apex-methodology
SkillProductivityapex-methodology is a skill that gives your AI one consistent way to begin development work. Once added, it kicks in whenever you start a feature, bug fix, refactor, or hotfix, so every task begins with the same method instead of a different approach each time.
Available today. Use it from your connected AI after setup.
No other account needed.
After adding the skill, describe your task in your own words — implement, build, fix, add a feature, or refactor — and your AI will begin the work using the methodology from the first step.
Then ask your AI: use the apex-methodology skill
What your AI can do with it
- Begin any feature, bug fix, refactor, or hotfix with a consistent method
- Recognize requests like implement, create, build, fix, or develop and start work with the methodology applied
- Apply the same starting approach no matter how you describe the task
- Give every development task a predictable first step
What this skill tells your AI
The instructions your AI receives, as published by fusengine/agents in plugins/ai-pilot/skills/apex-methodology/SKILL.md and read by ahel’s review.
It enforces the project's hard constraints throughout: files under 100 lines (split at 90), interfaces kept out of component files, SOLID principles, and a mandatory sniper pass after every Edit/Write (blocked by PostToolUse hooks until it runs). Three modes control how much is automatic: --auto (default, no prompts), --manual (step-by-step confirmation), and --skip-elicit (bypasses the self-review phase).
Current Task: $ARGUMENTS
APEX Methodology Skill
Analyze → Plan → Execute → eLicit → eXamine
Complete development workflow for features, fixes, and refactoring.
Step 0: Initialize Tracking (MANDATORY FIRST ACTION)
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.
Workflow Overview
┌─────────────────────────────────────────────────────────────────┐
│ 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 │
└─────────────────────────────────────────────────────────────────┘
Skills Integration
| 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 References
| 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 |
Core Rules
File Size (ABSOLUTE)
🚨 STOP at 90 lines → Split immediately
❌ NEVER exceed 100 lines
📊 Target: 50-80 lines per file
Interface Location
✅ src/interfaces/ (global)
✅ src/types/ (type definitions)
✅ Contracts/ (PHP/Laravel)
❌ NEVER in component files
Agent Usage
01-analyze: explore-codebase + research-expert (PARALLEL)
04-validate: sniper (MANDATORY after ANY change)
NEVER
❌ 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)
Detailed References (Load on Demand)
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 directories
Signals
- GitHub stars
- 25
- Forks
- 4
- Last commit
- Sep 2026
Advanced
- Catalog kind
- skill
- Gateway key
apex-methodology- Source
- github.com/fusengine/agents