菜单
Deterministic SARIF reporting and partitioning. Use when inspecting .sarif or .sarif.json static-analysis output, summarizing findings without loading full JSON into chat, or splitting results by rule, path, severity, or balanced chunks.
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
Nix operational playbooks for package diffs, build debugging, closure analysis, dependency forensics, flake maintenance, and evaluation performance tuning. Use when comparing Nix build outputs, diagnosing derivation failures, finding unexpected runtime/build dependencies, inspecting closure size, maintaining flakes, or profiling slow NixOS/Home Manager/Nixvim evaluation.
GitHub issue discovery, targeted triage, issue creation, pull-request creation, review authoring, review-feedback handling, and CI check-fix workflows using gh CLI. Use for read or write work against GitHub issues, pull requests, reviews, or checks.
Git commit planning, fixup/autosquash, branch cleanup, conflict resolution, regression bisect, and multi-commit change-stack workflows. Use for safe local history operations or deciding how changes should be split, repaired, or validated.
Progressive context-architecture expert for repository instructions, AI prompts, rules, agents, commands, and skills. Use when initializing, designing, refactoring, or auditing AI configuration for clear boundaries and token-efficient disclosure.
Use for working with Jujutsu (jj) history workflows, including hunk-level split/squash/diffedit/restore via `jj-hunk-tool`.
Write idiomatic and maintainable Nix code. Use when creating or refactoring Nix expressions, Home Manager or NixOS modules, overlays, packages, and flake outputs, especially when deciding module merge semantics, binding locality, option defaults, and conditional structure.
| name | sarif-toolkit |
| description | Deterministic SARIF reporting and partitioning. Use when inspecting .sarif or .sarif.json static-analysis output, summarizing findings without loading full JSON into chat, or splitting results by rule, path, severity, or balanced chunks. |
Use bundled script for mechanical inspection. Keep interpretation and fix prioritization with agent.
python3 <skill-dir>/scripts/sarif_report.py <file> --format markdown
Report includes schema/version, runs, tools, result and artifact counts, top
rules, severity counts, affected paths, and bounded representative results.
Scalar values, tools, severities, and split-file listings are bounded by default
with total/omitted metadata. Use --help to adjust limits; 0 means unlimited
for --max-* flags.
Write chunks only when user asks:
python3 <skill-dir>/scripts/sarif_report.py <file> \
--split rule --output-dir <directory>
python3 <skill-dir>/scripts/sarif_report.py <file> \
--split balanced --chunks 4 --output-dir <directory>
Strategies: rule, path, severity, balanced. Script uses stable filenames
and writes manifest.json last. Existing non-empty output requires --force.
Manifest keeps the complete file/run mapping even when stdout lists only a
bounded subset.
--split, read file and print report only.--split, write only selected output directory.