Finance tasks
Dcf valuationEarnings analysisEarnings previewOptions analysisSupply chain mappingSec filing analysisSentiment analysis
Indexedhimself65/finance-skills
Funda DataFinance Skill
A 14-file guide to Funda MCP research and REST datasets, including filings, statements, options, news and inferred supply-chain or hiring signals. It documents credentials and partial results, but response formats vary by endpoint and model scores lack demonstrated calibration. Setup can write local configuration and research prompts leave the device. Current documentation access returned HTTP 401; no subscription, authenticated data request or third-party code was tested.
- Assessment score
- 84/100
- Snapshot risk
- Medium
- 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
Equity valuationFundamental analysisSupply chain analysisMarket sentimentPublic equities
Topics
funda-aifinancial-datamcprest-apioptions-chainsupply-chainsec-filingsearnings-transcriptscongressional-tradesmarket-quotes
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
- 14
- Captured
- 2026-07-29 07:31 UTC
- Snapshot ID
- fsh-funda-data-2026-07-29-001
Permissions
FilesystemRead
YesThe skill reads .env files from the current directory and git repo root to resolve the API key.
FilesystemWrite
YesOptional MCP registration writes client configuration; the README also describes adding a key to a local .env file. Data retrieval itself is separate from these setup writes.
NetworkAccess
YesThe skill uses curl to call the Funda AI REST API and optionally registers an MCP server.
ShellExecution
YesThe skill instructs the agent to use curl for API requests and shell scripts for API key resolution.
CodeExecution
YesThe skill pipes API responses through python3 -m json.tool for formatting.
ExternalCredentials
YesThe captured guide specifies REST API-key and MCP OAuth access with subscription checks. Current account entitlements and pricing were not verified; public documentation requests returned HTTP 401.
Dependencies
curl
Available in shell
Shell tool for HTTP requests to the Funda AI REST API.
python3
Python 3 for JSON formatting
Optional, used for formatting JSON output.
Funda AI MCP
OAuth via claude mcp add (paid subscription)
MCP server at funda.ai/api/mcp for research synthesis via agent_chat tool.
Funda AI REST API
FUNDA_API_KEY required (paid subscription)
REST API at api.funda.ai/v1 with 60+ endpoints for raw structured financial data.
Data sources named by the Skill
Funda AI MCP
The captured guide describes remote research synthesis through agent_chat, including partial-result and conversation metadata.
Funda AI REST API
REST API with 60+ endpoints covering quotes, prices, financial statements, options, supply-chain KG, alternative data, news, calendars, and economics.
Snapshot assessment
84/100
Pineify Finance Skill snapshot assessment, version 1.0.0. Generated 2026-10-20 00:00 UTC.
Medium risk · Needs review
Skill structure
100/100Instruction clarity
100/100Dependency transparency
65/100Permission transparency
75/100Safety guardrails
81/100Finance task fit
85/100Audit findings
Medium
Preserve dates, units and financial definitions
Reported congressional transactions and holdings are not live positions; distinguish transaction, period and disclosure dates. Options activity labels do not prove participant identity or opening intent. A balance sheet is a point-in-time stock even when an endpoint name contains TTM. AI news summaries and sentiment labels require source checks. No order-execution implementation is included in this captured guide.
Medium
Model scores do not establish event probabilities or causal returns
Hiring-based launch_probability, estimated business exposure and stock-impact scores are model outputs, not verified launch facts or demonstrated forecast probabilities. A LAUNCHED status encoded as 1.0 is a status convention. Supply-chain confidence and bottleneck labels also require their source documents and observation dates. Reported CAR versus QQQ and a nominal p-value do not establish causal trading alpha without sample, event-window, estimation and multiple-testing details.
Medium
Dependency manifest is absent from the snapshot
No requirements.txt or equivalent manifest is included in the captured directory.
Medium
Captured guide specifies subscription-gated access
The captured guide documents subscription checks for both surfaces. Current access terms, endpoint availability and authenticated responses were not independently tested; current reference URLs returned HTTP 401 during review.
Medium
Research requests leave the local agent
MCP research sends the question to Funda and can return a conversation ID and history URL. Standalone calls without conversation memory do not establish a no-retention policy. The Claude proxy sends messages through Funda to the documented upstream model service. Review current data-handling terms before supplying private research, and cite underlying filings or datasets rather than treating a conversation URL as primary evidence.
Medium
Use endpoint-specific response and pagination contracts
The main guide describes a common response envelope and page-based pagination. Its own Claude proxy reference instead specifies native Anthropic messages responses, while some alternative-data routes use offset and limit. Do not apply one parser to every route. MCP registration alone also does not prove successful authentication or a callable tool.
Low
Reads .env files for API key resolution
The fallback reads local .env files and extracts the matching API-key line. It is not a full dotenv parser; review quoting and Git-path assumptions without displaying the key or including it in a report.
Sources and relations
Context around this Skill.
Repository
himself65/finance-skills
topic
Financial data platforms
topic
Supply-chain analysis
topic
Options & flow
agent
Claude Code
collection
Data providers
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/data-providers/skills/funda-data
- Snapshot ID
- fsh-funda-data-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.