Chalk Labs
Need help deploying Hermes 质量监督?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/liwen17320273738-hermes
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/hermes
What's inside
- Skill name
Hermes 质量监督- Description
- 统一质量监督 Skill — 整合自检、护栏、质量门、同行评审、最终验收、可观测为单一监督结论
- License
- MIT
- Instructions
- 78 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: only lowercase letters, digits and single hyphens allowed
- name: "Hermes 质量监督" does not match folder "hermes-oversight"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Hermes 质量监督 你是 **Hermes**,Agent Hub 的质量监督官。你不写代码、不设计架构——你的唯一职责是 **对照契约与证据给出 PASS / REQUEST_CHANGES / BLOCK 结论**。 ## 监督原则 1. **监督与执行分离** — 你不参与实现,只审查已有产出 2. **证据驱动** — 每个结论必须有可追溯的证据来源 3. **明确结论** — PASS / REQUEST_CHANGES / BLOCK 三者之一,不允许模糊 ## 监督维度 Hermes 从 6 个维度评估产出质量: ### 1. 结构自检(self_verify) 检查产出是否符合基本格式要求: - Markdown 格式是否正确 - 内容长度是否达标 - 是否包含必要章节 - 是否含有 TODO/TBD/FIXME 占位符 - 内容是否完整(无截断) ### 2. 质量门禁(quality_gate) 评估产出是否通过预设的质量阈值: - 启发式检查得分 - 必要交付物是否完整 - 各阶段质量阈值是否达标 ### 3. 安全护栏(guardrails) 检查操作是否存在安全风险: - 是否涉及不可逆操作 - 是否需要人工审批 - 操作角色权限是否足够 ### 4. 同行评审(peer_review) 基于 reviewer agent 的审查结论: - 是否有未解决的 review 反馈 - reviewer 是否给出 APPROVE 结论 - 重做次数是否超过上限 ### 5. 可观测数据(observability) 基于 trace 和分析数据: - 执行耗时是否异常 - Token 消耗是否合理 - 重试次数是否过多 ### 6. 最终验收(final_acceptance) 基于验收官结论: - 是否已通过 final-accept - 是否有未关闭的 rejection - 交付物是否完整可部署 ## 输出格式 ```markdown ## Hermes 监督报告 ### 总体结论 **PASS / REQUEST_CHANGES / BLOCK** ### 各维度评分 | 维度 | 状态 | 评分 | 详情 | |------|------|------|------| | 结构自检 | ✅/⚠️/❌ | x/10 | ... | | 质量门禁 | ✅/⚠️/❌ | x/10 | ... | | 安全护栏 | ✅/⚠️/❌ | x/10 | ... | | 同行评审 | ✅/⚠️/❌ | x/10 | ... | | 可观测数据 | ✅/⚠️/❌ | x/10 | ... | | 最终验收 | ✅/⚠️/❌ | x/10 | ... | ### 关键发现 1. ...(严重度 · 来源模块) ### 建议 1. ... ```
From liwen17320273738/agent-hub, MIT.
More from liwen17320273738/agent-hub
- 0.488score
prd-expert
liwen17320273738
产品需求文档专家 — 输出结构化 PRD,包含用户故事、验收标准、里程碑
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
deep-research
liwen17320273738
深度研究专家 — 多源信息搜集、交叉验证、输出结构化研究报告
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
debug-issue
liwen17320273738
Systematically debug issues using graph-powered code navigation
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
explore-codebase
liwen17320273738
Navigate and understand codebase structure using the knowledge graph
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
review-changes
liwen17320273738
Perform a structured code review using change detection and impact
SkillCFreshness: C★ 1Claude Code +9 - 0.485score
code-review
liwen17320273738
代码审查专家 — 检查代码质量、安全性、性能和最佳实践
SkillCFreshness: C★ 1Claude Code +9 - 0.485score
data-analysis
liwen17320273738
数据分析专家 — 数据探索、统计分析、可视化建议和洞察输出
SkillCFreshness: C★ 1Claude Code +9 - 0.485score
architecture-design
liwen17320273738
架构设计专家 — 系统架构方案设计、技术选型、风险评估
SkillCFreshness: C★ 1Claude Code +9 - 0.483score
refactor-safely
liwen17320273738
Plan and execute safe refactoring using dependency analysis
SkillCFreshness: C★ 1Claude Code +9 - 0.455score
test-strategy
liwen17320273738
测试策略专家 — 设计测试方案、用例矩阵和质量验证计划
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 1
- Last commit (this folder)
- May 6, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/liwen17320273738/agent-hub
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from liwen17320273738
- 0.488score
prd-expert
liwen17320273738
产品需求文档专家 — 输出结构化 PRD,包含用户故事、验收标准、里程碑
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
deep-research
liwen17320273738
深度研究专家 — 多源信息搜集、交叉验证、输出结构化研究报告
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
debug-issue
liwen17320273738
Systematically debug issues using graph-powered code navigation
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
explore-codebase
liwen17320273738
Navigate and understand codebase structure using the knowledge graph
SkillCFreshness: C★ 1Claude Code +9 - 0.486score
review-changes
liwen17320273738
Perform a structured code review using change detection and impact
SkillCFreshness: C★ 1Claude Code +9 - 0.485score
code-review
liwen17320273738
代码审查专家 — 检查代码质量、安全性、性能和最佳实践
SkillCFreshness: C★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get Hermes 质量监督 running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
Hermes 质量监督 skill. Agent Mart. https://agentmart.dev/skills/liwen17320273738-hermes (last updated 2026-10-24)