skill-idea-miner

Mine Claude Code session logs to extract and prioritize skill idea candidates.

Updated Apr 17, 2026
One-click install
npx skills add https://github.com/pasie15/claude-trading-skills-marketplace --skill skill-idea-miner-pasie15
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-idea-miner
Source: https://github.com/pasie15/claude-trading-skills-marketplace/tree/main/plugins/trading-dividend-investing/skills/skill-idea-miner
Command: npx skills add https://github.com/pasie15/claude-trading-skills-marketplace --skill skill-idea-miner-pasie15

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the tedious, manual process of reading Claude Code session logs to discover, abstract, and prioritize new skill ideas so maintainers can continuously grow a backlog of implementable trading skills without sifting through sessions by hand.

Core Features & Use Cases

  • Session log mining: Enumerates and scans recent Claude Code session files to extract user messages, tool usage, and timing signals.
  • Deterministic signal detection & deduplication: Detects skill-usage patterns, errors, repetitive workflows, automation requests, and unresolved messages, then deduplicates candidates against existing skills using Jaccard similarity.
  • LLM abstraction and scoring: Invokes Claude CLI to abstract user requests into candidate ideas, scores novelty/feasibility/trading value, and merges results into a prioritized backlog for downstream skill generation.
  • Use case: Run as a weekly pipeline to automatically convert a week's worth of developer sessions into a ranked list of implementable skill ideas for the trading skills repository.

Quick Start

Use the skill-idea-miner to scan the last seven days of Claude Code session logs, extract candidate ideas, score and deduplicate them, and append the prioritized entries to the skill generation backlog.

Frequently Asked Questions about skill-idea-miner

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

FAQPage Schema
How do I extract skill ideas from Claude Code session logs automatically?

Skill idea mining parses Claude Code session logs to detect repetitive tool sequences, errors, and direct automation requests from user messages. It converts these recurring pain points into abstracted, implementable skill candidates.

How does deduplication work when generating new skill ideas from logs?

Deduplication uses Jaccard similarity to compare newly mined candidates against existing skills. This matching process prevents duplicate backlog entries by identifying overlapping functionality before merging prioritized results.

Can I run session log mining as a weekly automated pipeline?

Yes, session log mining applies to weekly automated pipelines and manual runs. It scans recent Claude Code session files to extract, score, and append prioritized skill ideas to the generation backlog.

What scoring criteria are used to prioritize mined skill candidates?

Mined skill candidates are scored by novelty, feasibility, and trading value using LLM-based abstraction via Claude CLI. These individual metrics combine into a composite score that determines the priority ranking in the backlog.

What file formats does the idea mining process output for the backlog?

The idea mining process writes raw_candidates.yaml and a merged backlog file. These YAML formats store extracted candidates and their composite scores for downstream skill generation pipelines.