goal-engineering
cobusgreyling/goal-engineering
Goal Engineering provides a framework and toolset to replace one-shot prompts with verifiable, autonomous objectives that run until completion. It serves as the reference implementation for Grok Build CLI's goal-driven execution features.
38 4MITUpdated 2026-06-30
76
GreatOverview
Goal Engineering introduces structured goal-driven workflows for AI agents, allowing you to establish explicit objectives, separate verifiers, state management, and turn-based budgets. By leveraging tools like goal-audit, goal-init, and goal-cost alongside patterns for testing, migration, and bug fixing, it ensures tasks are carried out reliably until they meet verified success criteria rather than stopping prematurely.
Capabilities
- ▸Run-until-done objective tracking across turns
- ▸Goal readiness auditing (G0-G3)
- ▸Pattern scaffolding for tests, migrations, bug fixes, and refactors
- ▸Turn and token estimation for goals
- ▸Integration with Grok Build CLI goal commands
Best for
Managing autonomous multi-turn bug fixes and feature implementations in software projects, Auditing and scaffolding project readiness with G0-G3 readiness levels, Coordinating agent tasks that require independent verification before completion
Works with
CodexGemini CLICursor
Evoa Score breakdown= Σ (score × weight)
76Task usefulness20%88 → +17.6
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%85 → +12.8
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%40 → +4.8
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%42 → +3.4
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%75 → +3.8
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total76.3 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
The tools interact with project files and run test suites locally, which carries standard execution risks associated with untrusted repository scripts.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.