code-autopsy

🌐 English | 한국어 | 日本語 | 中文 | Español

sovereign-skills v6.2

12 skills for the full Claude Code project lifecycle — from setup to daily workflow to code review to session management. Each skill is useful standalone; the full sequence covers everything.

What changed in v6.2: New: code-autopsy — 12Q quantified code review with 4-axis scoring, severity anchors, deployment verdict, and CapCode/CEF meta-detection. Also new: stepback — one-shot perspective reset. All 10 existing skills upgraded.

---

Quick Start

New project (15 min):

/project-init       →  CLAUDE.md + ROADMAP + .gitignore + .env.example
/setup              →  rules/ + hooks + memory/ + agent routing + team
then daily:
  /session-start      at the start of every session
  /scope              before each feature (define IN/OUT/exit criteria)
  /freeze             before implementation (declare editable zone)
  /goal-lock          lock the goal, enforce PLAN→DO→VERIFY loop
  /stepback           anytime — zoom out, check direction, 10 lines
  /code-autopsy       12Q code review with severity scoring + verdict
  /pre-push           before each push (secrets scan + agent review)
  /session-checkpoint at the end of every session

Existing project (5 min):

/project-check      →  Score across 4 dimensions + gap list by severity
/collab-audit       →  14-section AI collaboration diagnostic from your work patterns

---

Skills

Setup Phase

Skill	What it does
project-init	Interview-based project scaffolding — generates CLAUDE.md, ROADMAP, .gitignore, .env.example from decisions, not templates
setup	Claude Code infrastructure + agent team — rules, hooks, memory, routing, and agent installation in one guided flow

Daily Workflow

Skill	What it does
scope	Define what's IN, what's OUT, and exit criteria before implementation. Quick mode (3 questions) or Full mode (layered spec)
freeze	Declare the editable zone — everything outside is frozen. Prevents scope creep during implementation
goal-lock	Agent discipline engine — locks the goal, enforces PLAN→DO→VERIFY→FINALIZE→OUTPUT loop, detects 11 success masquerading patterns
pre-push	Mandatory pre-push pipeline — secrets scan (12 patterns), build/test, lint, parallel AI code review. Blocks push on Critical/High findings

Perspective

Skill	What it does
stepback	New. One-shot perspective reset — generates 1 abstract reframing question + 3 quick checks (scope drift, side effects, better approach) in under 10 lines. Use anytime during work

Session Management

Skill	What it does
session-start	Load handoff from last session, review lessons, health check, output "ready" signal with priority action
session-checkpoint	Save session context before compact — handoff file, memory updates, lesson extraction, reflexion (what went wrong, what to do differently)

Code Review

Skill	What it does
code-autopsy	New. 12Q quantified code review — 4-axis scoring (Security/Stability/Robustness/Operability), severity anchors, deployment verdict (SHIP/FIX/RISKY/BLOCK), factuality gate. Backed by empirical evidence (Johnson 2019, Parnas 1972). Also works as a standalone prompt in any LLM

Quality

Skill	What it does
project-check	Scan existing project across 4 dimensions: Infrastructure, Security, Quality, Harness. Gaps ordered by severity
collab-audit	14-section AI collaboration audit — analyzes your actual work patterns (not surveys) to generate behavioral profile, blind spots, and growth direction

---

Lifecycle Flow