Decompose return and hedge

Skill secapi-ai/secapi-skills/decompose-return-and-hedge

SEC API agent skills for source-cited filing research with hosted API and MCP workflows

Install

npx -y skills add secapi-ai/secapi-skills --skill decompose-return-and-hedge

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Explains a security return over a stated window and evaluates hedge candidates as exposure trade-offs. Use when you need to separate model attribution from a hedge decision.

SKILL.md

1.7 KB, as published. Nobody here has run it

Decompose Return and Hedge

Explain a return before discussing a hedge. Set the date window, report what the factor model explains, and keep issuer evidence separate from attribution output.

First Read

curl --fail --silent --show-error \
  "https://api.secapi.ai/v1/factors/decomposition?symbol=AAPL&lookback=6m" \
  -H "x-api-key: $SECAPI_API_KEY"

symbol is required. The API also supports optional factors, keys, category, window, lookback, response_mode, and include controls.

What to provide

Give the agent a symbol, a precise date window or lookback, and the exposure question behind the hedge discussion. The skill evaluates trade-offs; it does not select a trade for the user.

Research path

Run GET /v1/factors/decomposition for the stated symbol and window.
Use GET /v1/stocks/{ticker}/loadings to inspect reported position loadings.
Use GET /v1/factors/exposures or GET /v1/factors/correlations only when they clarify concentration or hedge overlap.
Bring in filing or company context through the routes declared in metadata.json, and cite it independently from the attribution model.

Expected result

State the exact window, the model's explained and unexplained components, and any returned fit limitation. Present candidates as changes in exposures, concentration, and residual risk, not recommendations or guarantees. Distinguish factor attribution from filing facts, news, and causal explanation.