repo-task-proof-loop
DenisSergeevitch/repo-task-proof-loop
Repo Task Proof Loop enforces a rigorous, verifiable workflow for complex coding tasks by separating implementation from independent verification. It maintains durable task state and artifacts directly within the repository under `.agent/tasks/`.
719 45Apache-2.0Updated 2026-04-01
78
GreatOverview
Designed to handle substantial features, refactors, and bug fixes, this skill implements an evidence-driven development cycle modeled after research-backed agentic workflows. It initializes dedicated task directories, configures specialized subagents for Codex and Claude Code, freezes specifications prior to building, and subjects all implementation outputs to fresh, independent verification passes with minimal defensive fixes.
Capabilities
- ▸Durable task state tracking via `.agent/tasks/<TASK_ID>/`
- ▸Specification freezing and explicit acceptance criteria management
- ▸Automated generation of build and test execution evidence
- ▸Integration with specialized subagents (spec-freezers, builders, verifiers, fixers)
- ▸Bounded parallel helper orchestration for Codex
Best for
Executing complex multi-file feature implementations with automated acceptance criteria checking, Managing structured bug fixes and regression prevention with verifiable proof logs, Coordinating multi-agent coding sessions with clear separation between builders and verifiers
Works with
Claude CodeCodex
Evoa Score breakdown= Σ (score × weight)
78Task 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%70 → +10.5
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%37 → +4.4
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%100 → +15.0
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%73 → +5.8
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
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 total77.9 / 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
Executes local python helper scripts and configures repository subagents; operates within standard local project access boundaries.
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.