Agent skill

Canvas Discussion Facilitator

by vishalsachdev in vishalsachdev/canvas-mcp

Discussion forum facilitator for Canvas LMS. An agent skill from vishalsachdev/canvas-mcp.

MITAuto-check passedAgent Workflows

Install Canvas Discussion Facilitator

skills CLI
$ npx skills add vishalsachdev/canvas-mcp --skill canvas-discussion-facilitator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install vishalsachdev/canvas-mcp canvas-discussion-facilitator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/vishalsachdev/canvas-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/canvas-discussion-facilitator .claude/skills/canvas-discussion-facilitator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
canvas-discussion-facilitator
GitHub stars
286
Token cost
~2.6k tokens
SKILL.md length
1,284 words
Files
1
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Discussion forum facilitator for Canvas LMS. An agent skill from vishalsachdev/canvas-mcp.

  • Works in 7 steps: Identify the Course → Browse Discussion Topics → View Posts in a Discussion → …
  • Phrases include discussion posts
  • SKILL.md covers Prerequisites, Steps, Educator Use Cases and Student Use Cases, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Canvas Discussion Facilitator is an agent skill from vishalsachdev/canvas-mcp. Discussion forum facilitator for Canvas LMS. Helps students and educators browse, read, reply to, and create discussion posts. Trigger phrases include "discussion posts", "reply to students", "check discussions", "forum participation", "post a discussion", or any discussion-related Canvas task.

Its SKILL.md is about 2.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering MCP servers. The repository describes itself as: Canvas LMS MCP server — up to 102 tools and 8 agent skills for students & educators. Works with Claude, Cursor, Codex, and 40+ agents. The licence is MIT.

When your agent uses it

  • Phrases include discussion posts
  • Reply to students
  • Check discussions
  • Forum participation

Example prompts

  • “discussion posts”
  • “reply to students”
  • “check discussions”
  • “/canvas-discussion-facilitator”

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Identify the Course
  2. Browse Discussion Topics
  3. View Posts in a Discussion
  4. Read a Specific Post in Full
  5. Reply to a Post
  6. Post a New Top-Level Entry
  7. Create a New Discussion Topic

What it can do on your machine

Read from SKILL.md and the folder at commit b054b91. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Canvas Discussion Facilitator loads about 2.6k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 1,284 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~81
When it runs · the whole SKILL.md, loaded when a task matches
~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from vishalsachdev/canvas-mcp at commit b054b91, republished under its MIT licence (© vishalsachdev). 1,284 words, ~2,603 tokens.

Download SKILL.mdSave it as .claude/skills/canvas-discussion-facilitator/SKILL.md (or your agent's skills folder).
name
canvas-discussion-facilitator
description
Discussion forum facilitator for Canvas LMS. Helps students and educators browse, read, reply to, and create discussion posts. Trigger phrases include "discussion posts", "reply to students", "check discussions", "forum participation", "post a discussion", or any discussion-related Canvas task.

Canvas Discussion Facilitator

Facilitate discussion forum activity in Canvas LMS -- browse topics, read posts, reply to students, create new discussions, and monitor participation. Works for both students and educators.

Prerequisites

  • Canvas MCP server must be running and connected to the agent's MCP client.
  • The authenticated user can have any Canvas role (student, TA, or instructor). Tool access is governed by Canvas API permissions.
  • FERPA-conscious handling (educators): Set ENABLE_DATA_ANONYMIZATION=true in the Canvas MCP server environment to anonymize supported student identity fields in output. This control does not by itself establish compliance.

Steps

1. Identify the Course

Ask the user which course to work with. Accept a course code, Canvas ID, or ask them to pick from a list.

If the user does not specify, use list_courses to show active courses and prompt:

Which course should I look at discussions for?

2. Browse Discussion Topics

Call the MCP tool list_discussion_topics with the course identifier to retrieve all discussion forums.

Parameters:

  • course_identifier -- course code or Canvas ID
  • include_announcements -- set to false (default) to see only discussions, or true to include announcements

Data to surface per topic:

  • Topic ID and title
  • Author name
  • Posted date
  • Number of entries (if available)
  • Whether the topic is pinned or locked

Present the list so the user can pick a topic to drill into.

3. View Posts in a Discussion

Once the user selects a topic, call list_discussion_entries to retrieve posts.

Parameters:

  • course_identifier -- course code or Canvas ID
  • topic_id -- the selected discussion topic ID
  • include_full_content -- set to true to see complete post bodies
  • include_replies -- set to true to see threaded replies

Data to surface per entry:

  • Author name
  • Posted date
  • Message content (or preview)
  • Number of replies
  • Entry ID (needed for replying)
4. Read a Specific Post in Full

If a post is truncated or the user wants the complete text, call get_discussion_entry_details.

Parameters:

  • course_identifier -- course code or Canvas ID
  • topic_id -- the discussion topic ID
  • entry_id -- the specific entry ID
  • include_replies -- set to true to also fetch all replies to this entry

Present the full post content along with any replies, timestamps, and author information.

5. Reply to a Post

When the user wants to respond to a specific post, call reply_to_discussion_entry.

Parameters:

  • course_identifier -- course code or Canvas ID
  • topic_id -- the discussion topic ID
  • entry_id -- the entry being replied to
  • message -- the reply content (HTML is supported)

Before sending, always:

  1. Show the draft reply to the user for confirmation
  2. Reference the original post so the user can verify context
  3. Only send after explicit approval
6. Post a New Top-Level Entry

When the user wants to add a new post to an existing discussion (not a reply), call post_discussion_entry.

Parameters:

  • course_identifier -- course code or Canvas ID
  • topic_id -- the discussion topic ID
  • message -- the post content (HTML is supported)

Show the draft to the user and confirm before posting.

7. Create a New Discussion Topic

When the user needs an entirely new discussion forum, call create_discussion_topic.

Parameters:

  • course_identifier -- course code or Canvas ID
  • title -- the discussion title
  • message -- the opening post / prompt for the discussion
  • delayed_post_at -- (optional) ISO 8601 datetime to schedule the discussion to appear later
  • lock_at -- (optional) ISO 8601 datetime to automatically lock the discussion
  • require_initial_post -- set to true if students must post before seeing classmates' responses
  • pinned -- set to true to pin the topic to the top of the discussion list

Confirm the title, content, and any scheduling options with the user before creating.

Educator Use Cases

Monitor Participation
  1. Call list_discussion_topics to get all discussion forums in the course.
  2. For each topic, call list_discussion_entries to retrieve all posts.
  3. Cross-reference posters against the class roster (use list_users or list_submissions to get enrolled students).
  4. Identify students who have not posted in any active discussion.

Present participation as a summary:

## Discussion Participation: [Course Name]

### Topic: "Week 5 Reading Response" (due Mar 3)
- **Posted:** 28 / 32 students (88%)
- **Not posted:** Student_a1b2c3d, Student_e4f5g6h, Student_i7j8k9l, Student_m0n1o2p

### Topic: "Case Study Analysis" (due Mar 5)
- **Posted:** 15 / 32 students (47%)
- **Not posted:** [17 students listed]

### Students Missing Multiple Discussions
- Student_a1b2c3d -- missing 2 discussions
- Student_e4f5g6h -- missing 2 discussions
Send Reminders About Participation

After identifying non-participants, offer to:

  1. Post an announcement using create_announcement with a general reminder about discussion deadlines.
  2. Message specific students using send_conversation to contact students who are behind on participation.
Draft Thoughtful Replies

When an educator wants to reply to student posts:

  1. Read the full post with get_discussion_entry_details (include replies for context).
  2. Draft a reply that acknowledges the student's points, asks follow-up questions, or connects ideas to course material.
  3. Show the draft for educator review and revision before calling reply_to_discussion_entry.

Student Use Cases

Browse and Catch Up on Discussions
  1. Call list_discussion_topics to see all active discussions.
  2. Call list_discussion_entries with include_full_content=true to read posts.
  3. Summarize key themes or arguments across posts to help the student catch up quickly.
Show full SKILL.md (528 more words)Show less
Reply to Classmates
  1. Read the target post with get_discussion_entry_details.
  2. Help the student draft a reply that engages substantively with the original post.
  3. Confirm and send via reply_to_discussion_entry.
Post a New Entry
  1. Review existing posts with list_discussion_entries to avoid duplicating points already made.
  2. Help the student draft a post that adds a distinct perspective or builds on the conversation.
  3. Confirm and send via post_discussion_entry.

MCP Tools Used

ToolPurpose
list_coursesFind the target course
list_discussion_topicsBrowse all discussion forums in a course
list_discussion_entriesView posts within a discussion topic
get_discussion_entry_detailsRead a single post with full content and replies
get_discussion_topic_detailsGet metadata about a discussion topic
reply_to_discussion_entryReply to an existing post
post_discussion_entryAdd a new top-level post to a discussion
create_discussion_topicCreate a new discussion forum
create_announcementPost a course announcement (educator)
send_conversationMessage specific students through Canvas (educator)
list_usersGet enrolled students for participation tracking (educator)

Best Practices

  • Read before replying. Always read the full post and its replies before drafting a response. This avoids repeating points and shows engagement with the conversation.
  • Check for existing similar posts. Before posting a new entry, scan existing posts to avoid duplicating what others have already said. Build on or respectfully challenge existing arguments instead.
  • Reference specific points. When replying, quote or paraphrase specific parts of the original post. This makes the reply more substantive and shows careful reading.
  • Confirm before sending. Always show draft content to the user for approval before calling any write tool (reply_to_discussion_entry, post_discussion_entry, create_discussion_topic, create_announcement).
  • Respect discussion settings. Some discussions require an initial post before viewing others (require_initial_post). If a student cannot see other posts, they need to post first.
  • Mind the timing. Check delayed_post_at and lock_at dates on topics. Do not attempt to post to locked discussions.
  • Anonymization for educators. When reviewing student participation, rely on anonymous IDs if anonymization is enabled. The Canvas MCP server preserves functional user IDs for messaging while anonymizing display names.

Example

User (educator): "Show me who hasn't posted in the Week 5 discussion for CS 101."

Agent: Calls list_discussion_topics to find the Week 5 topic, then list_discussion_entries to get all posts, then cross-references with enrolled students. Outputs a participation summary listing students who have not posted.

User: "Send them a reminder."

Agent: Drafts a reminder message referencing the discussion deadline, shows it for confirmation, then calls send_conversation to message the non-participating students.


User (student): "I need to reply to Maria's post in the Case Study discussion."

Agent: Calls list_discussion_topics to find the Case Study topic, then list_discussion_entries to locate Maria's post, then get_discussion_entry_details to read the full content. Helps draft a reply that references Maria's key arguments, shows the draft for confirmation, then calls reply_to_discussion_entry.

Notes

  • This skill pairs well with canvas-morning-check for educators who want a full course status before diving into discussions.
  • Discussion entries support HTML content. When drafting posts, use paragraph tags for readability but avoid overly complex markup.
  • Canvas API permissions determine what each user can do. Students cannot create discussion topics unless the course allows it. Educators have full access.
  • For courses with many discussions, suggest filtering by recent or pinned topics to keep the workflow focused.

© vishalsachdev, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/canvas-discussion-facilitator of vishalsachdev/canvas-mcp.

Open the folder on GitHubat commit b054b91

Compare with similar skills

Canvas Discussion Facilitator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Canvas Discussion Facilitator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Canvas Discussion Facilitator this skillvishalsachdev/canvas-mcp286—~2.6kAutomated safety check: PassMIT
Learn MCPfancyboi999/ai-engineering-from-scratch-zh1.2k—~1.5kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k4 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official38k11 repos~3.1kAutomated safety check: PassApache-2.0
Microsoft Skill CreatorMicrosoftDocs/mcp1.9k3 repos~2.1kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Learn MCP

    fancyboi999/ai-engineering-from-scratch-zh

    AI Engineering from Scratch 中 Model Context Protocol (MCP) 路线的专注交互 tutor。

    1.2k GitHub stars~1.5k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 4 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    38k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Microsoft Skill Creator

    MicrosoftDocs/mcp

    Official

    Create agent skills for Microsoft technologies using official documentation.

    1.9k GitHub starsUsed in 3 repos~2.1k tokens
    Agent WorkflowsAuto-check passed
  • Furniture Fit Check

    pascalorg/editor

    Checks whether a sofa, table, bed or appliance fits in a measured Pascal room and reports only what the evidence supports, or asks for the missing measurements.

    25k GitHub stars~5.1k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from vishalsachdev/canvas-mcp

All 8 skills in this repo
  • Canvas Accessibility Auditor

    vishalsachdev/canvas-mcp

    Accessibility audit and remediation for Canvas LMS courses. An agent skill from vishalsachdev/canvas-mcp.

    286 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Canvas Course Builder

    vishalsachdev/canvas-mcp

    Scaffold complete Canvas LMS course structures from specs, templates, or existing courses.

    286 GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Canvas Course Qc

    vishalsachdev/canvas-mcp

    Learning designer quality check for Canvas LMS courses. An agent skill from vishalsachdev/canvas-mcp.

    286 GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Canvas Morning Check

    vishalsachdev/canvas-mcp

    Educator morning course health check for Canvas LMS. An agent skill from vishalsachdev/canvas-mcp.

    286 GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Canvas Peer Review Manager

    vishalsachdev/canvas-mcp

    Educator peer review management for Canvas LMS. An agent skill from vishalsachdev/canvas-mcp.

    286 GitHub stars~2.8k tokensUpdated today
    Auto-check passed
  • Canvas Week Plan

    vishalsachdev/canvas-mcp

    Student weekly assignment planner for Canvas LMS. An agent skill from vishalsachdev/canvas-mcp.

    286 GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Categories

Questions about Canvas Discussion Facilitator

What does Canvas Discussion Facilitator do?

Discussion forum facilitator for Canvas LMS. An agent skill from vishalsachdev/canvas-mcp. Canvas Discussion Facilitator is an agent skill from vishalsachdev/canvas-mcp. Discussion forum facilitator for Canvas LMS.

When should I use Canvas Discussion Facilitator?

Canvas Discussion Facilitator fits situations like: phrases include discussion posts; reply to students; check discussions; forum participation.

How do I install Canvas Discussion Facilitator in Claude Code?

Run `npx skills add vishalsachdev/canvas-mcp --skill canvas-discussion-facilitator -a claude-code`. Or copy the skill folder (skills/canvas-discussion-facilitator in vishalsachdev/canvas-mcp) into .claude/skills/canvas-discussion-facilitator in your project. Claude Code loads it when a task matches its description.

How do I install Canvas Discussion Facilitator in Codex?

Run `npx skills add vishalsachdev/canvas-mcp --skill canvas-discussion-facilitator -a codex`. Or copy the skill folder (skills/canvas-discussion-facilitator in vishalsachdev/canvas-mcp) into .agents/skills/canvas-discussion-facilitator in your project. Codex loads it when a task matches its description.

Can I use Canvas Discussion Facilitator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add vishalsachdev/canvas-mcp --skill canvas-discussion-facilitator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/canvas-discussion-facilitator, .gemini/skills/canvas-discussion-facilitator, .github/skills/canvas-discussion-facilitator and .opencode/skills/canvas-discussion-facilitator in your project.

What does Canvas Discussion Facilitator need to run?

SKILL.md names no scripts, command-line tools or credentials: Canvas Discussion Facilitator is instructions for the agent only.

Does Canvas Discussion Facilitator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Canvas Discussion Facilitator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Canvas Discussion Facilitator use?

Canvas Discussion Facilitator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Canvas Discussion Facilitator use?

About 2.6k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Canvas Discussion Facilitator?

Skills that share tags, products or a category with Canvas Discussion Facilitator: Learn MCP (fancyboi999/ai-engineering-from-scratch-zh, 1.2k stars), MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars) and MCP Integration for Plugins (anthropics/claude-plugins-official, 38k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Canvas Discussion Facilitator?

vishalsachdev (a GitHub user) maintains it in vishalsachdev/canvas-mcp, which has 286 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on October 10, 2026.

Source: vishalsachdev/canvas-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.