Finance tasks
Liquidity analysisOrder book analysis
Indexedhimself65/finance-skills
Stock Liquidity AnalysisFinance Skill
A three-file Python recipe for spreads, volume, turnover, Amihud measures and square-root impact scenarios. Static review found double-counted spread cost, incorrect tick-size reasoning, inconsistent turnover units and option helpers that omit computed results. Historical activity is not executable order-book depth, and the impact model is uncalibrated. Automatic pip installation writes files; no data request, installation or third-party code was run.
- Assessment score
- 69/100
- Snapshot risk
- High
- Audit conclusion
- Needs review
How the assessment score works
Pineify weights evidence recorded from the captured files: Skill structure 15%, Instruction clarity 20%, Dependency transparency 20%, Permission transparency 20%, Safety guardrails 15%, Finance task fit 10%. Each signal receives full credit for Yes, one-quarter credit for unknown, and none for No.
The score is not an output accuracy test or user rating. Read the findings and financial assumptions even when the score is high. Risk labels summarize recorded permissions and findings; they do not measure investment risk or certify that installation is safe.
Discovery
What this Skill helps an agent do.
Use the tasks and topics below to judge whether the captured workflow fits your question. Read its findings, dependencies and data requirements before relying on an output.
Domains and assets
Technical analysisPublic equities
Topics
liquiditybid-ask-spreadvolume-analysismarket-impactslippageturnover-ratioamihud-illiquidityorder-book-depthexecution-costadvdollar-volumeyfinance
Trust
Evidence from the captured directory.
This content snapshot assessment does not certify the repository, current files, or installation environment. "Not verified" means the captured files did not support a Yes or No conclusion.
License
MITYes
GitHub reports the repository license as MIT License.
Review state
- Automated review
- Automated review
- Install tested
- No
- Human reviewed
- Not verified
Snapshot
- Files reviewed
- 3
- Captured
- 2026-07-29 07:31 UTC
- Snapshot ID
- fsh-stock-liquidity-2026-07-29-001
Permissions
FilesystemRead
YesThe workflow reads the included liquidity reference and imports installed Python libraries.
FilesystemWrite
YesAutomatic pip installation writes packages into the selected Python environment; data-library caches and output destinations are not fully specified.
NetworkAccess
Yesyfinance fetches quote data, historical prices, volume data, and options chains from Yahoo Finance.
ShellExecution
YesThe skill executes Python code for liquidity analysis and may run pip install for dependencies.
CodeExecution
YesThe skill executes Python code for spread, volume, impact, and turnover computations using yfinance, pandas, and numpy.
ExternalCredentials
NoNo external credentials are required — yfinance uses public Yahoo Finance APIs.
Dependencies
yfinance
python3 -m pip install yfinance (auto-installed if missing)
Python library for Yahoo Finance market data. Auto-installed if missing.
pandas
python3 -m pip install pandas (auto-installed if missing)
Data manipulation library. Auto-installed if missing.
numpy
python3 -m pip install numpy (auto-installed if missing)
Numerical computing library. Auto-installed if missing.
Data sources named by the Skill
Yahoo Finance (yfinance)
Quote data, historical prices, options chains, and company info for liquidity analysis.
Snapshot assessment
69/100
Pineify Finance Skill snapshot assessment, version 1.0.0. Generated 2026-10-20 00:00 UTC.
High risk · Needs review
Skill structure
100/100Instruction clarity
100/100Dependency transparency
50/100Permission transparency
56/100Safety guardrails
35/100Finance task fit
80/100Audit findings
High
The impact curve is an uncalibrated scenario
The formula fixes its impact coefficient at one and treats order size divided by daily ADV as participation, without an execution duration or actual concurrent market volume. It does not solve an Almgren-Chriss execution schedule. Multiplying a modeled terminal price move by the whole order is not automatically its average execution cost. The time-scaling extension, score thresholds and 25/50 bps decision gates lack calibration; zero ADV must be unavailable rather than zero impact. Reject negative sizes and distinguish zero orders from missing input.
High
Spread costs and minimum-tick claims need correction
With an unchanged market, buying at ask and selling at bid crosses one full quoted spread, not twice the spread; the source 0.10% to 0.20% example double-counts. Effective spread requires a contemporaneous trade and midpoint, and quoted spread is not a universal upper bound on execution cost. The claim that a $0.50 stock must have a $0.01 or 2% minimum spread is false for sub-dollar NMS quotations; SEC guidance permits finer increments. Check the instrument and current venue rules.
Medium
Volume and open interest are not available order size
Historical intraday volume describes traded activity, and option open interest counts outstanding contracts; neither measures current resting bids or offers. OIC expressly warns against equating them with liquidity. The provided helpers do not supply full Level 2 depth, and ETF execution also depends on current quotes, basket conditions and creation/redemption access rather than one underlying-liquidity label.
Medium
Auto-installs Python packages via pip
Step 1 checks for yfinance/pandas/numpy and auto-installs them via subprocess.check_call([sys.executable, "-m", "pip", "install", ...]) if missing. This executes pip install without user confirmation, which may be unexpected in some environments.
Medium
Two helper return values omit their stated outputs
options_spread_analysis calculates spreads on local filtered frames but returns the original chain, losing those added metrics. Its tail/head selection does not reliably select near-the-money puts when strikes ascend. order_book_proxy computes call and put open interest and volume totals but returns only top-of-book and the volume profile. Correct return contracts and select strikes by actual spot distance before claiming those outputs.
Medium
Dependency manifest is absent from the snapshot
No requirements.txt or pyproject.toml is included. Dependencies (yfinance, pandas, numpy) are auto-installed via pip in Step 1 and documented in README.
Medium
Use consistent turnover, currency and observation windows
The turnover helper returns a fraction: 500% is 5, while the composite score divides its input by 5 expecting 500 to yield 100. Without an explicit conversion the score is off by a factor of 100 in that component. Dollar-volume labels require the actual quote currency; adjusted close times volume is an approximation, not observed execution turnover. Current float is not necessarily historical float. Compare incomplete-day volume with the same elapsed window, preserve genuine zeros, and disclose zero-volume exclusions and missing quote timestamps.
Sources and relations
Context around this Skill.
Repository
himself65/finance-skills
topic
Stock liquidity & trading cost analysis
topic
Bid-ask spread & effective spread
topic
Market impact & slippage estimation
topic
Volume profile & turnover ratio
agent
Claude Code
collection
Market analysis
guide
Reviewing finance skills before install
Registry
Read this record as data.
The public record includes the page-safe snapshot, evidence, assessment, taxonomy, and relations. Internal revision fields stay outside the public projection.
- Record ID
- github:himself65/finance-skills:plugins/market-analysis/skills/stock-liquidity
- Snapshot ID
- fsh-stock-liquidity-2026-07-29-001
This page is an informational registry entry, not investment advice or a security guarantee. A high content quality score does not make the Skill safe for every environment. Review current files, permissions, data sources, and financial assumptions before use.