跳到主内容
智客 ZICQ

技能库 智客分类:Agent 工作流 dual-axis-skill-reviewer

Dual Axis Skill Reviewer

使用双轴方法对任何项目进行复核技能:(1)基于编码的确定性检查(结构,脚本,测试,执行安全)和(2)LLM深度复核结果. 当需要再生产质量评分时,使用"技能/*/SKILL.md",想用分数阈值(例如90+)入门并出,或者需要具体改进项目进行低分技能. 通过 -- -- 项目根基进行跨项目工程.

2416 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

使用双轴方法审查任何项目的技能:(1) 确定基于编码的检查(结构、脚本、测试、执行安全)和(2) LLM深度审查结论

何时用

- 需要可复制的“技能/*/SKILL.md”技能评分

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Dual Axis Skill Reviewer、When to Use、Prerequisites、Workflow、If reviewing from the same project:、If reviewing another project (global install):。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 scripts/run_dual_axis_review.py、references/llm_review_schema.md、references/scoring_rubric.md,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root.

Dual Axis Skill ReviewerWhen to UsePrerequisitesWorkflowIf reviewing from the same project:If reviewing another project (global install):Step 1: Run Auto Axis + Generate LLM PromptStep 2: Run LLM ReviewStep 3: Merge Auto + LLM AxesStep 4: Optional ControlsOutputInstallation (Global)

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
dual-axis-skill-reviewer
description
Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root.
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 3
  • scripts/run_dual_axis_review.py
  • references/llm_review_schema.md
  • references/scoring_rubric.md

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「dual-axis-skill-reviewer」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-d9b30578f12fc6ea-%E5%8F%8C%E8%BD%B4%E6%8A%80%E8%83%BD%E5%AE%A1%E6%9F%A5%E5%99%A8.html
请存为 .cursor/skills/dual-axis-skill-reviewer/SKILL.md 或 .claude/skills/dual-axis-skill-reviewer/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/tradermonty/claude-trading-skills 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/tradermonty/claude-trading-skills' --list

npx skills add 'https://github.com/tradermonty/claude-trading-skills' --skill 'dual-axis-skill-reviewer'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: dual-axis-skill-reviewer description: "Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root." --- # Dual Axis Skill Reviewer Run the dual-axis reviewer script and save reports to `reports/`. The script supports: - Random or fixed skill selection - Auto-axis scoring with optional test execution - LLM prompt generation - LLM JSON review merge with weighted final score - Cross-project review via `--project-root` - Non-scoring display of `skills-index.yaml` production verification declarations ## When to Use - Need reproducible scoring for one skill in `skills/*/SKILL.md`. - Need improvement items when final score is below 90. - Need both deterministic checks and qualitative LLM code/content review. - Need to review skills in a **different project** from the command line. ## Prerequisites - Python 3.9+ - `uv` (recommended — auto-resolves `pyyaml` dependency via inline metadata) - For tests: `uv sync --extra dev` or equivalent in the target project - For LLM-axis merge: JSON file that follows the LLM review schema (see Resources) ## Workflow Determine the correct script path based on your context: - **Same project**: `skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py` - **Global install**: `~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py` The examples below use `REVIEWER` as a placeholder. Set it once: ```bash # If reviewing from the same project: REVIEWER=skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py # If reviewing another project (global install): REVIEWER=~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py ``` ### Step 1: Run Auto Axis + Generate LLM Prompt ```bash uv run "$REVIEWER" \ --project-root . \ --emit-llm-prompt \ --output-dir reports/ ``` When reviewing a different project, point `--project-root` to it: ```bash uv run "$REVIEWER" \ --project-root /path/to/other/project \ --emit-llm-prompt \ --output-dir reports/ ``` ### Step 2: Run LLM Review - Use the generated prompt file in `reports/skill_review_prompt__.md`. - Ask the LLM to return strict JSON output. - When running inside Claude Code, let Claude act as orchestrator: read the generated prompt, produce the LLM review JSON, and save it for the merge step. ### Step 3: Merge Auto + LLM Axes ```bash uv run "$REVIEWER" \ --project-root . \ --skill \ --llm-review-json \ --auto-weight 0.5 \ --llm-weight 0.5 \ --output-dir reports/ ``` ### Step 4: Optional Controls - Fix selection for reproducibility: `--skill ` or `--seed ` - Review all skills at once: `--all` - Skip tests for quick triage: `--skip-tests` - Change report location: `--output-dir ` - Increase `--auto-weight` for stricter deterministic gating. - Increase `--llm-weight` when qualitative/code-review depth is prioritized. ## Output - `reports/skill_review__.json` - `reports/skill_review__.md` - `reports/skill_review_prompt__.md` (when `--emit-llm-prompt` is enabled) When the target project has a `skills-index.yaml` entry with a complete `verification` block, JSON and Markdown reports also show its declared axes, `not_verified` gaps, non-applicable axes, and `all_applicable_axes_passed`. This section is informational only. It is excluded from auto/LLM/final scores and does not replace a live high-severity issue check. ## Installation (Global) To use this skill from any project, symlink it into `~/.claude/skills/`: ```bash ln -sfn /path/to/claude-trading-skills/skills/dual-axis-skill-reviewer \ ~/.claude/skills/dual-axis-skill-reviewer ``` After this, Claude Code will discover the skill in all projects, and the script is accessible at `~/.claude/skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py`. ## Resources - Auto axis scores metadata, workflow coverage, execution safety, artifact presence, and test health. - Auto axis detects `knowledge_only` skills and adjusts script/test expectations to avoid unfair penalties. - LLM axis scores deep content quality (correctness, risk, missing logic, maintainability). - Final score is weighted average. - If final score is below 90, improvement items are required and listed in the markdown report. - Script: `skills/dual-axis-skill-reviewer/scripts/run_dual_axis_review.py` - LLM schema: `references/llm_review_schema.md` - Rubric detail: `references/scoring_rubric.md`

相关技能

Agent 工作流

Skill Creator

创造有效技能指南。 当用户想创造出新的技能(或更新现有的技能),以专业知识,工作流程,或工具集成来扩展克洛德的能力时,应该使用这种技能.

Agent 工作流

Clawdhub

使用ClawdHub CLI搜索,安装,更新并发布从taladhub.com的代理技能. 需要获取苍蝇上的新技能时使用,将安装的技能同步到最新版本或特定版本,或者发布 npm-instainddhub CLI 的新/更新的技能文件夹.

Agent 工作流

Agent Team Orchestration

管弦乐团多代理团队,任务设定周期,交接协议,审查工作流程. 使用时间: (1)建立2+特派员队伍,具有不同专业,(2)确定任务路线和生命周期(收录框_ spec_建设_审查_完成),(3)在特派员之间制定交接协议,(4)建立审查和质量关口,(5)管理特派员之间的交流和文物共享.

Agent 工作流

Superpowers

Spec-first,TDD,子代理驱动的软件开发工作流程. 当:(1)构建任何新功能或应用——触发脑暴_计划_子代理执行回路,(2)调试出一个bug或测试失败——触发系统性的根起过程,(3)用户说"让我们构建","帮助我计划","我想添加X",或"这个被打破",(4)完成一个功…