← 返回 Skills 市场
254
总下载
0
收藏
0
当前安装
11
版本数
在 OpenClaw 中安装
/install kcard
功能描述
Knowledge Card generator. Extracts key knowledge from user-provided material (text, files, URLs), determines optimal card type (concept/memo/process/comparis...
使用说明 (SKILL.md)
Knowledge Card Generator
Workflow
1. Parse Input Material
Accept any of: pasted text, file path, URL, or image.
- If URL → fetch and extract main content by
web_fetchtool - If file → read it
Extract 3–7 core knowledge points. Prioritize: definitions > mechanisms > examples > details.
2. Determine Card Type
Pick the best-fit type based on content nature:
| Type | Trigger Pattern | Structure |
|---|---|---|
| Concept | Defines a term, theory, model | Term → Definition → Analogy → Key Points |
| Memo | Steps, commands, configs, references | Title → Ordered Steps → Tips / Gotchas |
| Process | Sequential workflow or lifecycle | Title → Phases → Steps per Phase → Output |
| Comparison | Compares 2+ items | Dimension → Item A vs Item B → Verdict |
If unsure, default to Concept card.
3. Apply Cognitive Science Principles
Follow these when structuring the card:
- Chunking: Group related info into 3–5 chunks max per section
- Dual Coding: Pair text with a visual metaphor or emoji anchors
- Elaboration: Add a "Why It Matters" or analogy section
- Spaced Repetition Cue: End with a self-test question (❓)
- Progressive Disclosure: Layer from simple to detailed
4. Generate Markdown
Use the template from references/card-templates.md. Output a single Markdown file.
Naming convention: kcard_\x3Ctopic>_\x3Ctype>.md (e.g., kcard_react-hooks_concept.md)
Save to user's specified path or default: ~/.openclaw/workspace/kcards/
5. Render to Image
Run the rendering script to convert the Markdown into a PNG:
python \x3Cskill-dir>/scripts/render_card.py \x3Cpath-to-markdown> [--output \x3Coutput.png>] [--theme \x3Cwarm|cool|girly|tech>] [--width 800]
Default theme: warm. Default output: same path with .png extension.
The script:
- Parses Markdown to styled HTML
- Renders HTML to image via headless browser or html2image
- Returns the output path
Present the final image to the user.
Output Format
Always output:
- The Markdown source file (for editing/reuse)
- The rendered PNG image
- A brief one-line summary of what the card covers
Notes
- Keep cards concise: one concept per card, maximum 195 words
- Use Chinese or English based on input language
- Emoji anchors are encouraged but keep them minimal (1–3 per section)
- For batch requests, process cards sequentially and summarize all outputs
安全使用建议
This skill appears to be what it says: it generates Markdown knowledge cards and runs a local Python renderer to produce PNGs. Before installing/using it, consider: (1) you will need Python packages (markdown, html2image, pillow) and a Chrome/Edge executable — the script will try to find a browser or use CHROME_PATH/EDGE_PATH; (2) it writes files to ~/.openclaw/workspace/kcards/ by default — change the path if you don't want files in your home directory; (3) rendering uses a headless browser and will load external resources (Google Fonts and any remote images linked in the Markdown), which can cause network requests that reveal your IP to third-party servers — avoid feeding sensitive or private URLs/images unless you trust them or are in a sandbox; (4) review the included scripts if you want to be extra cautious (they are local and readable). If you need tighter isolation, run the renderer in a restricted environment or specify a controlled browser path.
功能分析
Type: OpenClaw Skill
Name: kcard
Version: 1.6.5
The kcard skill is a legitimate tool for generating visual knowledge cards from text, files, or URLs. It uses a Python script (scripts/render_card.py) to convert Markdown into styled HTML and then renders it to a PNG image using a headless browser (via the html2image library). The code and instructions in SKILL.md and scripts/render_card.py are consistent with the stated purpose and do not exhibit signs of data exfiltration, malicious execution, or unauthorized access.
能力标签
能力评估
Purpose & Capability
Name/description align with requested behavior: the skill extracts knowledge, creates Markdown cards, and renders them to PNG via an included renderer script. There are no unrelated env vars, binaries, or config paths required.
Instruction Scope
SKILL.md stays on task (accepts text/file/URL/image, uses web_fetch for URLs, reads files, saves markdown and PNG). Minor scope notes: it instructs the agent to fetch arbitrary URLs (via the agent's web_fetch tool) and to save outputs under ~/.openclaw/workspace/kcards/ by default; rendering will load fonts and any remote images referenced in the Markdown via a headless browser, which may trigger external network requests.
Install Mechanism
No install spec is provided (instruction-only), but the included Python script requires runtime dependencies (markdown, html2image, pillow, optional Pygments) and a local Chrome/Edge executable. The lack of an automated install step means the host must manually install these; this is expected but worth noting.
Credentials
The skill declares no required env vars or credentials. The renderer optionally reads CHROME_PATH/EDGE_PATH if set to locate a browser, which is reasonable for rendering.
Persistence & Privilege
always is false and the skill does not request permanent platform-level privileges or modify other skills. It will write output files to the user's workspace directory (~/ .openclaw/workspace/kcards/) which is consistent with its purpose.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install kcard - 安装完成后，直接呼叫该 Skill 的名称或使用
/kcard触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.6.5
- Replaced Chinese card type names (概念卡, 备忘卡, 流程卡, 对比卡) with English equivalents (Concept, Memo, Process, Comparison) in all documentation and workflow steps.
- Updated the card type table and trigger patterns to match the new English terminology.
- No functional or workflow changes; documentation now aligns with English card type names for improved clarity and consistency.
v1.6.4
kcard 1.6.4
- Updated documentation to remove image input parsing and OCR/visual analysis steps from workflow.
- Clarified that only pasted text, file paths, or URLs are accepted as input sources.
- No functional or code changes; documentation only.
v1.6.3
No user-visible changes; documentation updated only.
- SKILL.md updated to clarify image input handling: now explicitly states OCR uses `paddleocr` or LLM-based visual analysis.
- No changes to code or features.
v1.6.2
- Added explicit instruction to use the `web_fetch` tool when extracting main content from URLs.
- All other workflow and features remain unchanged.
v1.6.1
- Minor update to knowledge extraction instructions: "trivia" changed to "details" for core knowledge points.
- No functional or workflow changes.
v1.6.0
- Updated documentation to include "girly" and "tech" as new available card rendering themes.
- change metal style bg color.
v1.1.1
No user-facing changes in this version.
- No file changes detected from the previous version.
- SKILL.md content remains the same.
v1.1.0
kcard 1.1.0
- No file changes detected in this release.
- No updates or modifications to skill logic, workflow, or documentation.
- Functionality and features remain the same as the previous version.
v1.0.2
kcard 1.0.2
- Increased the maximum allowed words per card from 190 to 195.
- No other changes detected.
v1.0.1
kcard v1.0.1
- Updated default fallback card type wording from "概念卡" to "Concept card" for consistency.
- Adjusted naming conventions and default save paths for Markdown output to use home directory (`~`) and English suffixes (e.g., `_concept.md`).
- Revised workflow and card structure language to prioritize English and simplify instructions (e.g., "Why It Matters" instead of "为什么重要").
- Reduced the maximum allowed card length from 300 to 190 words.
- Minor rewording and formatting improvements throughout documentation.
v1.0.0
Initial release of Knowledge Card (kcard) generator skill.
- Extracts key knowledge from user-provided text, files, URLs, or images.
- Automatically selects optimal card type: concept, memo, process, or comparison.
- Structures cards with cognitive science principles for better learning and memory.
- Outputs both Markdown and a rendered image (PNG) of the card.
- Provides a concise summary of each card’s content.
- Supports both Chinese and English materials.
元数据
常见问题
Knowledge card creator, your memory notes 是什么？
Knowledge Card generator. Extracts key knowledge from user-provided material (text, files, URLs), determines optimal card type (concept/memo/process/comparis... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 254 次。
如何安装 Knowledge card creator, your memory notes？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install kcard」即可一键安装，无需额外配置。
Knowledge card creator, your memory notes 是免费的吗？
是的，Knowledge card creator, your memory notes 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Knowledge card creator, your memory notes 支持哪些平台？
Knowledge card creator, your memory notes 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Knowledge card creator, your memory notes？
由 Jay（@goog）开发并维护，当前版本 v1.6.5。
推荐 Skills