AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Benchmark Review Miner

skill-woshixiguaweierde-codex-sci-review-agent-s06-benchmark-review-miner · by woshixiguaweierde

建立对标综述库,学习写作逻辑与范围边界。 Use when: screening_pack.csv 已完成. Do not use when: benchmark_reviews.csv 已稳定.

No reviews yet
0 installs
20 views
0.0% view→install

Install

$ agentstack add skill-woshixiguaweierde-codex-sci-review-agent-s06-benchmark-review-miner

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-woshixiguaweierde-codex-sci-review-agent-s06-benchmark-review-miner)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Benchmark Review Miner? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Identity

  • Skill ID: S06
  • Slug: benchmark-review-miner
  • Directory: .agents/skills/S06-benchmark-review-miner/
  • Name: Benchmark Review Miner
  • 中文角色: 对标综述库建立
  • Stage: Bliteratureevidence
  • Skill Type: business
  • Human Gate: G2
  • Required QA Hooks: - Q02

Mission

建立对标综述库,学习写作逻辑与范围边界。

此 skill 在综述生产流水线中的角色:对标综述库建立。它在"Bliteratureevidence"阶段运行, 生成结构化产物供下游 skill 消费,并在 G2 处接受人工审核。

Scientific Role in the Workflow

  • 所处阶段: 文献分析阶段——识别已有综述,建立对标库,为差异化定位提供依据
  • 产出形式: benchmarkreviews.csv + benchmarknotes.md
  • 人机协同点: 产物在 G2 处需人工审签;关键决策记录在 decision_log.md 中
  • 对下游的价值: 为 S13 叙事设计提供差异化策略,避免重复已有综述

Scope of Responsibility

  • 本 skill 仅负责 综述识别、标杆选定、差异化分析
  • 不负责 原始研究质量评估(那是 S11 的职责)
  • 不负责 全文精读(那是 S09 的职责)

Trigger When

screening_pack.csv 已完成

Do Not Trigger When

benchmark_reviews.csv 已稳定

Required Inputs

  • master_records.csv
  • topic_keywords

Optional Inputs

  • 用户提供的已知关键综述列表

Output Contract

  1. 所有输出文件写入 /artifacts/run-/stage-2/ 目录下
  2. 结构化输出(.json / .csv)优先于叙述性输出(.md),必须通过 schemas/ 下对应 JSON Schema 校验
  3. 每个输出产物在 artifact registry 中注册时,须记录其上游依赖、生成时间、生成器和版本号
  4. 产物格式优先级:结构化数据 (.json) > 表格 (.csv) > 叙述性 Markdown (.md) > 自由文本
  5. 产物路径和命名遵循 configs/artifact_registry_rules.json 中定义的规范

Expected Outputs

  • benchmark_reviews.csv
  • benchmark_notes.md

Operational Steps

  1. 验证所有 Required Inputs 存在且可读,缺失则立即停止并报告
  2. 加载相关 Schema 和契约文件(schemas/ 目录下)
  3. 仅执行 Purpose 与 Scope of Responsibility 中定义的任务,不漂移到相邻 skill 的职责
  4. 先产出结构化数据(.json / .csv),再生成叙述性说明(.md)
  5. 记录所有假设、未解决的歧义和失败追踪信息
  6. 若置信度不足(如关键数据缺失导致无法做出科学判断),停止执行并升级给人工,不得猜测或编造

Decision / Writing / Validation Principles

  • 结构化字段优先:先填满 schema 的 required 字段,再补充 optional 字段
  • 证据三元组:每个科学论断必须包含 (sourceid, findingdirection, evidence_strength)
  • 冲突分类:如发现证据方向矛盾,标记为 direction_conflict 而非强行选边
  • 术语一致性:同一实体在全文中使用统一的 canonical term(参见 configs/ontology/)
  • 保守推断:不在证据不足时声称"clearly" "definitively" "proves"

Hard Constraints

  • 不得编造 DOI、PMID、样本量、统计值、期刊身份或研究结论
  • 不得静默覆盖已有高版本 artifact(必须 version incrementally,参见 AGENTS.md)
  • 不得删除上游可审计痕迹(raw exports、screening decisions、extraction logs 必须保留)
  • 不得绕过 Gate 或把 QA 结论写成"已人工确认"(除非真正通过了人工审核)
  • 不为了'显示差异化'而贬低已有综述
  • 不将非综述文献误标为 benchmark
  • benchmark 选择必须有期刊/年份/覆盖度的多样性

QA Hooks

  • Q02

Human-in-the-Loop Checkpoint

  • 产出物完成后,进入 G2 等待人工审核
  • 审核通过前,下游 skill 不得启动
  • 若人工审核要求修订,返回上游 skill(参见 orchestrator/state_machine/transitions.yaml

Acceptance Checklist (Self-Verification Before Declaring Done)

  • [ ] 所有 Required Inputs 已加载且完整
  • [ ] 所有 Expected Outputs 已生成且非空
  • [ ] 结构化输出通过对应 JSON Schema 校验
  • [ ] 产物已在 artifact registry 中注册(含 checksum + version)
  • [ ] QA hooks 中列出的所有 QA skill 已触发
  • [ ] decision_log.md 记录了关键决策及其理由

Failure Handling

  • 缺少输入: 发出 blocking error,立即停止,不继续执行
  • Schema 校验失败: 重试一次(带错误上下文修正);若第二次仍失败,升级给 checkpoint manager
  • 下游污染风险: 如果当前产物可能影响下游 skill 的正确性,标记为 status: blocked,阻止流水线继续
  • 领域特定失败: 若找到相关综述 /logs/S06/`):
  • input_manifest.json — 所有输入的路径和校验和
  • output_manifest.json — 所有输出的路径和校验和
  • validation_result.json — Schema 校验结果
  • decision_log.md — 关键决策及其理由
  • failure_trace.md — 失败时的错误堆栈(如有)

Collaboration Notes for Codex / Orchestrator

  • 执行前先读取 AGENTS.md 获取项目级非协商规则
  • 执行前先读取 configs/skills_manifest.json 确认本 skill 的上下游依赖
  • 产物注册使用 orchestrator/artifact_registry/registry_v2.py 的统一接口

Definition of Done

  1. 所有 Expected Outputs 已写入磁盘并通过 Schema 校验
  2. 所有 Required QA Hooks 已触发并获得非 blocking 结果
  3. 产物已在 artifact registry 中注册,具备完整的 provenance 记录

Examples

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.