canvas-peer-review-manager

Name: canvas-peer-review-manager
Author: vishalsachdev

167stars54forks

How to install canvas-peer-review-manager?

vishalsachdev/canvas-mcp/canvas-peer-review-manager

$npx -y skills add vishalsachdev/canvas-mcp --skill canvas-peer-review-manager

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# Canvas Peer Review Manager
2
3	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.
4
5	## Prerequisites
6
7	- Canvas MCP server must be running and connected to the agent's MCP client (e.g., Claude Code, Cursor, Codex, OpenCode).
8	- The authenticated user must have an educator or instructor role in the target Canvas course.
9	- The assignment must have peer reviews enabled in Canvas (either manual or automatic assignment).
10	- FERPA compliance: Set `ENABLE_DATA_ANONYMIZATION=true` in the Canvas MCP server environment to anonymize student names. When enabled, names render as `Student_xxxxxxxx` hashes while preserving functional user IDs for messaging.
11
12	## Steps
13
14	### 1. Identify the Assignment
15
16	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.
17
18	If the user does not specify, prompt:
19
20	> Which course and assignment would you like to check peer reviews for?
21
22	Use `list_courses` and `list_assignments` to help the user find the right identifiers.
23
24	### 2. Check Peer Review Completion
25
26	Call `get_peer_review_completion_analytics` with the course identifier and assignment ID. This returns:
27
28	- Overall completion rate (percentage)
29	- Number of students with all reviews complete, partial, and none complete
30	- Per-student breakdown showing completed vs. assigned reviews
31
32	Key data points to surface:
33
34	\| Metric \| What It Tells You \|
35	\|--------\|-------------------\|
36	\| Completion rate \| Overall health of the peer review cycle \|
37	\| "None complete" count \| Students who haven't started -- highest priority for reminders \|
38	\| "Partial complete" count \| Students who started but didn't finish \|
39	\| Per-student breakdown \| Exactly who needs follow-up \|
40
41	### 3. Review the Assignment Mapping
42
43	If the user wants to understand who is reviewing whom, call `get_peer_review_assignments` with:
44
45	- `include_names=true` for human-readable output
46	- `include_submission_details=true` for submission context
47
48	This shows the full reviewer-to-reviewee mapping with completion status.
49
50	### 4. Extract and Read Comments
51
52	Call `get_peer_review_comments` to retrieve actual comment text. Parameters:
53
54	- `include_reviewer_info=true` -- who wrote the comment
55	- `include_reviewee_info=true` -- who received the comment
56	- `anonymize_students=true` -- recommended when sharing results or working with sensitive data
57
58	This reveals what students actually wrote in their reviews.
59
60	### 5. Analyze Comment Quality
61
62	Call `analyze_peer_review_quality` to generate quality metrics across all reviews. The analysis includes:
63
64	- Average quality score (1-5 scale)
65	- Word count statistics (mean, median, range)
66	- Constructiveness analysis (constructive feedback vs. generic comments vs. specific suggestions)
67	- Sentiment distribution (positive, neutral, negative)
68	- Flagged reviews that fall below quality thresholds
69
70	Optionally pass `analysis_criteria` as a JSON string to customize what counts as high/low quality.
71
72	### 6. Flag Problematic Reviews
73
74	Call `identify_problematic_peer_reviews` to automatically flag reviews needing instructor attention. Flagging criteria include:
75
76	- Very short or empty comments
77	- Generic responses (e.g., "looks good", "nice work")
78	- Lack of constructive feedback
79	- Potential copy-paste or identical reviews
80
81	Pass custom `criteria` as a JSON string to override default thresholds.
82
83	### 7. Get the Follow-up List
84
85	Call `get_peer_review_followup_list` to get a prioritized list of students requiring action:
86
87	- `priority_filter="urgent"` -- students with zero reviews completed
88	- `priority_filter="medium"` -- students with partial completion
89	- `priority_filter="all"` -- everyone who needs follow-up
90	- `days_threshold=3` -- adjusts urgency calculation based on days since assignment
91
92	### 8. Send Reminders
93
94	Always use a dry run or review step before sending messages.
95
96	For targeted reminders, call `send_peer_review_reminders` with:
97
98	- `recipient_ids` -- list of Canvas user IDs from the analytics results
99	- `custom_message` -- optional custom text (a default template is used if omitted)
100	- `subject_prefix` -- defaults to "Peer Review Reminder"
101
102	Example flow:
103
104	1. Get incomplete reviewers from step 2
105	2. Extract their user IDs
106	3. Review the recipient list with the user
107	4. Send reminders after confirmation
108
109	For a fully automated pipeline, call `send_peer_review_followup_campaign` with just the c

People who liked this also viewed

6 picks

Type

canvas-peer-review-manager

167stars54forks

View on GitHub

How to install canvas-peer-review-manager?

vishalsachdev/canvas-mcp/canvas-peer-review-manager

$npx -y skills add vishalsachdev/canvas-mcp --skill canvas-peer-review-manager

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Canvas Peer Review Manager
2
3	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.
4
5	## Prerequisites
6
7	- Canvas MCP server must be running and connected to the agent's MCP client (e.g., Claude Code, Cursor, Codex, OpenCode).
8	- The authenticated user must have an educator or instructor role in the target Canvas course.
9	- The assignment must have peer reviews enabled in Canvas (either manual or automatic assignment).
10	- FERPA compliance: Set `ENABLE_DATA_ANONYMIZATION=true` in the Canvas MCP server environment to anonymize student names. When enabled, names render as `Student_xxxxxxxx` hashes while preserving functional user IDs for messaging.
11
12	## Steps
13
14	### 1. Identify the Assignment
15
16	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.
17
18	If the user does not specify, prompt:
19
20	> Which course and assignment would you like to check peer reviews for?
21
22	Use `list_courses` and `list_assignments` to help the user find the right identifiers.
23
24	### 2. Check Peer Review Completion
25
26	Call `get_peer_review_completion_analytics` with the course identifier and assignment ID. This returns:
27
28	- Overall completion rate (percentage)
29	- Number of students with all reviews complete, partial, and none complete
30	- Per-student breakdown showing completed vs. assigned reviews
31
32	Key data points to surface:
33
34	\| Metric \| What It Tells You \|
35	\|--------\|-------------------\|
36	\| Completion rate \| Overall health of the peer review cycle \|
37	\| "None complete" count \| Students who haven't started -- highest priority for reminders \|
38	\| "Partial complete" count \| Students who started but didn't finish \|
39	\| Per-student breakdown \| Exactly who needs follow-up \|
40
41	### 3. Review the Assignment Mapping
42
43	If the user wants to understand who is reviewing whom, call `get_peer_review_assignments` with:
44
45	- `include_names=true` for human-readable output
46	- `include_submission_details=true` for submission context
47
48	This shows the full reviewer-to-reviewee mapping with completion status.
49
50	### 4. Extract and Read Comments
51
52	Call `get_peer_review_comments` to retrieve actual comment text. Parameters:
53
54	- `include_reviewer_info=true` -- who wrote the comment
55	- `include_reviewee_info=true` -- who received the comment
56	- `anonymize_students=true` -- recommended when sharing results or working with sensitive data
57
58	This reveals what students actually wrote in their reviews.
59
60	### 5. Analyze Comment Quality
61
62	Call `analyze_peer_review_quality` to generate quality metrics across all reviews. The analysis includes:
63
64	- Average quality score (1-5 scale)
65	- Word count statistics (mean, median, range)
66	- Constructiveness analysis (constructive feedback vs. generic comments vs. specific suggestions)
67	- Sentiment distribution (positive, neutral, negative)
68	- Flagged reviews that fall below quality thresholds
69
70	Optionally pass `analysis_criteria` as a JSON string to customize what counts as high/low quality.
71
72	### 6. Flag Problematic Reviews
73
74	Call `identify_problematic_peer_reviews` to automatically flag reviews needing instructor attention. Flagging criteria include:
75
76	- Very short or empty comments
77	- Generic responses (e.g., "looks good", "nice work")
78	- Lack of constructive feedback
79	- Potential copy-paste or identical reviews
80
81	Pass custom `criteria` as a JSON string to override default thresholds.
82
83	### 7. Get the Follow-up List
84
85	Call `get_peer_review_followup_list` to get a prioritized list of students requiring action:
86
87	- `priority_filter="urgent"` -- students with zero reviews completed
88	- `priority_filter="medium"` -- students with partial completion
89	- `priority_filter="all"` -- everyone who needs follow-up
90	- `days_threshold=3` -- adjusts urgency calculation based on days since assignment
91
92	### 8. Send Reminders
93
94	Always use a dry run or review step before sending messages.
95
96	For targeted reminders, call `send_peer_review_reminders` with:
97
98	- `recipient_ids` -- list of Canvas user IDs from the analytics results
99	- `custom_message` -- optional custom text (a default template is used if omitted)
100	- `subject_prefix` -- defaults to "Peer Review Reminder"
101
102	Example flow:
103
104	1. Get incomplete reviewers from step 2
105	2. Extract their user IDs
106	3. Review the recipient list with the user
107	4. Send reminders after confirmation
108
109	For a fully automated pipeline, call `send_peer_review_followup_campaign` with just the c

People who liked this also viewed

6 picks

Type