compound-capture

Name: compound-capture
Availability: InStock
Author: Thompson

Extract durable lessons from sprint outcomes with artifact path provenance.

28|2|Updated Feb 5, 2026

Search Tags:#learning #memory #traceability #docs #artifact #sprint #compound

Ready to run

npx skills add https://github.com/thompson0012/agents-stack --skill compound-capture-thompson0012

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: compound-capture
Source: https://github.com/thompson0012/agents-stack/tree/main/templates/.agents/skills/using-agents-stack/compound-capture
Command: npx skills add https://github.com/thompson0012/agents-stack --skill compound-capture-thompson0012

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Compound Capture skill enables teams to extract and preserve durable lessons from sprint outcomes, ensuring cross-sprint memory survives state reconciliation and compounding work without reintroducing noise.

Core Features & Use Cases

Patch durable learning into shared memory, linked records, and stable references only when provenance is guaranteed by decisive sprint evidence.
Update docs/live/memory.md and docs/live/tracked-work.json to reflect verified outcomes while avoiding regressions in active sprint state.
Use after state-update to distill evidence into actionable guidance that informs future proposals, contracts, or design decisions.

Quick Start

Initiate a compound capture by running the compounding workflow on the queued feature indicated in docs/live/tracked-work.json.

Frequently Asked Questions about compound-capture

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

FAQPage Schema

How do I preserve cross-sprint learnings without reintroducing noise into active state?▼

To preserve cross-sprint learnings, extract evidence from sprint outcomes and patch durable lessons into shared memory only when provenance is guaranteed by decisive artifacts. This ensures reusable guidance survives state reconciliation without regressions.

What is the best way to link sprint outcomes to durable memory references?▼

The best way to link sprint outcomes to durable memory is to apply a durable-learning workflow that grounds lessons in decisive sprint evidence. You must reference the exact artifact paths proving provenance before updating memory or reference docs.

How do I distill evidence from tracked work into actionable guidance for future proposals?▼

You distill evidence into actionable guidance by identifying the queued feature in tracked-work.json and running a compounding workflow. This extracts verified outcomes into durable lessons that inform future contracts, proposals, or design decisions.

When should I update docs/live/memory.md to reflect sprint outcomes?▼

You should update docs/live/memory.md only after verifying that evidence supports a lasting, reusable lesson. This prevents active sprint state regressions while ensuring shared memory reflects proven, decisive sprint artifacts.

Can I capture durable lessons from sprint artifacts without affecting active sprint state?▼

Yes, you can capture durable lessons without affecting active sprint state by using a compounding workflow. It updates shared memory and linked records based on proven evidence while explicitly avoiding regressions in your current tracked work.

Why does cross-sprint memory require provenance from decisive artifacts?▼

Cross-sprint memory requires provenance from decisive artifacts to ensure lessons are grounded in verified evidence rather than noise. Referencing artifact paths proves the learning is lasting and reusable for future design decisions.