在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。
文档
Proof Card Forge
试用Create SVG and Markdown trust cards from skill audits or release metadata
它能做什么
Use this skill when a builder wants a small trust badge that shows a skill was checked before publish.
技能文档
Proof Card Forge
Use this skill when a builder wants a small trust badge that shows a skill was checked before publish.
When To Use
- A skill audit JSON exists and needs a clean proof card.
- A GitHub README, landing page, or ClawHub listing needs a visual trust signal.
- A release needs a stable score, grade, status, and install link in one asset.
- A builder wants a proof card without hand-editing SVG.
Workflow
- Locate the audit JSON from Skill Package Doctor, or collect the skill name, score, grade, and URL.
- Run the bundled script:
python3 scripts/proof_card.py \
--audit skill-doctor.json \
--out-svg proof-card.svg \
--out-md proof-card.md \
--out-json proof-card.json
- If there is no audit file, pass
--name,--score,--grade, and--url. - If you intentionally replace existing artifacts, add
--force. - Review the generated SVG text, score, and link before sharing.
- Use the Markdown snippet in GitHub and the raw SVG in landing pages.
- Keep the card honest: refresh it after every material skill change.
- Read
references/source-manifest.jsononly when you need package provenance.
Review Rules
- Do not show
publish-readyunless the latest audit supports it. - Escape all names, descriptions, and links before rendering SVG or Markdown.
- Keep proof cards small, legible, and embeddable.
- Use plain labels: score, status, grade, version, and checked date.
- Link the card to the skill page, release page, or public audit artifact when available.
- If the score is missing, ask for the audit or mark the status as
unchecked. - Refuse accidental overwrites unless the user explicitly chooses
--force.
Output
Return:
- proof-card SVG path
- Markdown badge snippet
- JSON summary path when generated
- any missing inputs or honesty warnings
- suggested placement for README, landing page, and listing
Stop Conditions
Do not create or recommend a proof card when:
- the audit says
do-not-publish - the user asks to hide known errors
- the source score or status cannot be verified and the card would imply a completed audit
相关技能
把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。
以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。
诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。
从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。
编写、调试与调优 Playwright 测试,涵盖定位器策略、追踪诊断与 CI 友好的超时配置。
zack-dev-cm 的更多技能
浏览全部技能OpenClaw CWS Publisher is a public ClawHub Chrome Web Store publisher skill. Use it when the user says "chrome web store publisher", "extension release publi...
SOTA Agent is a public ClawHub SOTA-campaign skill for CV and DS work. Use it when the user says "sota agent", "state of the art benchmark scouting", or want...
Use when studying or normalizing Chinese lesson transcript/subtitle inputs with bundled public lesson data, learner docs, local export bundles, and pilot-fir...
OpenClaw YouTube Publisher is a public ClawHub YouTube publishing skill. Use it when the user says "youtube creator ops", "youtube publisher", "YouTube Studi...
Build source-backed research claim ledgers from drafts, literature matrices, notes, citation lists, PDFs, source packets, or reviewer comments. Use when the...
Install, wire, audit, and harden AgentMemory for AI coding agents and project workspaces. Use when Codex needs to adopt rohitg00/agentmemory, configure Codex...