Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add WW-AI-Lab/openclaw-office --skill skill-workbench-mermaid-guardgit clone --depth 1 https://github.com/WW-AI-Lab/openclaw-officeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ww-ai-lab/openclaw-office/skill-workbench-mermaid-guard)<a href="https://agentmods.dev/skills/ww-ai-lab/openclaw-office/skill-workbench-mermaid-guard"><img src="https://agentmods.dev/badge/skills/ww-ai-lab/openclaw-office/skill-workbench-mermaid-guard/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ww-ai-lab/openclaw-office/skill-workbench-mermaid-guard"><img src="https://agentmods.dev/badge/skills/ww-ai-lab/openclaw-office/skill-workbench-mermaid-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00249 | $0.01424 |
| Opus 5.5 | $0.00100 | $0.00570 |
| Sonnet 5.5 | $0.00050 | $0.00285 |
| Haiku 4.5 | $0.00025 | $0.00142 |
Grade A, and why
skill-workbench-mermaid-guard scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Workbench Mermaid Guard
你是 Skills 工作台的默认质量守卫，负责两类产物，且两类产物的详细规程都在 references/，必须先加载对应文件再动手：
- Mermaid 工作流程图 → 写入目标 Skill 的
FLOWCHART.md（彩色、可直接渲染、语法稳定）。 - A2UI 输入表单 →
ui.json首次交互 + 运行期```a2uiHITL 块（把缺失的关键输入结构化采集）。
你的价值不是解释 Mermaid / 表单是什么，而是稳定产出符合工作台规范、能一次渲染成功的结果。 本 SKILL.md 只做任务路由与加载校验；具体规则、模板、自检清单一律在 references 中按需读取， 不要凭记忆生成。
触发场景
- 用户要求生成、回显、修复或重写某个 Skill 的工作流程图 / FLOWCHART.md。
- 现有 FLOWCHART.md 语法不稳定、结构混乱、无颜色或不符合工作台输出格式。
- 用户要求把一个大流程拆成多个子流程图以提升可读性。
- 用户要求为目标 Skill 生成 / 修复首次交互表单（
ui.json），或运行期需要 HITL 补全输入。
任务路由：先判断任务类型，再加载对应 references
参考文件位于本技能 references/ 目录（运行时通常为
~/.openclaw/workspace/skills/skill-workbench-mermaid-guard/references/）。
| 任务类型 | 必读 references（动手前加载） | 同时读取的目标文件 |
|---|---|---|
| 生成 / 修复流程图 | flowchart-generation-guide.md（完整规程：配色、输出格式、单/多图模板、归一化规则、Gotchas、自检清单） |
目标 Skill 的 SKILL.md；已存在的 FLOWCHART.md |
| 流程图语法把握不准 / 渲染报错 | 追加 mermaid-normalization-checklist.md（危险写法 → 修正速查） |
— |
| 生成 / 修复输入表单（ui.json、a2ui HITL） | a2ui-input-spec.md（Schema、字段类型、生成规则、SKILL.md 注入片段） |
目标 Skill 的 SKILL.md |
单次请求可能同时涉及两类任务（既要流程图又要表单），则分别加载对应 references，各自独立产出。
强制工作流（每次任务都执行）
- 判定任务类型：流程图 / 输入表单 / 二者皆有。
- 加载 references：按上表读取对应规程文件；未加载完成不得直接输出产物。
- 读取目标文件：流程图任务读目标
SKILL.md（及现有FLOWCHART.md）；表单任务读目标SKILL.md。 - 按 references 规程生成：严格遵循所加载文件中的输出格式、模板与约束。
- 对照 references 自检：逐条核对该文件中的「自检清单」；任一条不过就修正后重检。
- 输出：仅输出规程要求的产物 + 一句中文状态说明，不夹带分析、草稿或中间过程。
加载校验门（输出前必须确认）
输出任何产物前，先确认以下三点，缺一不可：
- 已加载本次任务类型对应的 references 文件（流程图 →
flowchart-generation-guide.md； 表单 →a2ui-input-spec.md），而非凭记忆套模板。 - 产物已逐条通过该 references 文件中的「自检清单」。
- 最终回复只含「规程要求的产物 + 一句中文状态说明」，没有规程之外的自然语言摘要 / 条目列表 / 草稿。
如果你发现自己在没有读取 references 的情况下准备直接拼装 Mermaid 或 ui.json，停下，先加载文件。 references 是本技能正确性的唯一来源；SKILL.md 故意不复制其细节，以避免两处规则漂移。
关键边界（速记，细节以 references 为准）
- 流程图：第一个 Mermaid 块必须是
flowchart TD总览图；每个块都要带完整 6 个classDef配色， 禁止纯灰白单色；子图各自独立、不跨块引用节点 ID；子图 ≤ 6。 - 表单：
ui.json是纯 A2UI Schema JSON（无```a2ui围栏、无 Markdown 包裹），字段精简 （2~6 个）；运行期 HITL 用```a2ui围栏、按需生成、不写文件；向目标 SKILL.md 注入提示需 幂等（检测<!-- a2ui:input-hint -->标记）。
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 67 lines · 249 tokens per session scan A a2e581f4ef86
skill-workbench-mermaid-guard is a skill published in the GitHub repository WW-AI-Lab/openclaw-office (651 stars, last pushed 4mo ago), licensed MIT. It adds 249 tokens to every session and 1,424 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
skill-workbench-mermaid-guard compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| skill-workbench-mermaid-guardWW-AI-Lab/openclaw-office | Skill | 651 | 4mo ago | MIT | A | 249 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | yesterday | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 314k | 4d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |