Index of every page on this site: llms.txt
All skills
tradermonty avatar

/skill-idea-miner

@f95e770
Run it yourself

Mine Claude Code session logs for skill idea candidates. Use when running the weekly skill generation pipeline to extract, score, and backlog new skill ideas from recent coding sessions.

Use this Skill: https://skilld.dev/gh/tradermonty/claude-trading-skills/skill-idea-miner

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈51 tokens for metadata: the name and description. ≈960 when used: this file. ≈1.6k more on demand in 1 file.

Description uses 2.6% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈205 characters, or 2.6%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

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

Run these from the repository root, so the backlog is the one the pipeline reads.

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

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

# Score existing candidates
python3 skills/skill-idea-miner/scripts/score_ideas.py \
  --candidates reports/raw_candidates.yaml \
  --backlog logs/.skill_generation_backlog.yaml

Stage 1: Session Log Mining

  1. Enumerate session logs from allowlist projects in ~/.claude/projects/
  2. Filter to past 7 days by file mtime, confirm with timestamp field
  3. Extract user messages (type: "user", userType: "external")
  4. Extract tool usage patterns from assistant messages
  5. 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)
  6. Invoke Claude CLI headless for idea abstraction
  7. Output raw_candidates.yaml

Stage 2: Scoring and Deduplication

  1. Load existing skills from skills/*/SKILL.md frontmatter
  2. Deduplicate via Jaccard similarity (threshold > 0.5) against:
    • Existing skill names and descriptions
    • Existing backlog ideas
  3. 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
  4. Merge scored candidates into logs/.skill_generation_backlog.yaml

Output Format

raw_candidates.yaml

generated_at_utc: "2026-03-08T06:00:00Z"
period: {from: "2026-03-01", to: "2026-03-07"}
projects_scanned: ["claude-trading-skills"]
sessions_scanned: 12
candidates:
  - id: "raw_2026w10_001"
    title: "Earnings Whispers Image Parser"
    source_project: "claude-trading-skills"
    evidence:
      user_requests: ["Extract earnings dates from screenshot"]
      pain_points: ["Manual image reading"]
      frequency: 3
    raw_description: "Parse Earnings Whispers screenshots to extract dates."
    category: "data-extraction"

Backlog (logs/.skill_generation_backlog.yaml)

updated_at_utc: "2026-03-08T06:15:00Z"
ideas:
  - id: "idea_2026w10_001"
    title: "Earnings Whispers Image Parser"
    description: "Skill that parses Earnings Whispers screenshots..."
    category: "data-extraction"
    scores: {novelty: 75, feasibility: 60, trading_value: 80, composite: 73}
    status: "pending"

Resources

  • references/idea_extraction_rubric.md — Signal detection criteria and scoring rubric
  • scripts/mine_session_logs.py — Session log parser
  • scripts/score_ideas.py — Scorer and deduplicator

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert8d5 checks · Risk SAFE
  • Gen Agent Trust Hub8d

    The skill mines local Claude Code session logs to generate skill ideas. It accesses sensitive user history and uses the Claude CLI to process it. While these actions are central to its purpose, they create a risk of indirect prompt injection and expose session data to the LLM processor.

  • Socket8d

    No alerts

  • Snyk8d

    Risk: MEDIUM · 1 issue

  • Runlayer8mo

    4/7 files flagged

  • ZeroLeaks7mo

    Score: 93/100 · 2 sections analyzed

Signed by skilld at f95e770. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated last week

README badge

README badge for tradermonty/claude-trading-skills/skill-idea-miner