菜单
Systematic implementation using APEX methodology (Analyze-Plan-Execute-eXamine) with parallel agents, self-validation, and optional adversarial review. Use when implementing features, fixing bugs, or making code changes that benefit from structured workflow.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | apex |
| description | Systematic implementation using APEX methodology (Analyze-Plan-Execute-eXamine) with parallel agents, self-validation, and optional adversarial review. Use when implementing features, fixing bugs, or making code changes that benefit from structured workflow. |
| argument-hint | [-a] [-x] [-s] [-t] [-v] [-b] [-pr] [-i] [-m] [-r <task-id>] <task description> |
<quick_start>
/apex add authentication middleware # Basic
/apex -a -s implement user registration # Autonomous + save
/apex -a -x -s fix login bug # With adversarial review
/apex -a -v implement user dashboard # With feature verification
/apex -a -m implement full auth system # Agent Teams (parallel)
/apex -a -x -s -t -v add auth middleware # Full workflow with tests + verify
/apex -a -pr add auth middleware # With PR creation
/apex -r 01-auth-middleware # Resume previous task
/apex -e add auth middleware # Economy mode (save tokens)
/apex -i add auth middleware # Interactive flag config
</quick_start>
**Enable (lowercase ON) / Disable (UPPERCASE OFF):**| ON | OFF | Long | Description |
|---|---|---|---|
-a | -A | --auto | Skip confirmations, auto-approve |
-x | -X | --examine | Adversarial code review |
-s | -S | --save | Save outputs to .claude/output/apex/ |
-t | -T | --test | Include test creation + runner |
-v | -V | --verify | Launch app and verify feature works |
-e | -E | --economy | No subagents, save tokens |
-b | -B | --branch | Verify not on main, create branch |
-pr | -PR | --pull-request | Create PR at end (enables -b) |
-i | --interactive | Configure flags via menu | |
-k | -K | --tasks | Task breakdown with dependencies |
-m | -M | --teams | Agent Teams parallel execution (enables -k) |
-r | --resume | Resume from previous task ID |
Parsing: Defaults from steps/step-00-init.md, flags override, remainder = {task_description}, ID = NN-kebab-case.
<step_files>
| Step | File | Purpose |
|---|---|---|
| 00 | steps/step-00-init.md | Parse flags, initialize state |
| 00b | steps/step-00b-save.md | Setup save output structure (if -s) |
| 00b | steps/step-00b-branch.md | Git branch setup (if -b) |
| 00b | steps/step-00b-economy.md | Economy mode overrides (if -e) |
| 00b | steps/step-00b-interactive.md | Interactive flag config (if -i) |
| 01 | steps/step-01-analyze.md | Smart context gathering |
| 02 | steps/step-02-plan.md | File-by-file plan + TaskList |
| 02b | steps/step-02b-tasks.md | Task breakdown (if -k/-m) |
| 03 | steps/step-03-execute.md | Todo-driven implementation |
| 03t | steps/step-03-execute-teams.md | Agent Team execution (if -m) |
| 04 | steps/step-04-validate.md | Self-check and validation |
| 05 | steps/step-05-examine.md | Adversarial code review |
| 06 | steps/step-06-resolve.md | Finding resolution |
| 07 | steps/step-07-tests.md | Test analysis and creation |
| 08 | steps/step-08-run-tests.md | Test runner loop |
| 09 | steps/step-09-finish.md | Create pull request |
| 10 | steps/step-10-verify.md | Launch & verify feature |
</step_files>
<state_variables>
| Variable | Type | Set by |
|---|---|---|
{task_description} | string | step-00 |
{feature_name} | string | step-00 |
{task_id} | string | step-00 / step-00b-save |
{acceptance_criteria} | list | step-01 |
{auto_mode} | boolean | step-00 |
{examine_mode} | boolean | step-00 |
{save_mode} | boolean | step-00 |
{test_mode} | boolean | step-00 |
{verify_mode} | boolean | step-00 |
{economy_mode} | boolean | step-00 |
{branch_mode} | boolean | step-00 |
{pr_mode} | boolean | step-00 |
{tasks_mode} | boolean | step-00 |
{teams_mode} | boolean | step-00 |
{output_dir} | string | step-00b-save |
{branch_name} | string | step-00b-branch |
</state_variables>
<execution_rules>
{save_mode} = true (each step appends to its file)/Users/melvynx/.agents/skills/find-docs/SKILL.md for current technical docs, and /Users/melvynx/.agents/skills/exa-search/SKILL.md for broader web research or cited sources
</execution_rules><entry_point>
FIRST ACTION: Load steps/step-00-init.md
</entry_point>
Create Claude-style local HTML artifacts under global ~/.agents/artifacts. Use for artifact requests, variations/options croquis, feature plans, thinking docs, prototypes, visualizations, dashboards, diagrams, or substantial reusable content. Pair with use-style.
Apply named visual style guides to landing pages, app shells, and UI. Use for $use-style, /useskill, list styles, or styles like ios-app, grid, vercel, black-grid, stripe, linear, raycast, gumroad, dusk, or luma.
Expert guidance for creating, building, and using Claude Code agents and the Task tool. Use when working with agents, setting up agent configurations, understanding how agents work, or using the Task tool to launch specialized agents.
Interact with App Store Connect via the asc CLI - apps, builds, TestFlight, beta testers, reviews, sales/analytics, metadata, IAP, signing, submissions. Use for "check my app", "App Store Connect", "TestFlight status", "app review", "my app sales", or "asc".
Set up per-worktree environments for Claude Code, Cursor, or Codex. Use for worktree-ready repos, IDE environment config, worktree-up/down scripts, or dev.sh wiring.
Implement one focused code change quickly with minimal exploration and targeted validation. Use for small bug fixes, single feature edits, config updates, or explicit "$oneshot" requests.