القائمة
Implement features end-to-end: plan, code, test, review via registry agents. Use for 'implement X', 'build Y feature', 'add Z functionality'. Handles full workflow.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Asset Hunter Pro — unused asset detection, dependency graph, duplicate finder, project cleanup automation for Unity
Practical tools and validation methods for game balance — DPS calculators, EHP formulas, spreadsheet layouts, stat audits, difficulty spike detection
GDD structure, templates, and living documentation patterns for game projects — wiki pages, design docs, section layout, sync triggers
Game feel and juice — screen shake, hit stop, particles, animation curves, input responsiveness, feedback timing. Makes actions feel satisfying.
Mobile game design patterns — session design, retention mechanics, notification strategy, portrait/landscape, battery/thermal constraints, FTUE
Create or update TheOneKit agent .md files with canonical structure. Use when adding a new agent, updating maxTurns/model, or fixing frontmatter fields.
| name | t1k:cook |
| description | Implement features end-to-end: plan, code, test, review via registry agents. Use for 'implement X', 'build Y feature', 'add Z functionality'. Handles full workflow. |
| version | 2.0.0 |
| argument-hint | [task|plan-path] [--interactive|--fast|--parallel|--auto|--no-test] |
| effort | high |
| origin | theonekit-core |
| repository | The1Studio/theonekit-core |
| module | null |
| protected | true |
End-to-end feature implementation. Routes to the registered implementer agent for the current kit.
Principles: YAGNI, KISS, DRY | Token efficiency | Concise reports
/t1k:cook <natural language task OR plan path>
IMPORTANT: If no flag is provided, the skill uses interactive mode by default.
Optional flags: --interactive (default) | --fast (skip research) | --parallel (multi-agent) | --no-test | --auto (auto-approve)
Follow protocol: rules/routing-protocol.md — role: implementer
Follow protocol: rules/activation-protocol.md
| Input Pattern | Detected Mode |
|---|---|
Path to plan.md or phase-*.md | code — execute existing plan |
| Contains "fast", "quick" | fast — skip research |
| Contains "trust me", "auto" | auto — auto-approve all steps |
| Lists 3+ features OR "parallel" | parallel — multi-agent |
| Contains "no test", "skip test" | no-test — skip testing |
| Default | interactive — full workflow |
Full detection logic: references/intent-detection.md
[Intent Detection] -> [Research?] -> [Review] -> [Plan] -> [Review] -> [Implement] -> [Review] -> [Test?] -> [Review] -> [Finalize]
| Mode | Research | Testing | Review Gates |
|---|---|---|---|
| interactive | yes | yes | User approval at each step |
| auto | yes | yes | Auto if score>=9.5 |
| fast | no | yes | User approval at each step |
| parallel | optional | yes | User approval at each step |
| no-test | yes | no | User approval at each step |
| code | no | yes | User approval per plan |
Full step definitions: references/workflow-steps.md
Review processes: references/review-cycle.md
Testing, Review, and Finalize phases MUST use Task tool to spawn subagents — DO NOT inline these steps.
Full subagent table and injection protocol: references/subagent-patterns.md
Finalize (never skip): project-manager → plan sync-back | docs-manager → update ./docs | git-manager → commit offer
Human review required at: Post-Research, Post-Plan, Post-Implementation, Post-Testing (100% pass required).
Always enforced: 100% test pass (unless no-test), code review score>=9.5 for auto-approve.
T1K resolves env vars in priority order — never hardcode values. Details: references/env-hierarchy.md
references/intent-detection.md — detection rules and routing logicreferences/workflow-steps.md — detailed step definitions for all modesreferences/review-cycle.md — interactive and auto review processesreferences/subagent-patterns.md — subagent invocation patternsreferences/env-hierarchy.md — .env resolution hierarchy