What is skill-idea-miner?

A workflow that reads Claude Code session logs, which are records of earlier coding-agent conversations, and extracts possible ideas for new skills. It scores those ideas and keeps a prioritized backlog for later generation.

Use it for weekly or manual mining of session logs, previewing possible skill ideas, scoring existing candidates, and maintaining a backlog.

It helps turn repeated needs from past coding work into organized candidates instead of relying on memory or reviewing every session manually. Full scoring requires the Claude CLI; a dry run can preview candidates.

skill-idea-miner — Skill for Claude Code and Codex by BaggaT236

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add BaggaT236/AI-Trading-Skills --skill skill-idea-miner

Clone the repo

git clone --depth 1 https://github.com/BaggaT236/AI-Trading-Skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/baggat236/ai-trading-skills/skill-idea-miner/github.svg)](https://agentmods.dev/skills/baggat236/ai-trading-skills/skill-idea-miner)

Your own site

<a href="https://agentmods.dev/skills/baggat236/ai-trading-skills/skill-idea-miner"><img src="https://agentmods.dev/badge/skills/baggat236/ai-trading-skills/skill-idea-miner/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/baggat236/ai-trading-skills/skill-idea-miner"><img src="https://agentmods.dev/badge/skills/baggat236/ai-trading-skills/skill-idea-miner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 976 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin 100% copy Near-identical to another mod in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00039	$0.00976
Opus 5	$0.00019	$0.00488
Sonnet 5	$0.00008	$0.00195
Haiku 4.5	$0.00004	$0.00098

Measured 12d ago against content hash 34c0ecda26c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

skill-idea-miner scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 6 executable files (scripts/__init__.py, scripts/mine_session_logs.py, scripts/score_ideas.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

100% identical to skill-idea-miner — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/skill-idea-miner/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Idea Miner

Automatically extract skill idea candidates from Claude Code session logs, score them for novelty, feasibility, and trading value, and maintain a prioritized backlog for downstream skill generation.

When to Use

Weekly automated pipeline run (Saturday 06:00 via launchd)
Manual backlog refresh: python3 scripts/run_skill_generation_pipeline.py --mode weekly
Dry-run to preview candidates without LLM scoring

Prerequisites

Python 3.10+ with pyyaml package
Claude CLI installed and authenticated (claude --version to verify)
Session logs in ~/.claude/projects/<project>/ (created automatically by Claude Code)
No API keys required (uses Claude CLI for LLM calls)

Workflow

Quick Start

# Dry-run: preview mined candidates without LLM scoring
python3 scripts/mine_session_logs.py --dry-run --output-dir reports/

# Full mining with scoring (requires Claude CLI)
python3 scripts/mine_session_logs.py --output-dir reports/

# Score existing candidates
python3 scripts/score_ideas.py \
  --candidates reports/raw_candidates.yaml \
  --output-dir logs/

Stage 1: Session Log Mining

Enumerate session logs from allowlist projects in ~/.claude/projects/
Filter to past 7 days by file mtime, confirm with timestamp field
Extract user messages (type: "user", userType: "external")
Extract tool usage patterns from assistant messages
Run deterministic signal detection:
- Skill usage frequency (skills/*/ path references)
- Error patterns (non-zero exit codes, is_error flags, exception keywords)
- Repetitive tool sequences (3+ tools repeated 3+ times)
- Automation request keywords (English and Japanese)
- Unresolved requests (5+ minute gap after user message)
Invoke Claude CLI headless for idea abstraction
Output raw_candidates.yaml

Stage 2: Scoring and Deduplication

Load existing skills from skills/*/SKILL.md frontmatter
Deduplicate via Jaccard similarity (threshold > 0.5) against:
- Existing skill names and descriptions
- Existing backlog ideas
Score non-duplicate candidates with Claude CLI:
- Novelty (0-100): differentiation from existing skills
- Feasibility (0-100): technical implementability
- Trading Value (0-100): practical value for investors/traders
- Composite = 0.3 * Novelty + 0.3 * Feasibility + 0.4 * Trading Value
Merge scored candidates into logs/.skill_generation_backlog.yaml

Read the full file on GitHub · 109 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 109 lines · 39 tokens per session scan A 34c0ecda26c4

Subscribe to this mod's changes

skill-idea-miner is a skill published in the GitHub repository BaggaT236/AI-Trading-Skills (121 stars, last pushed 8d ago), licensed MIT. It adds 39 tokens to every session and 976 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to skill-idea-miner, differing in 0 lines, and is treated as a copy.

Building agents agent-skills ai-agent ai-trading claude-trading trading-agent trading-agent-vn

ib-pmcc-advisor

Analyze PMCC (Poor Man's Covered Call / diagonal spread) positions from IB portfolio. For each diagonal spread, reports short leg risk (delta, IV, assignment probability), daily P&L projections, top-3 roll candidates, and a side-by-side comparison table. Requires TWS or IB Gateway running locally.

staskh/trading_skills · 71 tokens

scanner-pmcc

Scan stocks for Poor Man's Covered Call (PMCC) suitability. Analyzes LEAPS and short call options for delta, liquidity, spread, IV, yield, trend direction, and earnings proximity. Use when user asks about PMCC candidates, diagonal spreads, or LEAPS strategies.

staskh/trading_skills · 63 tokens

ib-stop-loss

Downside stop-loss management for PMCC, naked LEAPS, and stock positions in IB. Computes stop prices, detects alerts, and places conditional combo orders. Dry-run by default. Requires TWS or IB Gateway running locally.

staskh/trading_skills · 50 tokens

ib-trailing-stop

Server-side trailing stop management for stocks and naked LEAPS in IB. Places native TRAIL orders that auto-ratchet the stop as price climbs. Dry-run by default. Requires TWS or IB Gateway running locally.

staskh/trading_skills · 49 tokens

stock_analyzer

A stock and market analysis skill that returns structured information about trends, prices, news, risks, catalysts, and possible trading plans.

EthanAlgoX/LLM-TradeBot · 27 tokens

ib-find-short-roll

Find roll options for existing short positions OR find best covered call/put to open against long stock. Use when user asks about rolling shorts, finding roll candidates, writing covered calls, or managing option positions. Requires TWS or IB Gateway running locally.

staskh/trading_skills · 55 tokens