agentleFS
FaisalAlqarniFaisalAlqarni/sp-ecc/skills/extract-patterns/SKILL.md

extract-patterns

Skill9 starsChanged 9 months agoMITView on GitHub

Extract learned patterns from session - invoked automatically by finishing-a-development-branch or manually anytime

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use /sp-ecc:learn command to extract patterns:

    line 22

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Extract Patterns

Overview

Wraps ECC's continuous-learning-v2 system to extract and save useful patterns from development sessions.

Auto-invoked by: finishing-a-development-branch skill Can be invoked: Manually anytime to save learning Purpose: Build institutional knowledge over time

Announce at start: "I'm using the extract-patterns skill to learn from this session."

The Process

Step 1: Invoke Pattern Extraction

Use /sp-ecc:learn command to extract patterns:

/sp-ecc:learn

This analyzes the current session for:

  • Successful problem-solving approaches
  • Useful code patterns
  • Effective debugging strategies
  • Language/framework insights
  • Common mistake avoidance

Step 2: Review Extracted Patterns

The learning system will show patterns with confidence scores.

Review criteria:

  • Is the pattern actually useful?
  • Is the confidence score appropriate?
  • Would this help in future sessions?

Step 3: Save to Instinct System

Patterns are automatically saved to the instinct system.

View saved patterns:

/sp-ecc:instinct-status

Step 4: Optional - Evolve into Skills

For mature patterns (high confidence, multiple uses):

/sp-ecc:evolve

This clusters related patterns into reusable skills.

Integration with Workflow

Auto-Invoked:

finishing-a-development-branch:
1. Verify tests pass
2. Sync documentation
3. Extract patterns (THIS SKILL) ← Auto-invoked
4. Generate changelist
5. Present options

Manual Invocation:

Any time during development:
- "Can you extract patterns from what we just did?"
- Skill invoked
- Patterns saved for future

Opt-Out

To disable auto-invocation in finishing workflow:

See: docs/integration/OPT-OUT.md

Exporting/Importing Patterns

Export patterns to file:

/sp-ecc:instinct-export

Import patterns from file:

/sp-ecc:instinct-import

Useful for:

  • Sharing patterns across teams
  • Backing up learned knowledge
  • Transferring patterns between projects

Quick Reference

CommandPurpose
/sp-ecc:learnExtract patterns from session
/sp-ecc:instinct-statusView saved patterns
/sp-ecc:instinct-exportExport to file
/sp-ecc:instinct-importImport from file
/sp-ecc:evolveCluster patterns into skills

Remember

  • Patterns accumulate over time
  • Higher confidence = more proven
  • Export periodically for backup
  • Share successful patterns with team

Remember: This builds institutional knowledge. The more you use it, the smarter the system becomes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.