- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add vishalsachdev/canvas-mcp --skill canvas-peer-review-manager -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add vishalsachdev/canvas-mcp --skill canvas-peer-review-manager -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add vishalsachdev/canvas-mcp --skill canvas-peer-review-manager -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add vishalsachdev/canvas-mcp --skill canvas-peer-review-manager -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/vishalsachdev/canvas-mcp/tree/HEAD/skills/canvas-peer-review-manager來自發布者
A complete peer review management workflow for educators using Canvas LMS. Monitor completion, analyze quality, identify students who need follow-up, send reminders, and export data -- all through MCP tool calls against the Canvas API.
ENABLE_DATA_ANONYMIZATION=true in the Canvas MCP server environment to anonymize supported student identity fields. When enabled, names render as Student_xxxxxxxx hashes while preserving functional user IDs for messaging. This control does not by itself establish compliance.Ask the user which course and assignment to manage peer reviews for. Accept a course code, Canvas ID, or course name, plus an assignment name or ID.
If the user does not specify, prompt:
Which course and assignment would you like to check peer reviews for?
Use list_courses and list_assignments to help the user find the right identifiers.
Call get_peer_review_completion_analytics with the course identifier and assignment ID. This returns:
Key data points to surface:
If the user wants to understand who is reviewing whom, call get_peer_review_assignments with:
include_names=true for human-readable outputinclude_submission_details=true for submission contextThis shows the full reviewer-to-reviewee mapping with completion status.
Call get_peer_review_comments to retrieve actual comment text. Parameters:
include_reviewer_info=true -- who wrote the commentinclude_reviewee_info=true -- who received the commentanonymize_students=true -- recommended when sharing results or working with sensitive dataThis reveals what students actually wrote in their reviews.
Call analyze_peer_review_quality to generate quality metrics across all reviews. The analysis includes:
Optionally pass analysis_criteria as a JSON string to customize what counts as high/low quality.
Call identify_problematic_peer_reviews to automatically flag reviews needing instructor attention. Flagging criteria include:
Pass custom criteria as a JSON string to override default thresholds.
Call get_peer_review_followup_list to get a prioritized list of students requiring action:
priority_filter="urgent" -- students with zero reviews completedpriority_filter="medium" -- students with partial completionpriority_filter="all" -- everyone who needs follow-updays_threshold=3 -- adjusts urgency calculation based on days since assignmentBoth send tools are two-call: the first call returns a preview and a confirmation_token and sends nothing; show the preview to the instructor, then call again with the token (and identical arguments) to send.
For targeted direct Inbox messages, call send_peer_review_inbox_messages with:
recipient_ids -- list of Canvas user IDs from the analytics resultscustom_message -- optional custom text (a default template is used if omitted)subject_prefix -- defaults to "Peer Review Reminder"Example flow:
For an automated pipeline, call send_peer_review_followup_campaign with the course identifier and assignment ID; the first call returns analytics plus a preview of urgent vs. gentle recipients and a token. This tool:
Warning: The campaign tool sends real messages. Always confirm with the instructor before running it.
Call extract_peer_review_dataset to export all peer review data for external analysis:
output_format="csv" or output_format="json"include_analytics=true -- appends quality metrics to the exportanonymize_data=true -- recommended for sharing or archivalsave_locally=true -- saves to a local file; set to false to return data inlineCall generate_peer_review_feedback_report for a formatted, shareable report:
report_type="comprehensive" -- full analysis with samples of low-quality reviewsreport_type="summary" -- executive overview onlyreport_type="individual" -- per-student breakdowninclude_student_names=false -- recommended for privacy-conscious reportingFor a completion-focused report (rather than quality-focused), use generate_peer_review_report with options for executive summary, student details, action items, and timeline analysis. This report can be saved to a file with save_to_file=true.
"How are peer reviews going?" Run steps 1-2. Present completion rate, highlight any concerning patterns (e.g., "Only 60% complete, 8 students haven't started").
"Who hasn't done their reviews?"
Run steps 1-2, then step 7 with priority_filter="urgent". List the students who need follow-up.
"Are the reviews any good?" Run steps 4-6. Present quality scores, flag generic or low-effort reviews, and surface recommendations.
"Send reminders to stragglers" Run steps 1-2 to identify incomplete reviewers, then step 8. Always confirm the recipient list before sending.
"Give me a full report" Run steps 2, 5, 6, and 10. Combine completion analytics with quality analysis into a comprehensive instructor report.
"Export everything for my records"
Run step 9 with output_format="csv" and anonymize_data=true for a privacy-conscious dataset.
User: "How are peer reviews going for Assignment 3 in BADM 350?"
Agent: Calls get_peer_review_completion_analytics and presents:
## Peer Review Status: Assignment 3
- **Completion rate:** 72% (23/32 students fully complete)
- **Partial:** 5 students (started but not finished)
- **Not started:** 4 students
### Students Needing Follow-up
**Not started (urgent):**
- Student_a8f7e23 (0 of 3 reviews done)
- Student_b2c91d4 (0 of 3 reviews done)
- Student_f5e67a1 (0 of 3 reviews done)
- Student_d9c34b2 (0 of 3 reviews done)
**Partial (needs nudge):**
- Student_c1d82e5 (1 of 3 reviews done)
- Student_e4f03a9 (2 of 3 reviews done)
User: "Send reminders to the ones who haven't started"
Agent: Confirms the 4 recipients, then calls send_peer_review_inbox_messages with their user IDs.
User: "Now check if the completed reviews are any good"
Agent: Calls analyze_peer_review_quality and presents quality scores, flags 3 reviews as too short, and recommends the instructor follow up with specific students.
anonymize_students=true or anonymize_data=true when reviewing data in shared contexts.send_peer_review_followup_campaign tool combines analytics and messaging: the first call previews recipients and returns a token, and the second call (with the token) sends real messages. Make the second call only after the instructor approves the preview.canvas-morning-check for a full course health overview that includes peer review status alongside submission rates and grade distribution.Educator peer review management for Canvas LMS. Tracks completion rates, analyzes comment quality, flags problematic reviews, sends targeted reminders, and generates instructor-ready reports. Trigger
---name: canvas-peer-review-managerdescription: Educator peer review management for Canvas LMS. Tracks completion rates, analyzes comment quality, flags…---# skills/canvas-peer-review-manager/SKILL.md總覽
Educator peer review management for Canvas LMS. Tracks completion rates, analyzes comment quality, flags problematic reviews, sends targeted reminders, and generates instructor-ready reports. Trigger phrases include "peer review status", "how are peer reviews going", "who hasn't reviewed", "review quality", or any peer review follow-up task.
常見問題
從發布者下載 skills/canvas-peer-review-manager/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/vishalsachdev/canvas-mcp。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。