收集系统全链路操作日志,生成可追溯的执行证据链与向量索引,是多智能体系统可观测性与安全审计的底座。
Scanned 9/2/2026
Install to Claude Code
npx -y skills add anbeime/skill --skill provenance --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Provenance?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/anbeime-provenance)More formats (shields.io, HTML) on the badges page.
---
name: provenance
description: 收集系统全链路操作日志,生成可追溯的执行证据链与向量索引,是多智能体系统可观测性与安全审计的底座。
assign_when: 该 Worker 负责记录每一次分发、扫描、解析与卡片生成事件,为系统提供端到端留痕与可观测能力。
---
# 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。
## 复赛代码包执行(runnable package)
- 真实入口:`scripts/run_provenance.py`
- 执行等价于 `core.runtime.AgentSession.run_stage("provenance")`,调用 `memory.taishige.TaiShiGeAgent.writeback`(把全链路事件与四色卡片回流证据链,纯 Python 可离线)。
- 运行:`python skills/provenance/scripts/run_provenance.py`
- 产物:`examples/snse_survey/provenance/`(trace.jsonl + trace_summary.json,含每一条军机处派发与官署执行事件)。
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Use when a repo needs CodeGraph plus ast-grep for Codex MCP setup, exploration, impact analysis, structural search, or safe refactor planning.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.