advise
Pre-work command that queries past learnings and leverages MCPs before starting a new task
Post-work command that extracts learnings and updates the learning registry
$ npx -y skills add DanielPodolsky/ownyourcode --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/retroContext preview
What this command does when you run it.
Post-work command that extracts learnings and updates the learning registry
name: retro description: Post-work command that extracts learnings and updates the learning registry allowed-tools: Read, Glob, Grep, Write, Edit, AskUserQuestion, mcp__octocode__githubSearchCode, mcp__octocode__githubGetFileContent
> ⚠️ **PLAN MODE WARNING:** Toggle plan mode off before running this command (`shift+tab`). OwnYourCode commands don't work correctly with plan mode.
Extract learnings from completed work and persist them for future reference.
This command is run **after** completing work (typically after `/own:done`). It: 1. Reflects on what was learned 2. Documents patterns worth reusing 3. Records failures to avoid 4. Updates the learning registry 5. Generates skill files for significant learnings
> "The junior who documents their failures outgrows the senior who repeats them."
---
> "What did you just finish working on?"
If they just ran `/own:done`, reference that context.
Get:
---
Ask these questions to extract learnings:
> "What was the hardest part of this work?"
Looking for:
> "What do you know now that you didn't know before you started?"
Looking for:
> "Did you discover or use a pattern that worked well? Something you'd want to reuse?"
Looking for:
> "Did you make any mistakes or hit any walls? What went wrong before it went right?"
Looking for:
> "If you could go back and tell yourself one thing before starting this task, what would it be?"
This often captures the most actionable learning.
---
Based on their answers, categorize:
**Patterns** (reusable solutions):
**Failures** (anti-patterns):
**Insights** (general learnings):
---
**All learnings are stored GLOBALLY at `~/ownyourcode/learning/` to persist across projects.**
Create a pattern file at `~/ownyourcode/learning/patterns/[PatternName].md`:
--- name: [Pattern Name] description: [When to use this pattern] --- # [Pattern Name] **Learned:** 2026-01-01 **Domain:** [Domain] **Context:** [Brief context of when this was learned] ## When to Use [Situations where this pattern applies] ## The Pattern [Code example or description] ## Why It Works [Explanation of why this is effective] ## Watch Out For [Common mistakes or edge cases] ## Related - [Link to original task if applicable]
Create a failure doc at `~/ownyourcode/learning/failures/[Topic].md`:
# FAILURE: [Short Description] **Date:** 2026-01-01 **Domain:** [Domain] **Time Lost:** [Rough estimate] ## What Happened [Description of the failure] ## Root Cause [Why it happened] ## The Fix [How it was resolved] ## How to Avoid [What to do differently next time] ## Red Flags [Warning signs to watch for]
---
Append to `~/ownyourcode/learning/LEARNING_REGISTRY.md`:
### 2026-01-01: [Title] **Domain:** [Domain] **Type:** Pattern | Failure | Insight **Summary:** [One-line summary] **Key Insight:** [The main takeaway] **Location:** [Path to skill file or failure doc if created]
Also update the index tables at the top of the registry.
---
Based on accumulated learnings, assess growth:
┌─────────────────────────────────────────┐ │ COMPETENCY SNAPSHOT │ ├─────────────────────────────────────────┤ │ │ │ Total Patterns Documented: [X] │ │ Total Failures Documented: [Y] │ │ Total Insights Captured: [Z] │ │ │ │ Domains Explored: │ │ • Auth: ████████░░ (8 learnings) │ │ • Forms: ████░░░░░░ (4 learnings) │ │ • API: ██░░░░░░░░ (2 learnings) │ │ │ │ Current Level: ⭐⭐⭐ (Intermediate) │ │ │ │ "You're building a solid foundation. │ │ Keep documenting — this compounds." │ │ │ └─────────────────────────────────────────┘
---
┌─────────────────────────────────────────┐ │ RETROSPECTIVE COMPLETE │ ├─────────────────────────────────────────┤ │ │ │ Task: [Feature Name] │ │ Domain: [Domain] │ │ │ │ LEARNINGS CAPTURED │ │ ───────────────── │ │ ✅ Pattern: [Name] → saved to skills │ │ ⚠️ Failure: [Name] → documented │ │ 💡 Insight: "[Key insight]" │ │ │ │ GLOBAL REGISTRY UPDATED │ │ ───────────────── │ │ ~/ownyourcode/learning/LEARNING_REGISTRY│ │ │ │ NEXT TIME │ │ ───────────────── │ │ Run /own:advise before your next task │ │
Claude Code workflow for AI-mentored development. Work efficiently with Spec-Driven Development and the 6 Gates. Built to fight cognitive offloading — for developers using AI to grow and maintain ownership.
Repo: DanielPodolsky/ownyourcode
Pre-work command that queries past learnings and leverages MCPs before starting a new task
Guide the junior through writing documentation for their project or code
Complete a task with 6 Gates verification, code review, and career value extraction