Antinet Provenance

by anbeime

Antinet Provenance is an AI Engineering skill for Claude Code, published by anbeime in skill.

5.3K stars519 forkson anbeime/skillAdded 2026/08/16+3% in starsRepository updated 2026/08/16

View source on GitHub Download repo ZIP

claude-skillsfinance-skillgemini-skillshermes-skilloffice-skillopenclaw-skillsskillskill-mdskills

Install in seconds

Install Antinet Provenance

Copy Antinet Provenance into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/anbeime/skill/tree/main/skills/antinet-provenance ~/.claude/skills/antinet-provenance

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/anbeime/skill.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: skills/antinet-provenance/SKILL.md in anbeime/skill
Installs to: ~/.claude/skills/antinet-provenance
Collection: One of 23 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Antinet Provenance does

Antinet Provenance collects full-chain operational logs and generates traceable evidence chains and vector indexes for multi-agent system observability and security auditing. Use it to record key operation events, query audit trails by trace ID or time window, and support rollback and compliance.

Antinet Provenance is cataloged under AI Engineering on DirSkills. Antinet Provenance comes from a repository tagged claude-skills, finance-skill, gemini-skills, hermes-skill and office-skill.

Documentation

README

Excerpt

Provenance 留痕 Skill（太史阁）

使用方式

由各官署在关键操作节点调用（或通过事件总线异步推送），写入证据链。
提供按 trace_id / 时间窗 / 官署维度的检索接口，支撑审计面板与回滚定位。

输入（Input）

event：操作事件，含 actor（官署名）、action、target、timestamp、trace_id
payload：（可选）与事件关联的结构化产物引用

输出（Output）

evidence_chain：按 trace_id 串联的可追溯证据链
vector_index：用于语义检索的向量索引条目
query_api：按条件检索历史证据的接口描述

依赖（Dependencies）

Qdrant（向量存储，经 MCP 接入）
SQLite（结构化事件落地，本地兜底）
各官署的事件上报协议（统一 schema）

失败处理（Failure Handling）

向量库写入失败 → 本地 SQLite 缓存事件，恢复后异步补写，不阻塞主流程。
单条事件 schema 非法 → 记录并丢弃该条，不影响整链写入。
检索超时 → 返回最近一次成功快照并标注 stale。

复用价值（Reuse Value）

可观测性底座：任何多 Agent 系统都能直接挂载，获得开箱即用的审计与回放能力。
契合评审：Agent Infra 赛道「工程落地与运行验证及安全审计（20%）」维度的天然得分点。

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Antinet Provenance

What else does anbeime publish alongside Antinet Provenance?
Antinet Provenance is one of 23 skills that DirSkills catalogs from anbeime/skill, the repository it ships in. Its siblings there include Agent Team, AgentKit Multimedia Shopping and Antinet Doc Parse. Each one is a separate skill with its own page in this directory, installs the same way Antinet Provenance does, and is maintained by anbeime in that same repository. The rest of the collection is listed on the anbeime/skill page.
How does Antinet Provenance compare to other AI Engineering skills?
Antinet Provenance ranks #486 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Antinet Provenance against them. Open each page to compare what they document and how they install.