advise
Pre-work command that queries past learnings and leverages MCPs before starting a new task
Complete a task with 6 Gates verification, code review, and career value extraction
$ npx -y skills add DanielPodolsky/ownyourcode --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
/doneContext preview
What this command does when you run it.
Complete a task with 6 Gates verification, code review, and career value extraction
name: done description: Complete a task with 6 Gates verification, code review, and career value extraction allowed-tools: Read, Glob, Grep, Write, Edit, AskUserQuestion, Bash
> ⚠️ **PLAN MODE WARNING:** Toggle plan mode off before running this command (`shift+tab`). OwnYourCode commands don't work correctly with plan mode.
Complete a task with gate checks, senior-level code review, and career value extraction.
This command is run when the user finishes a task or feature. It performs: 1. **Gate Checks** — 6 Mentorship Gates verification 2. **Code Review** — FAANG-level feedback on their code 3. **Task Completion** — Update the dashboard (task done, DoD, phase status) 4. **Interview Story** — Extract STAR format story (if career_focus allows) 5. **Resume Bullet** — Draft action-impact bullet (if career_focus allows)
**Profile-Aware Behavior:**
---
Question: "What did you just finish?" Options: 1. A task from my active spec Description: Completing planned work 2. A bug fix Description: Fixed something that was broken 3. A feature (not specced) Description: Built something new 4. A refactor Description: Improved existing code
If from active spec, read the dashboard to understand context:
task in its `tasks[]` (match by `text`/`detail`, note its `id`)
---
Review what code was written:
# Recent commits git log --oneline -5 # Files changed git diff --name-only HEAD~1 # Or if uncommitted git status
Ask them to point to the key files:
> "Which files contain the main implementation?"
Read those files to understand what they built.
---
Before code review, run through the 6 Mentorship Gates. These ensure quality and understanding.
> "Before we review the code, let's run through the 6 Gates."
*Reference: `.claude/skills/gates/ownership/SKILL.md`*
> "Walk me through what this code does, step by step."
**Questions:** 1. "Why did you choose this approach? What alternatives did you consider?" 2. "If the requirements changed to [X], what would you modify?"
**Outcomes:**
*Reference: `.claude/skills/gates/security/SKILL.md`*
> "Where does user input enter this feature?" > "How is that input validated?"
**Check for:**
**Outcomes:**
*Reference: `.claude/skills/gates/error/SKILL.md`*
> "What happens if [main operation] fails?" > "What does the user see when an error occurs?"
**Check for:**
**Outcomes:**
*Reference: `.claude/skills/gates/performance/SKILL.md`*
> "What happens when there are 10,000 items?" > "How many database queries does this make?"
**Check for:**
**Outcomes:**
*Reference: `.claude/skills/gates/fundamentals/SKILL.md`*
> "Would a new developer understand this code?"
**Check for:**
**Outcomes:**
*Reference: `.claude/skills/gates/testing/SKILL.md`*
> "What tests prove this feature works?"
**Questions:** 1. "What tests did you write for this feature?" 2. "What edge cases do your tests cover?" 3. "If I broke [specific part], which test would catch it?"
**Check for:**
**Outcomes:**
**Note:** This gate issues WARNINGS only. The goal is to build the testing habit through encouragement, not enforcement.
┌─────────────────────────────────────────┐ │ GATE CHECK RESULTS │ ├─────────────────────────────────────────┤ │ 1. Ownership: ✅ PASS / 🛑 BLOCKED │ │ 2. Security: ✅ PASS / ⚠️ WARNING │ │ 3. Error: ✅ PASS / ⚠️ WARNING │ │ 4. Performance: ✅ PASS / ⚠️ WARNING │ │ 5. Fundamentals: ✅ PASS / 💡 SUGGEST │ │ 6. Testing: ✅ PASS / ⚠️ WARNING │ └─────────────────────────────────────────┘
**If BLOCKED on Gate 1:** Stop here. The junior must understand their code before proceeding.
**If WARNINGS exist:** Note them and incorporate into code review. The junior should address them.
**If only SUGGESTIONS:** Proceed to code review. These are polish, not blockers.
---
Perform a thorough code rev
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