#
ENJA

issue-proof-for-codex

wly12312/issue-proof-for-codex

IssueProof for Codex is a Windows-based verification tool that records privacy-filtered evidence for open-source maintenance tasks. It helps developers reproduce issues, ingest Codex JSONL traces, and generate audit receipts.

29 1Apache-2.0Updated 2026-08-12

Overview

Designed specifically for Windows 10/11 environments running Python 3.11+, this skill provides a structured CLI wrapper and workflow guide for auditing code changes, verifying fixes against established baselines, and producing deterministic Markdown/JSON maintenance receipts. It operates completely offline for trace ingestion and enforces strict safety boundaries preventing automatic pushing, posting, or commenting on GitHub.

Capabilities

  • Windows PowerShell integration and CLI delegation
  • Baseline collection and deterministic command verification
  • Codex JSONL trace ingestion and event projection
  • Receipt generation with evidence-backed claims and SHA-256 trace hashing
  • Privacy filtering and local-only output management

Best for

Reproducing open-source software bugs and verifying bug fixes on Windows, Ingesting and analyzing explicit Codex JSONL execution traces offline, Generating privacy-filtered maintenance receipts for human maintainer review, Auditing Codex code maintenance completions and checking command execution outputs

Works with

Codex
Evoa Score breakdown= Σ (score × weight)
76
Task 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%100 → +15.0

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%41 → +4.9

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%38 → +3.0

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%25 → +1.3

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 total75.8 / 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 skill enforces strict isolation: it does not post to GitHub, push changes, or create PRs. Trace ingestion and parsing occur entirely offline without making network requests. However, explicitly authorized verification commands executed by the user may modify the local repository.

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.