plugins/ai-pilot/skills/apex-methodology/SKILL.md
Systematic development workflow: Analyze → Plan → Execute → eLicit → eXamine. Use for ANY development task: features, bug fixes, refactoring, hotfixes. Triggers: "implement", "create", "build", "fix", "add feature", "refactor", "develop". Auto-detects project type (Laravel, Next.js, React, Swift) and loads framework-specific references. Enforces: files <100 lines, interfaces separated, SOLID principles, expert self-review, sniper validation. Modes: --auto (default), --manual, --skip-elicit
npx skillsauth add fusengine/agents apex-methodologyInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Current Task: $ARGUMENTS
Analyze → Plan → Execute → eLicit → eXamine
Complete development workflow for features, fixes, and refactoring.
BEFORE anything else, initialize APEX tracking — see references/init-tracking.md for the exact command.
This creates .claude/apex/task.json (documentation consultation status) and .claude/apex/docs/ (consulted documentation summaries). The PreToolUse hooks will BLOCK Write/Edit until documentation is consulted.
┌─────────────────────────────────────────────────────────────────┐
│ APEX WORKFLOW │
├─────────────────────────────────────────────────────────────────┤
│ 00-init-branch → Create feature branch │
│ 00.5-brainstorm → Design-first questioning (B) ← NEW │
│ 01-analyze-code → Understand codebase (A) │
│ 02-features-plan → Plan implementation (P) │
│ 03-execution → Write code with TDD (E) ← UPDATED │
│ 03.5-elicit → Expert self-review (L) │
│ 03.7-verification → Functional resolution check (V) ← NEW │
│ 04-validation → Verify quality (X) │
│ 05-review → Self-review │
│ 06-fix-issue → Handle issues │
│ 07-add-test → Write tests (TDD cycle) │
│ 08-check-test → Run tests │
│ 09-create-pr → Create Pull Request │
└─────────────────────────────────────────────────────────────────┘
| Phase | Skill | Invocation |
|-------|-------|------------|
| 00.5 | brainstorming | Questions → alternatives → design doc → approval |
| 03 | tdd | RED (test) → GREEN (code) → REFACTOR cycle |
| 03.7 | verification | Re-read request → check criteria → confirm resolution |
| Phase | File | Purpose |
| --- | --- | --- |
| 00 | references/00-init-branch.md | Create feature branch |
| 01 | references/01-analyze-code.md | Explore + Research (APEX A) |
| 02 | references/02-features-plan.md | TaskCreate planning (APEX P) |
| 03 | references/03-execution.md | Implementation (APEX E) |
| 03.5 | references/03.5-elicit.md | Expert self-review (APEX L) ← NEW |
| 04 | references/04-validation.md | sniper validation (APEX X) |
| 05 | references/05-review.md | Self-review checklist |
| 06 | references/06-fix-issue.md | Fix validation/review issues |
| 07 | references/07-add-test.md | Write unit/integration tests |
| 08 | references/08-check-test.md | Run and verify tests |
| 09 | references/09-create-pr.md | Create and merge PR |
🚨 STOP at 90 lines → Split immediately
❌ NEVER exceed 100 lines
📊 Target: 50-80 lines per file
✅ src/interfaces/ (global)
✅ src/types/ (type definitions)
✅ Contracts/ (PHP/Laravel)
❌ NEVER in component files
01-analyze: explore-codebase + research-expert (PARALLEL)
04-validate: sniper (MANDATORY after ANY change)
❌ Skip explore-codebase or research-expert
❌ Assume API syntax without verification
❌ Create files >100 lines
❌ Put interfaces in component files
❌ Skip sniper after changes
❌ Merge without tests
❌ Large PRs (>400 lines)
references/init-tracking.md — Load when running Step 0 (the exact tracking-init command)references/phases-explained.md — Load when you need the full explanation of each APEX phase (A/P/E/V/X)references/branching-strategy.md — Load when creating or naming branchesreferences/commit-conventions.md — Load when writing commit messagesreferences/quick-start-flows.md — Load when you need the full step-by-step Standard Feature / Bug Fix / Hotfix flowsreferences/flow-diagram.md — Load when you want the full ASCII flow diagram of the workflowreferences/validation-requirements.md — Load when running the pre-PR / code-quality checklistreferences/pr-guidelines.md — Load when writing a PR title or descriptionreferences/language-detection.md — Load when auto-detecting project type or navigating framework-specific reference directoriestesting
Copy self-audit and ban-lists — filler verbs/hype adjectives, slop placeholder names, fake-precise numbers, Title Case headlines, humor in error copy ('Oops!'), em-dash crutch, one copy register per page.
development
Logged-in web apps — dashboards, auth flows, settings, onboarding, data tables, command palettes, modals, toasts. Register `product`: density and glance-speed over marketing polish, no hero/CTA-tricks, every data surface covers empty/loading/error explicitly, tables and dataviz follow preattentive-processing rules.
development
Marketing sites, landing pages, campaign pages — register `brand` (design IS the product). Structure comes from the register's POV + a macrostructure pick, never from copying an inspiration site's section flow. Hero discipline, deviated section order, asymmetric grids, and a silhouette lookalike-test gate before ship.
development
Token-strategy core — OKLCH color rules, neutral tinting, accent-commitment levels, type scale, 8pt spacing grid, touch targets, and the canonical output format of design-system.md (the file the harness gates on). This is routing step 1 of design-method/SKILL.md — read it before design-web/design-webapp/design-ios/design-android, before picking or auditing a single color/type/spacing value.