skills.rest
loanntc
loanntcCOMMUNITY
Explore all skills by this author →
GitHub

research-goal

Structure multi-step finance research with acceptance criteria and auditable evidence.

Updated Apr 14, 2026
Search Tags:#backtesting#evidence tracking#research workflow#goal management#finance research#criteria audit#non-advice boundary
One-click install
npx skills add https://github.com/loanntc/Paave --skill research-goal
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research-goal
Source: https://github.com/loanntc/Paave/tree/main/skills/research-goal
Command: npx skills add https://github.com/loanntc/Paave --skill research-goal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you run goal-driven finance research with clear criteria and verifiable evidence, while preventing the workflow from being used for live trading or execution.

Core Features & Use Cases

  • Goal tracking with acceptance criteria: Define what “supported” means before drawing conclusions.
  • Evidence-first progress: Add audited evidence after each research step (data lookup, backtest, reading, web sources).
  • Safety boundary for trading: Explicitly research-only—never instructs trade placement, submission, or execution.

Quick Start

Use the research-goal skill to track a research objective like “Compare strategy A vs strategy B for volatility regimes” and keep working until each criterion has verified evidence.

Frequently Asked Questions about research-goal

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I track finance research goals with auditable evidence across multiple steps?▼

Finance research workflow structures multi-step tasks around explicit goals and acceptance criteria, recording audited evidence after each step. It ensures conclusions remain fully supported across multiple turns without live-trading actions.

What is the best way to manage a long-running backtesting comparison without execution actions?▼

Managing a backtesting comparison requires setting a research-only goal and linking evidence to criteria. The workflow explicitly prevents live trade placement or execution, keeping the focus strictly on verifiable research conclusions.

How does evidence tracking work for multi-turn finance research?▼

Evidence tracking works by linking each data lookup, backtest, or reading to predefined acceptance criteria. You add audited evidence after every research step, ensuring final conclusions are fully supported before finalizing the goal status.

Can I use this workflow for live trading or placing orders?▼

No, this workflow cannot be used for live trading or placing orders. It maintains an explicit non-advice boundary and is strictly research-only, never instructing trade placement, submission, or execution.

When should I finalize a research goal as blocked or insufficient evidence?▼

You should finalize a research goal as blocked or insufficient evidence when criteria cannot be met with verified data. Finalizing the status using complete, blocked, insufficient evidence, or cancelled ensures the research outcome is properly documented.

Related Skills

Explore More Finance & Accounting Skills→
blockscoutblockscout
229

research-scope

Clarify codebase topics through guided discussion and propose a research-note outline.

Official
Advanced
hxhyyyhxhyyy

research-goal

Tracks research objectives, acceptance criteria, and evidence verification for financial analysis.

Community
Advanced
Yangel-hideYangel-hide

oss-forensics

Correlate evidence from GitHub, web archives, and CI/CD data to investigate supply chain security incidents.

Community
Advanced
OrestesKOrestesK
2

goal-crafter

Craft a paste-ready Pi /goal command from session context and repository evidence.

Community
Advanced