codify-learning

Transform ephemeral learnings into durable system improvements.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "codify-learning" with this command: npx skills add phrazzld/claude-config/phrazzld-claude-config-codify-learning

/codify-learning

Transform ephemeral learnings into durable system improvements.

Philosophy

Default codify, justify exceptions. Every correction, feedback, or "I should have known" moment represents a gap in the system. Codification closes that gap.

The "3+ occurrences" threshold is a myth - we have no cross-session memory. If you learned something, codify it.

Process

  1. Identify Learnings

Scan the session for:

  • Errors encountered and how they were fixed

  • PR feedback received

  • Debugging insights ("the real problem was...")

  • Workflow improvements discovered

  • Patterns that should be enforced

  1. Brainstorm Codification Targets

For each learning, consider:

  • Hook - Should this be guaranteed/blocked? (most deterministic)

  • Lint rule - Can a lint rule catch this at edit time? → invoke /guardrail

  • Agent - Should a reviewer catch this pattern?

  • Skill - Is this a reusable workflow?

  • CLAUDE.md - Is this philosophy/convention?

Choose the target that provides the most leverage. Hooks > Lint rules > Agents > Skills > CLAUDE.md for enforcement. Skills > CLAUDE.md for workflows.

Lint rules are ideal for: import boundaries, naming conventions, deprecated API usage, auth enforcement, architectural layering violations. If the pattern can be expressed as "this code shape should never/always appear," it's a lint rule.

  1. Implement

For each codification:

  • Read the target file

  • Add the learning in appropriate format

  • Wire up if needed (hooks need settings.json entry)

  • Verify no duplication

  1. Report

CODIFIED:

  • [learning] → [file]: [summary of change]

NOT CODIFIED:

  • [learning]: [justification - must be specific]

Anti-Patterns

❌ "No patterns detected" - One occurrence is enough ❌ "First time seeing this" - No cross-session memory exists ❌ "Seems too minor" - Minor issues compound into major friction ❌ "Not sure where to put it" - Brainstorm, ask, don't skip ❌ "Already obvious" - If it wasn't codified, the system didn't know it

See CLAUDE.md "Continuous Learning Philosophy" for valid exceptions and the full codification philosophy.

See Also

/done — Full session retrospective (subsumes codification as one step in a broader process: went-well, friction, bugs, codify, report).

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

pencil-renderer

No summary provided by upstream source.

Repository SourceNeeds Review
General

ui-skills

No summary provided by upstream source.

Repository SourceNeeds Review
General

llm-gateway-routing

No summary provided by upstream source.

Repository SourceNeeds Review
General

documentation-standards

No summary provided by upstream source.

Repository SourceNeeds Review