← 返回 Skills 市场
michaeljmoody

Caring CourseForge

作者 michaeljmoody · GitHub ↗ · v1.0.3
cross-platform ⚠ suspicious
1302
总下载
2
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install caring-courseforge
功能描述
Create and manage online courses via the CourseForge API (caringcourseforge.com). Use when the user wants to create courses, modules, lessons, generate AI content, export to SCORM/xAPI, manage knowledge libraries, or interact with the CourseForge platform. Handles course building, content generation, quizzes, accessibility validation, and course export.
使用说明 (SKILL.md)

CourseForge

Build and manage courses on Caring CourseForge via the MCP client.

Source: npm — courseforge-mcp-client Publisher: Caring Consulting Co (caringcos.com)

Setup

  1. Install: npm install -g courseforge-mcp-client
  2. Set COURSEFORGE_API_KEY in your environment:
    • Get your key: caringcourseforge.com → Settings → API Keys
    • Store securely via your gateway environment config or shell profile (export COURSEFORGE_API_KEY=cf_prod_...). Do not store API keys in plaintext workspace files.
  3. Verify: courseforge-mcp starts without errors

Calling Tools

Use the wrapper script to call any of the 89 CourseForge tools:

node scripts/courseforge.mjs \x3Ctool_name> '\x3Cjson_args>'

The script requires COURSEFORGE_API_KEY in the environment (set via gateway env or shell profile).

node scripts/courseforge.mjs list_courses '{}'

Output is clean JSON (the MCP envelope is stripped automatically).

Available Tools (89)

  • Courses (7): list_courses, create_course, get_course, update_course, delete_course, get_course_settings, update_course_settings
  • Modules (5): create_module, update_module, delete_module, reorder_modules, get_module
  • Lessons (7): create_lesson, get_lesson, update_lesson, delete_lesson, reorder_lessons, move_lesson, duplicate_lesson
  • Content Blocks (6): add_content_block, get_content_block, update_content_block, delete_content_block, reorder_content_blocks, move_content_block
  • Course Management (3): validate_course, duplicate_module, export_course
  • Knowledge Library (5): list_collections, create_collection, list_documents, delete_document, search_knowledge
  • AI & Generation (26): ai_chat_assistant, ai_chat_with_research, generate_course_outline, generate_lesson_content, generate_quiz_from_content, generate_image, generate_job_aid_pdf, suggest_improvements, auto_fix_quality_issues, translate_content, summarize_document, convert_document_to_pdf, analyze_image, marketing_support_chat, web_search, fetch_url_content, get_youtube_metadata, get_youtube_captions, scrape_web_to_knowledge, upload_to_knowledge, manage_knowledge_files, search_user_media, list_storage_files, delete_storage_file, get_storage_usage, get_openapi_spec
  • Search & Media (2): search_stock_media, search_youtube
  • Recordings (1): list_recordings
  • API Keys (3): list_api_keys, create_api_key, revoke_api_key
  • Skills (2): list_skills, get_skill
  • Agentic UI Control (22): lock_canvas, unlock_canvas, refresh_canvas, notify_user, show_progress, request_confirmation, request_choice, scroll_to_element, select_element, expand_sidebar_item, focus_content_block, get_canvas_state, open_preview, close_preview, open_settings, toggle_sidebar, create_checkpoint, rollback_to_checkpoint, list_checkpoints, add_annotation, remove_annotation, highlight_issues

For full parameter details on any tool, read references/tools.md.

Common Workflows

Create a course from scratch

  1. create_course — title, description, difficulty (beginner/intermediate/advanced)
  2. create_module — for each section, pass courseId
  3. create_lesson — for each lesson, pass courseId + moduleId
  4. add_content_block — add text, images, quizzes to lessons
  5. validate_course — check quality and accessibility
  6. export_course — export to SCORM 1.2, SCORM 2004, xAPI, or HTML

AI-powered course generation

  1. generate_course_outline — provide topic, audience, difficulty → get full structure
  2. create_course + create_module + create_lesson — build the structure from the outline
  3. generate_lesson_content — auto-generate content for each lesson
  4. generate_quiz_from_content — create assessments from lesson content
  5. suggest_improvements — get AI suggestions for quality
  6. auto_fix_quality_issues — automatically fix issues

Use domain skills for specialized content

  1. list_skills — see all 17 available specialist skills
  2. get_skill — load a skill (e.g., "Instructional Designer", "HR Specialist")
  3. Use the skill context when generating content with ai_chat_assistant

Export a course

node scripts/courseforge.mjs export_course '{"courseId":"xxx","format":"scorm12"}'

Formats: scorm12, scorm2004, xapi, html

Content block types

When using add_content_block, the type field accepts:

  • text — Rich text/HTML content
  • image — Image with URL and alt text
  • video — Embedded video (YouTube, Vimeo, URL)
  • quiz — Interactive quiz/assessment
  • tabs — Tabbed content sections
  • accordion — Collapsible sections
  • callout — Highlighted callout box
  • divider — Visual separator
  • code — Code block with syntax highlighting
  • embed — External embed (iframe)
  • hotspot — Interactive image hotspot
  • flashcard — Flashcard for review
  • sortable — Drag-and-drop sorting activity
  • timeline — Timeline visualization
  • process — Step-by-step process
  • labeled_graphic — Image with labels
  • knowledge_check — Quick knowledge check
  • scenario — Branching scenario

Notes

  • All IDs are Firestore document IDs (alphanumeric strings)
  • Courses have a hierarchy: Course → Modules → Lessons → Content Blocks
  • The Knowledge Library stores reference documents that AI tools can use for generation
  • Agentic UI Control tools require the user to have the course editor open in their browser
  • Rate limits apply to AI generation tools based on the user's subscription tier
安全使用建议
This skill appears coherent for interacting with CourseForge. Before installing: (1) Verify the npm package (courseforge-mcp-client) and its publisher on npmjs.org to ensure it’s the official client; (2) keep your COURSEFORGE_API_KEY scoped/rotated and store it in your gateway secret store rather than plaintext; (3) be aware the wrapper may use npx to download the client at runtime (downloads third-party code); (4) if you don't trust automatic package fetches, install the package yourself from a vetted source and ensure the binary path used by the script points to that installation.
功能分析
Type: OpenClaw Skill Name: caring-courseforge Version: 1.0.3 The skill is classified as suspicious due to the broad and powerful capabilities exposed by its 89 tools, which include web search, URL content fetching, web scraping to a knowledge base, AI image generation, file deletion from Firebase Storage, and management of CourseForge API keys. While the `scripts/courseforge.mjs` wrapper demonstrates good security practices by explicitly filtering environment variables passed to child processes and safely invoking the `courseforge-mcp` client, the inherent power of these tools presents a significant attack surface for potential misuse if the AI agent were compromised (e.g., via prompt injection). There is no clear evidence of intentional malicious behavior within the skill's code or instructions, but the extensive capabilities warrant a 'suspicious' classification.
能力评估
✓ Purpose & Capability
Name, description, declared requirements (node + COURSEFORGE_API_KEY), and the included wrapper script all align with a CourseForge MCP client that calls CourseForge tools. The listed tools (course, module, lesson, AI generation, export, API key management, UI control) are consistent with a full-featured platform client.
✓ Instruction Scope
SKILL.md instructions are narrowly scoped: install the MCP client, set COURSEFORGE_API_KEY, and run the wrapper script with a tool name and JSON args. The runtime script only interacts with the MCP binary via stdin/stdout and limits environment variables passed to the child process.
ℹ Install Mechanism
No packaged install spec is required by the platform (instruction-only with an npm installation recommendation). The skill expects either a globally installed courseforge-mcp-client or will fall back to npx to fetch [email protected]. Installing or running packages from npm/npx is a moderate risk relative to pure instruction-only skills because it fetches third-party code at runtime; however this is proportionate for a client wrapper and the version is pinned in the script.
✓ Credentials
Only COURSEFORGE_API_KEY (declared) and a few standard env vars (HOME, PATH, NODE_PATH, npm_config_prefix) are used. The wrapper explicitly limits the env passed to the child process, reducing risk of unintended secret leakage. No unrelated credentials are requested.
✓ Persistence & Privilege
The skill does not request 'always: true' or other elevated persistence. It is user-invocable and can be invoked autonomously (platform default) which is expected for a tools wrapper. It does not modify other skills or system-wide settings.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install caring-courseforge
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /caring-courseforge 触发
  4. 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
v1.0.3
Version 1.0.3 of caring-courseforge - No file changes detected in this release. - No user-facing changes; documentation, features, and workflows remain the same.
v1.0.2
No user-facing changes in this version. - No file changes detected. - Documentation and functionality remain the same as the previous version.
v1.0.1
- Added OpenClaw metadata, clarifying environment and installation requirements (Node.js, API key). - Included install instructions for the CourseForge MCP client directly in the metadata. - Improved security guidance for API key storage—recommends using environment configs rather than plaintext files. - Added links to npm and publisher for clearer package sourcing and support. - No functional changes to available tools or workflows.
v1.0.0
Initial public release of CourseForge skill. - Create and manage online courses using the CourseForge API. - Supports workflows for course/module/lesson creation, content generation, quiz creation, and accessibility validation. - Includes 89 tools: courses, modules, lessons, content blocks, AI generation, knowledge library, SCORM/xAPI export, UI control, and more. - Detailed setup and environment configuration instructions provided. - AI-powered tools for course outline, lesson content, quizzes, content quality, translation, and more. - Supports exporting courses to SCORM 1.2, SCORM 2004, xAPI, and HTML formats.
元数据
Slug caring-courseforge
版本 1.0.3
许可证 —
累计安装 0
当前安装数 0
历史版本数 4
常见问题

Caring CourseForge 是什么？

Create and manage online courses via the CourseForge API (caringcourseforge.com). Use when the user wants to create courses, modules, lessons, generate AI content, export to SCORM/xAPI, manage knowledge libraries, or interact with the CourseForge platform. Handles course building, content generation, quizzes, accessibility validation, and course export. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1302 次。

如何安装 Caring CourseForge？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install caring-courseforge」即可一键安装，无需额外配置。

Caring CourseForge 是免费的吗？

是的，Caring CourseForge 完全免费（开源免费），可自由下载、安装和使用。

Caring CourseForge 支持哪些平台？

Caring CourseForge 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 Caring CourseForge？

由 michaeljmoody（@michaeljmoody）开发并维护，当前版本 v1.0.3。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191115 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论