Agentic Research Directory

Agent skill

AlphaKit: bilingual investment-research skills

AlphaKit documents a bilingual finance and investment-research skill collection. Its original skills cover incremental business sizing, model exhibits and preliminary stock-research briefs; the sizing workflow accepts sourced assumptions and produces scenarios and sensitivity outputs.

Workflow level n/a Source: Repository-documented Outcome: Not empirically evaluated here

Research applicability

Supports explicit-assumption financial scenario analysis and source-grounded research briefs; researchers must distinguish hypothetical scenarios from empirical estimates.

Getting started

Editorial suggestion, not an executed recipe: read docs/RESEARCH_SKILLS.md, inspect one complete skill folder and its licence, then try the supplied synthetic scenario in an isolated environment before supplying authorized research inputs.

Maintenance

Live documentation was retrieved; maintenance quality and future availability are not guaranteed.

License

Consult original licence files and third-party terms; not independently audited.

Workflow & human oversight

Resource-level automation is unspecified. Researchers choose goals, inputs, permissions and evaluation criteria and remain responsible for interpreting outputs.

Workflow level is not an evidence score; higher is not better evidence.

Approach

AlphaKit documents a bilingual finance and investment-research skill collection. Its original skills cover incremental business sizing, model exhibits and preliminary stock-research briefs; the sizing workflow accepts sourced assumptions and produces scenarios and sensitivity outputs.

Limitations

README and original-skills documentation only; no skill execution, investment outcome verification, host integration test or underlying third-party catalogue audit. The source explicitly distinguishes source checks from execution checks; examples are synthetic. Documentation reports other hosts' discovery/calling has not been tested. No return or predictive-accuracy claim is accepted.

Reproducibility

No software or research experiment was run. Bodies, retrieval URLs, access timestamps and SHA-256 are archived; no commit pin was retrieved.

Adoption requirements

A compatible custom-skill host and complete skill folders; Python for sizing, Pillow/openpyxl and Chinese-capable fonts for rendering, as documented. Use only authorized source material, preserve package and third-party licences, and review permissions and assumptions before running.

Comments

No comments yet.

Add a comment

Comments are held for moderation before appearing. Critical or corrective comments are welcome — especially evidence that an entry overstates what has been verified.

Submitting stores your comment text, the optional name and email, and a pseudonymised connection identifier used only for spam limiting (the raw IP address is not stored).