a research-only objective, track criteria, and add evidence while avoiding live trading execution.
- category
- flow
Goal-Driven Finance Research
Use this skill when a user asks for a multi-step finance research task, comparison, audit, thesis review, or "keep working until the answer is supported." The goal runtime is for research only. Never use it to place, submit, or execute trades.
When to Attach a Goal
Start a goal when the task has any of these traits:
- It needs multiple criteria before a conclusion is credible.
- It compares strategies, assets, regimes, or evidence sources.
- It may continue across turns or require a final audit.
- The user asks for "long driven task", "goal", "审计", "对比", "研究结论", or similar.
Do not start a goal for a tiny one-shot answer unless the user explicitly asks.
Tool Flow
- Call
start_research_goalwith a concise research-only objective. - Include 3-5 acceptance criteria when the user provided enough context.
- Before continuing an existing task, call
get_research_goal. - After a market-data lookup, backtest, document read, web source, or manual reasoning step, call
add_goal_evidence. - Link evidence to a criterion using
criterion_idorcriterion_index. - When all required criteria have been audited, call
update_research_goal_status.
Criteria Template
Use this shape when the user did not provide criteria:
- Define the research-only thesis and symbol universe.
- Collect fresh market, benchmark, or artifact evidence.
- Compare alternatives or a control baseline.
- Record caveats, contradictions, and the non-advice boundary.
Show full SKILL.md (206 more words)Show less
Evidence Rules
- Keep evidence short and concrete.
- Prefer artifact-backed evidence when a tool produced a run or file.
- Include
run_id,artifact_path,source_provider,source_type,symbol_universe,benchmark, anddata_as_ofwhen known. - For evidence backed by one specific tool result, copy that result's exact
tool_call_idintoadd_goal_evidence; do not shorten, alias, or invent it. evidence_idvalues such asev_...identify rows in the research-goal ledger. They are used by goal audits and are never grounding source refs; do not writeev_...::fieldin a figures declaration.tool_call_idpreserves provenance but does not verify goal completion by itself. Completion still needs verified evidence from an existingrun_idor an allowedartifact_pathwith a matching sha256 hash.- Do not mark live trading instructions as evidence. Refuse or reframe them as research-only analysis.
Completion Rules
- Use
update_research_goal_status(status="complete")only after every required criterion has an audit row. - Satisfied audit rows must cite verified
evidence_ids. - Use
status="blocked"orstatus="insufficient_evidence"when evidence is missing, stale, contradictory, or not verifiable. - Use
status="cancelled"only when the user explicitly asks to end or discard the goal.
Response Style
Tell the user what the goal is tracking only when it helps. Do not flood the answer with ledger details. Lead with the research conclusion, then mention which criteria remain unresolved.
© HKUDS, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in agent/src/skills/research-goal of HKUDS/Vibe-Trading.
Open the folder on GitHubat commit 8e43007
Compare with similar skills
Goal-Driven Finance Research 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 |
|---|---|---|---|---|---|---|
| Goal-Driven Finance Research this skillHKUDS/Vibe-Trading | 35k | — | ~813 | Automated safety check: Pass | MIT | |
| China Market Open Data SearchOpenSenseNova/SenseNova-Skills | 5.7k | — | ~954 | Automated safety check: Notes | MIT | |
| Private Company Researchxbtlin/ai-berkshire | 17k | — | ~5.9k | Automated safety check: Pass | MIT | |
| Longbridge Earningshelsome/folio | 271 | 1 repos | ~2.5k | Automated safety check: Pass | None | |
| Consulting Analysisbytedance/deer-flow | 84k | 4 repos | ~8.4k | Automated safety check: Pass | MIT | |
| Management Deep Divexbtlin/ai-berkshire | 17k | — | ~1.7k | Automated safety check: Pass | MIT |
Similar skills
Private Company Research
xbtlin/ai-berkshire
Runs a team of parallel agents to research a company with no public listing, rebuilding its business model, finances and competition from scattered sources.
Longbridge Earnings
helsome/folio
Earnings analysis — pre- and post-earnings. An agent skill from helsome/folio.
Consulting Analysis
bytedance/deer-flow
A skill your agent uses when the user requests to generate, create, or write professional research reports including but not limited to market analysis, consumer insights, brand analysis, financial…
Management Deep Dive
xbtlin/ai-berkshire
Researches a company's leadership from public sources: statements versus results, capital allocation decisions, governance and pay, and feedback from outside the firm.
Earnings Analyst Master
OctagonAI/skills
Comprehensive earnings call analyst skill that orchestrates all Octagon earnings analysis skills.
More from HKUDS/Vibe-Trading
All 89 skills in this repoEastmoney Market Data
HKUDS/Vibe-Trading
Index of Eastmoney's free, no-token market data interfaces for China A-shares and Hong Kong stocks: fund flows, dragon-tiger lists, margin trading, reports and news.
OKX Market Data
HKUDS/Vibe-Trading
Retrieves public OKX cryptocurrency market data such as spot prices, candlesticks, funding rates and open interest through the OKX V5 REST API, with no authentication.
SEC EDGAR Filings Fetcher
HKUDS/Vibe-Trading
Fetches U.S. SEC EDGAR data: resolves tickers to CIK numbers, lists recent 10-K, 10-Q and 8-K filings with document URLs, and pulls XBRL financial series.
A-Share ST Risk Screener
HKUDS/Vibe-Trading
Predicts whether a mainland China A-share company risks an ST or *ST warning after its next annual report, using financial thresholds and Sina penalty records.
Supply-Chain Bottleneck Hunter
HKUDS/Vibe-Trading
Breaks a structural trend such as AI infrastructure into its physical supply chain and ranks lesser-known listed companies sitting on each bottleneck.
Eight-Part Company Deep Dive
HKUDS/Vibe-Trading
Plans and drafts an eight-part, roughly 120k-word investigative series on one company, built around a strict fact-check pass rather than fast drafting.
Related
Categories
Questions about Goal-Driven Finance Research
What does Goal-Driven Finance Research do?
Runs multi-step finance research as a tracked goal with acceptance criteria and linked evidence, strictly for research and never for placing trades. This skill attaches a research-only goal to larger finance tasks, such as comparisons, audits and thesis reviews, that need several criteria before a conclusion is credible or that continue across turns. It uses a set of goal tools: one to start the goal with a short objective and usually three to five acceptance criteria, one to read the current goal, one to add evidence, and one to update the status once every required criterion has been audited.
When should I use Goal-Driven Finance Research?
Goal-Driven Finance Research fits situations like: comparing several strategies or assets where each conclusion needs supporting evidence; running a thesis review that will continue across several conversation turns; auditing a finished piece of finance research against its stated criteria.
How do I install Goal-Driven Finance Research in Claude Code?
Run `npx skills add HKUDS/Vibe-Trading --skill research-goal -a claude-code`. Or copy the skill folder (agent/src/skills/research-goal in HKUDS/Vibe-Trading) into .claude/skills/research-goal in your project. Claude Code loads it when a task matches its description.
How do I install Goal-Driven Finance Research in Codex?
Run `npx skills add HKUDS/Vibe-Trading --skill research-goal -a codex`. Or copy the skill folder (agent/src/skills/research-goal in HKUDS/Vibe-Trading) into .agents/skills/research-goal in your project. Codex loads it when a task matches its description.
Can I use Goal-Driven Finance Research 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 HKUDS/Vibe-Trading --skill research-goal -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/research-goal, .gemini/skills/research-goal, .github/skills/research-goal and .opencode/skills/research-goal in your project.
What does Goal-Driven Finance Research need to run?
SKILL.md names no scripts, command-line tools or credentials: Goal-Driven Finance Research is instructions for the agent only. Our summary lists: The research goal tools provided by the host runtime.
Does Goal-Driven Finance Research 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 Goal-Driven Finance Research 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. Review the folder before installing.
What licence does Goal-Driven Finance Research use?
Goal-Driven Finance Research is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Goal-Driven Finance Research use?
About 813 tokens (SKILL.md is roughly 3.3k 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 Goal-Driven Finance Research?
Skills that share tags, products or a category with Goal-Driven Finance Research: China Market Open Data Search (OpenSenseNova/SenseNova-Skills, 5.7k stars), Private Company Research (xbtlin/ai-berkshire, 17k stars), Longbridge Earnings (helsome/folio, 271 stars) and Consulting Analysis (bytedance/deer-flow, 84k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Goal-Driven Finance Research?
HKUDS (a GitHub organization) maintains it in HKUDS/Vibe-Trading, which has 35,163 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 10, 2026.
Source: HKUDS/Vibe-Trading on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.