Agent测试
- 作者仓库星标 3,406
- 作者更新于 实时读取
- 作者仓库 claude-octopus
- 领域
- 通用
- 兼容 Agent
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- 信任分
- 88 / 100 · 社区维护
- 作者 / 版本 / 许可
- @nyldn · 未声明 license
- Token 消耗评级
- 低消耗
- 接入复杂程度
- 需简单配置
- 是否需要外部 API Key
- 不需要
- 兼容的系统
- macOS · Linux · Windows
- 底层运行要求
- 无特殊要求
- 文件与系统权限
-
- 只读
- 允许写入 / 修改
- Shell 执行
- 网络行为
- 仅限本地
- 安装命令数
- 26 条
档案由构建时根据 SKILL.md 与安装命令自动衍生，可能与作者实际意图存在差异。
需要注意： 未限定 allowed-tools，默认拥有全部工具权限。
---
name: skill-verify
description: Evidence before claims — run verification commands before declaring work complete, fixed, or pas…
category: 通用
runtime: 无特殊运行时
---
# skill-verify 输出预览
## PART A: 任务判断
- 适用问题：通用任务拆解、检查和交付。
- 输入要求：目标材料、限制条件、期望输出和验收方式。
- 证据边界：围绕“The Iron Law / The Gate / What Counts as Evidence”读取原文规则，不把推断写成作者承诺。
## PART B: 执行结果
- **01** 任务判断：确认你的需求是否属于通用任务拆解、检查和交付，并标出输入、限制和预期结果。
- **02** 执行计划：优先按“The Iron Law / The Gate / What Counts as Evidence”拆成步骤，说明每一步会读取什么、修改什么、产出什么。
- **03** 交付结果：给出可复制的命令、文件改动、检查清单或内容草稿，并说明如何继续迭代。
- **04** 风险边界：结合 读取文件、写入/修改文件、执行终端命令、主要在本地完成、通常不需要额外 API Key 给出执行前确认项。
## Running Rules
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先小样例验证，再放大到真实任务。
- 交付时同时给结果、检查口径和下一步迭代建议。 先确认触发方式
原文出现了 `/octo` 这类斜杠命令；如果你的 Agent 支持命令触发，优先用命令开场，再补充目标和边界。
给清楚输入和边界
告诉 Agent 目标文件或材料、期望结果、不可改范围、是否允许联网或执行命令。本 Skill 的权限画像是：读取文件、写入/修改文件、执行终端命令。
小样例验证后再放大
先用一个小任务确认它会围绕“The Iron Law / The Gate / What Counts as Evidence”工作；涉及文件或命令时，先看 diff、日志、预览或测试结果。
复核后再交付
检查最终产物是否包含明确结果、必要证据和下一步动作；如果输出泛泛而谈，就补充输入、边界和验收标准后重跑。
---
name: skill-verify
description: Evidence before claims — run verification commands before declaring work complete, fixed, or pas…
category: 通用
source: nyldn/claude-octopus
---
# skill-verify
## 什么时候使用
- 把通用方向的常用动作沉淀成 Agent 可调用的技能 适合处理通用任务拆解、检查、交付和复盘，核心价值是把输入、判断、执行、验证和交付边界固定下来，避免 Agent 泛泛回答。 把任务拆成可执行、可检查、可继续迭代的步骤；通常不需要额外…
- 面向通用任务拆解、检查和交付，优先处理能明确输入、步骤和验收标准的工作。
## 需要提供什么
- 目标材料、目录范围、期望结果和不可改动内容。
- 是否允许联网、执行命令、读写文件或调用外部服务。
## 执行规则
- 围绕「The Iron Law / The Gate / What Counts as Evidence」组织步骤，不把推断写成作者事实。
- 读取文件、写入/修改文件、执行终端命令；主要在本地完成；通常不需要额外 API Key。
- 先跑小样例，确认结果可检查后再扩大任务范围。
## 输出要求
- 给出最终产物、关键证据、验证方式和下一步动作。
- 信息不足时标记 unknown，不编造命令、平台或依赖。 证据边界与执行链路
作者原文负责流程事实；仓库文件负责来源和命令；流狐只补充适用场景、限制和质量判断。
skill "skill-verify" {
输入层 -> 用户目标 + 目标文件 + 禁止范围 + 验收标准
上下文层 -> The Iron Law / The Gate / What Counts as Evidence
规则层 -> SKILL.md 触发条件 / 执行顺序 / 输出格式
运行层 -> 无特殊运行时 | 读取文件、写入/修改文件、执行终端命令 | 主要在本地完成
安全层 -> 通常不需要额外 API Key + 小任务验证 + diff / 日志复核
输出层 -> 可复制结果 + 检查清单 + 下一步迭代
}Host: Codex CLI — This skill was designed for Claude Code and adapted for Codex. Cross-reference commands use installed skill names in Codex rather than
/octo:*slash commands. Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it. For host tool equivalents, seeskills/blocks/codex-host-adapter.md.
Verification Gate
The Iron Law
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCEIf you haven't run the verification command in this turn, you cannot claim it passes.
The Gate
Before claiming any success or expressing satisfaction:
- IDENTIFY — What command proves this claim?
- RUN — Execute the full command (fresh, not cached)
- READ — Full output, check exit code, count failures
- VERIFY — Does output actually confirm the claim?
- ONLY THEN — State the claim WITH evidence
Skip any step = the claim is unverified.
What Counts as Evidence
| Claim | Requires | NOT Sufficient |
|---|---|---|
| Tests pass | Test command output showing 0 failures | Previous run, "should pass" |
| Build succeeds | Build command exit 0 | Linter passing |
| Bug fixed | Reproduce original symptom: now passes | "Code changed, should work" |
| Regression test works | Red (fail without fix) → Green (pass with fix) | Test passes once |
| Subagent completed task | git diff shows expected changes |
Subagent says "done" |
| Requirements met | Line-by-line checklist against spec | Tests passing |
| Provider dispatch worked | Output contains expected content | No error ≠ success |
Red Flags — STOP and Verify
If you catch yourself thinking any of these, STOP:
| Thought | What to do instead |
|---|---|
| "Should work now" | Run the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "The linter passed" | Linter ≠ tests ≠ build |
| "The agent said it worked" | Verify independently |
| "It's a small change" | Small changes cause big bugs |
Multi-Provider Context
In Claude Octopus workflows, verification is especially critical because:
- Provider outputs can be hallucinated — Codex/Gemini/Copilot may claim success without evidence
- Consensus ≠ correctness — three models agreeing doesn't mean they're right
- Synthesis files may be stale — check timestamps, don't assume freshness
- orchestrate.sh exit code 0 ≠ quality — the script ran, but did it produce good output?
After any multi-provider workflow:
# Verify synthesis file exists and is recent
ls -la ~/.claude-octopus/results/*-synthesis-*.md | tail -1
# Verify it has content (not just headers)
wc -l ~/.claude-octopus/results/*-synthesis-*.md | tail -1When to Apply
ALWAYS before:
- Committing code
- Creating PRs
- Marking tasks complete
- Moving to next workflow phase
- Reporting results to user
- Claiming a bug is fixed
In orchestrate.sh workflows:
- After
probe(discover) — verify synthesis file exists - After
grasp(define) — verify consensus score meets threshold - After
tangle(develop) — verify tests pass, not just that code was written - After
ink(deliver) — verify review actually ran, not just that it was dispatched
Examples
Correct: Evidence-Based Claim
$ npm test
✓ user.create() saves to database (45ms)
✓ user.create() validates email (12ms)
Tests: 2 passed, 2 total
All 2 tests pass. ← Claim backed by output.Incorrect: Claim Without Evidence
I've implemented the feature. It should work now. The tests should pass.
← No test was run. "Should" is not evidence.Correct: Regression Test Red-Green
1. Write test → run → FAIL (expected, proves test detects the bug)
2. Implement fix → run → PASS (proves fix works)
3. Revert fix → run → FAIL (proves test isn't false-positive)
4. Restore fix → run → PASS (final confirmation)Integration with Other Skills
This skill is referenced by:
flow-develop.md— verification gate after implementationflow-deliver.md— verification gate before deliveryskill-code-review.md— verify review findings before reportingskill-tdd.md— red-green cycle requires evidence at each stepskill-factory.md— autonomous pipeline must verify at every phase
先判断是否适合
作者设计意图
作者的方法与取舍
边界和复核