mcpField
L
learned-skills-index

learned-skills-index

github.com/tony363Agent workflows2093 installsUpdated 30w ago
Repository

About learned-skills-index

learned-skills-index documents skills extracted from successful Claude Code execution sessions. It tracks validation status and provenance, while enabling relevant skills to be retrieved for future tasks.

Key features

  1. 01Records extracted skill patterns
  2. 02Tracks pending, promoted, and archived status
  3. 03Applies quality thresholds for promotion
  4. 04Retrieves skills by task and context
  5. 05Stores provenance for audit and rollback

Use cases

  1. 01Find learned patterns for a new task
  2. 02Review whether a skill passed promotion criteria
  3. 03Audit the origin of an applied skill

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/tony363/superclaude --skill learned-skills-index

After installing, type/learned-skills-indexin Claude Code to confirm it loaded.

Details

From the project README

Learned Skills Index

This directory contains skills that have been automatically extracted from successful execution sessions. These skills represent patterns that led to quality improvements and are available for retrieval in future tasks.

How Skills Are Learned

  1. Execution: Claude Code runs a task with --loop enabled
  2. Feedback Collection: Each iteration's quality scores and improvements are recorded
  3. Pattern Extraction: Successful patterns are extracted from quality-improving iterations
  4. Skill Generation: Patterns are compiled into a learnable skill definition
  5. Promotion Gate: Skills must meet quality thresholds before promotion

Skill Status

StatusMeaning
PendingSkill extracted but not yet promoted (needs more validation)
PromotedSkill has been validated and can be applied to new tasks
ArchivedSkill deprecated or superseded by newer learning

Quality Thresholds for Promotion

  • Minimum quality score: 85.0
  • Minimum successful applications: 2
  • Minimum success rate: 70%

Directory Structure

learned/
├── SKILL.md                    # This index file
├── learned-backend-auth/       # Example learned skill
│   ├── SKILL.md               # Skill definition
│   └── metadata.json          # Machine-readable metadata
└── learned-frontend-form/      # Another learned skill
    ├── SKILL.md
    └── metadata.json

Integration

Learned skills are automatically retrieved based on:

  • Task description keywords
  • File types being modified
  • Domain context

To manually query learned skills:

from core.skill_persistence import retrieve_skills_for_task

skills = retrieve_skills_for_task(
    task_description="your task here",
    domain="backend"  # optional
)

Safety

All learned skills include full provenance:

  • Source session ID
  • Source repository
  • Timestamp of learning
  • Quality progression

This enables rollback and audit of any behavioral changes from learned skills.

Comments

Markdown supported