做什么
完成任何非部落任务后使用 。 剂自定其输出在5个轴上——精度,完整性,清晰度,可操作性,简洁性——每个标准都有具体的证据. 制作一个结构化的1-5计分卡,并有具体的改进建议.
技能库 智客分类:Agent 工作流 agent-self-evaluation
完成任何非部落任务后使用 。 剂自定其输出在5个轴上——精度,完整性,清晰度,可操作性,简洁性——每个标准都有具体的证据. 制作一个结构化的1-5计分卡,并有具体的改进建议.
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
完成任何非部落任务后使用 。 剂自定其输出在5个轴上——精度,完整性,清晰度,可操作性,简洁性——每个标准都有具体的证据. 制作一个结构化的1-5计分卡,并有具体的改进建议.
官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。
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:Agent Self-Evaluation、When to Activate、Core Concepts、The 5 Evaluation Axes、Scoring Scale、The Evidence Rule。 其中含规范建议的小节:分步指令、输入输出示例。
文件分析:除 SKILL.md 外,正文引用了 references/hook-integration.md,属于带资源的技能包,这些文件按需再读。
Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy, completeness, clarity, actionability, conciseness — with concrete evidence per criterion. Produces a structured 1-5 scorecard with specific improvement suggestions.
Agent Self-EvaluationWhen to ActivateCore ConceptsThe 5 Evaluation AxesScoring ScaleThe Evidence RuleWorkflowStep 1: Collect the Raw MaterialStep 2: Score Each Axis IndependentlyStep 3: Produce the Evaluation ReportStep 4: Apply the ImprovementCode Examples
来源分类:skills.sh agent-skill
nameagent-self-evaluationdescriptionreferences/hook-integration.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 ↗
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。
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「agent-self-evaluation」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-62a3e05dfe013538-%E4%BB%A3%E7%90%86%E8%87%AA%E6%88%91%E8%AF%84%E4%BB%B7.html 请存为 .cursor/skills/agent-self-evaluation/SKILL.md 或 .claude/skills/agent-self-evaluation/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/affaan-m/ecc 取完整目录,不要只建一个 SKILL.md。
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/affaan-m/ecc' --list
npx skills add 'https://github.com/affaan-m/ecc' --skill 'agent-self-evaluation'
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。
After completing a complex task, the agent pauses to rate its own output against a structured 5-axis rubric. This is NOT a pass/fail gate — it's a deliberate reflection step that catches omissions, flags overconfidence, and surface areas for improvement before the user has to.
references/hook-integration.md)| Axis | Question | What it catches | |---|---|---| | Accuracy | Are the facts, claims, and outputs correct? | Hallucinations, wrong API names, incorrect syntax, false statements | | Completeness | Did it cover everything the user asked for? | Missed edge cases, unhandled error paths, forgotten requirements, skipped subtasks | | Clarity | Is the explanation understandable and well-structured? | Confusing explanations, jargon without definition, missing context, rambling | | Actionability | Can the user act on the output immediately? | Vague suggestions, missing steps, "you should X" without showing how, no verification path | | Conciseness | Did it use the minimum words/tokens needed? | Redundancy, over-explanation, repeating the user's question verbatim, filler content |
5 — Exceptional: no reasonable improvement possible
4 — Good: minor nits only, no substantive gaps
3 — Adequate: meets the request but has a notable weakness on at least one axis
2 — Weak: has a clear gap that affects usability or correctness
1 — Poor: fundamentally misses the request or contains significant errors
Every score below 5 MUST cite specific evidence. A score of 3 cannot just say "could be better" — it must say exactly what is missing or wrong. The mantra: "Show the gap, don't just name it."
Gather what you'll evaluate:
- The original user request (read back from conversation)
- Your final response/output (the deliverable)
- Any tool outputs that verify correctness (test results, exit codes, lint output)
- Any user feedback received during the task (corrections, "try again", "that's not right")
Work through the 5 axes one at a time. For each:
Do NOT average the scores in your head first and then work backwards. Score each axis fresh.
Use the template from templates/evaluation-report.md. The report must include:
- One-line summary
- 5-axis scorecard (score + evidence per axis)
- Overall score (simple average, rounded to 1 decimal)
- 1-3 specific improvements ranked by impact
- Self-check: "Would the user agree with this assessment?"
If any axis scored 3 or below:
Task: Add retry logic to HTTP client
Scorecard:
Accuracy: 5 — All API calls correct. Verified: retries use
exponential backoff. No hallucinated methods.
Completeness: 4 — Covered happy path + 3 error cases. Missing:
timeout handling for hung connections.
Clarity: 5 — Code comments explain backoff formula.
PR description links to incident that motivated this.
Actionability:5 — Single merge. No follow-up tasks. Tests pass.
Conciseness: 4 — 47 lines total. The retry loop could be extracted
into a helper to drop ~8 lines.
Overall: 4.6 — One gap (timeout handling). Fix before merging.
Task: Add retry logic to HTTP client
Scorecard:
Accuracy: 2 — Used urllib3 which doesn't match our
httpx-based codebase. Wrong library.
Completeness: 3 — Works for GET. POST/PUT not handled (user
said "all HTTP requests").
Clarity: 4 — Code is readable. Good variable names.
Actionability:2 — "Add tests" mentioned but no test file created.
User has to write tests before merging.
Conciseness: 3 — 120 lines. The retry config is duplicated in
3 places instead of one shared RetryConfig object.
Overall: 2.8 — Wrong library used. Needs httpx rewrite.
Fix accuracy first (switch to httpx), then extend to all
HTTP methods, then consolidate config.
FAIL: Accuracy: 5 — All good.
Completeness: 5 — Everything covered.
Clarity: 5 — Clear.
No evidence cited. This is self-congratulation, not evaluation. A real 5 requires proving there's nothing to improve.
FAIL: Completeness: 2 — Didn't handle WebSocket connections or
gRPC streaming (user didn't ask for these)
Only evaluate against what the user actually requested, not what you could have additionally built.
FAIL: "As I said earlier, this approach is wrong. Score: 1"
The evaluation is about the delivered output, not about re-arguing design decisions that were already made. If the approach was wrong, that should have been caught before delivery.
FAIL: "Score: 3. I don't like Python decorators."
"Don't like" is not evidence. Cite a concrete readability, testability, or correctness concern, or leave the score at 4+.
agent-eval — Head-to-head comparison of different coding agents on benchmark tasksverification-loop — Systematic verification of outputs against expected resultssecurity-review — Security-focused code review checklistAgent 工作流
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
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
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
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…