canvas-bulk-grading

Name: canvas-bulk-grading
Author: vishalsachdev

167stars54forks

How to install canvas-bulk-grading?

vishalsachdev/canvas-mcp/canvas-bulk-grading

$npx -y skills add vishalsachdev/canvas-mcp --skill canvas-bulk-grading

Installs into the current project.

Summary

Bulk grading workflows for Canvas LMS assignments using rubrics. Covers single grading, batch grading, and code execution strategies with safety-first dry runs.

Files · 1

View on GitHub

SKILL.md

1	# Canvas Bulk Grading
2
3	Grade Canvas LMS assignments efficiently using rubric-based workflows. This skill requires the Canvas MCP server to be running and authenticated with an instructor or TA token.
4
5	## Prerequisites
6
7	- Canvas MCP server running and connected
8	- Authenticated with an educator (instructor/TA) Canvas API token
9	- Assignment must exist and have submissions to grade
10	- Rubric must already be created in Canvas and associated with the assignment (Canvas API cannot reliably create rubrics -- use the Canvas web UI for that)
11
12	## Workflow
13
14	### Step 1: Gather Assignment and Rubric Information
15
16	Before grading, retrieve the assignment details and its rubric criteria.
17
18	```
19	get_assignment_details(course_identifier, assignment_id)
20	```
21
22	Then get the rubric. Use `get_assignment_rubric_details` if the rubric is already linked to the assignment, or `list_all_rubrics` to browse all rubrics in the course:
23
24	```
25	get_assignment_rubric_details(course_identifier, assignment_id)
26	list_all_rubrics(course_identifier)
27	get_rubric_details(course_identifier, rubric_id)
28	```
29
30	Record the criterion IDs (often prefixed with underscore, e.g., `_8027`) and rating IDs from the rubric response. These are required for rubric-based grading.
31
32	### Step 2: List Submissions
33
34	Retrieve all student submissions to determine how many need grading:
35
36	```
37	list_submissions(course_identifier, assignment_id)
38	```
39
40	Note the `user_id` for each submission and the `workflow_state` (submitted, graded, pending_review). Count the submissions that need grading to determine which strategy to use.
41
42	### Step 3: Choose a Grading Strategy
43
44	Use this decision tree based on the number of submissions to grade:
45
46	```
47	How many submissions need grading?
48	\|
49	+-- 1-9 submissions
50	\| Use grade_with_rubric (one call per submission)
51	\|
52	+-- 10-29 submissions
53	\| Use bulk_grade_submissions (concurrent batch processing)
54	\| Set max_concurrent: 5, rate_limit_delay: 1.0
55	\| ALWAYS run with dry_run: true first
56	\|
57	+-- 30+ submissions OR custom grading logic needed
58	Use execute_typescript with bulkGrade function
59	99.7% token savings -- grading logic runs locally
60	ALWAYS run with dry_run: true first
61	```
62
63	### Strategy A: Single Grading (1-9 submissions)
64
65	Call `grade_with_rubric` once per student:
66
67	```
68	grade_with_rubric(
69	course_identifier,
70	assignment_id,
71	user_id,
72	rubric_assessment: {
73	"criterion_id": {
74	"points": <number>,
75	"rating_id": "<string>", // optional
76	"comments": "<string>" // optional per-criterion feedback
77	}
78	},
79	comment: "Overall feedback" // optional
80	)
81	```
82
83	### Strategy B: Bulk Grading (10-29 submissions)
84
85	Always dry run first. Build the grades dictionary mapping each user ID to their grade data, then validate before submitting:
86
87	```
88	bulk_grade_submissions(
89	course_identifier,
90	assignment_id,
91	grades: {
92	"user_id_1": {
93	"rubric_assessment": {
94	"criterion_id": {"points": 85, "comments": "Good analysis"}
95	},
96	"comment": "Overall feedback"
97	},
98	"user_id_2": {
99	"grade": 92,
100	"comment": "Excellent work"
101	}
102	},
103	dry_run: true, // VALIDATE FIRST
104	max_concurrent: 5,
105	rate_limit_delay: 1.0
106	)
107	```
108
109	Review the dry run output. If everything looks correct, re-run with `dry_run: false`.
110
111	### Strategy C: Code Execution (30+ submissions)
112
113	For large classes or custom grading logic, use `execute_typescript` to run grading locally. This avoids loading all submission data into the conversation context.
114
115	```
116	execute_typescript(code: `
117	import { bulkGrade } from './canvas/grading/bulkGrade.js';
118
119	await bulkGrade({
120	courseIdentifier: "COURSE_ID",
121	assignmentId: "ASSIGNMENT_ID",
122	gradingFunction: (submission) => {
123	// Custom grading logic runs locally -- no token cost
124	const notebook = submission.attachments?.find(
125	f => f.filename.endsWith('.ipynb')
126	);
127
128	if (!notebook) return null; // skip ungraded
129
130	return {
131	points: 100,
132	rubricAssessment: { "_8027": { points: 100 } },
133	comment: "Graded via automated review"
134	};
135	}
136	});
137	`)
138	```
139
140	Use `search_canvas_tools("grading", "signatures")` to discover available TypeScript modules and their function signatures before writing code.
141
142	## Token Efficiency
143
144	The three strategies have very different token costs:
145
146	\| Strategy \| When \| Token Cost \| Why \|
147	\|----------\|------\|------------\|-----\|
148	\| `grade_with_rubric` \| 1-9 submissions \| Low \| Few round-trips, small payloads \|
149	\| `bulk_grade_submissions` \| 10-29 submissions \| Medium \| One call with batch data \|
150	\| `execute_typescript` \| 30+ submissions \| Minimal \| Grading logic runs locally; only the code string is sent. 99.7% savings vs loading all submissions into context \|
151
152	The key insight: as submission count grows, s

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

canvas-bulk-grading

167stars54forks

View on GitHub

How to install canvas-bulk-grading?

vishalsachdev/canvas-mcp/canvas-bulk-grading

$npx -y skills add vishalsachdev/canvas-mcp --skill canvas-bulk-grading

Installs into the current project.

Summary

Bulk grading workflows for Canvas LMS assignments using rubrics. Covers single grading, batch grading, and code execution strategies with safety-first dry runs.

Files · 1

View on GitHub

SKILL.md

1	# Canvas Bulk Grading
2
3	Grade Canvas LMS assignments efficiently using rubric-based workflows. This skill requires the Canvas MCP server to be running and authenticated with an instructor or TA token.
4
5	## Prerequisites
6
7	- Canvas MCP server running and connected
8	- Authenticated with an educator (instructor/TA) Canvas API token
9	- Assignment must exist and have submissions to grade
10	- Rubric must already be created in Canvas and associated with the assignment (Canvas API cannot reliably create rubrics -- use the Canvas web UI for that)
11
12	## Workflow
13
14	### Step 1: Gather Assignment and Rubric Information
15
16	Before grading, retrieve the assignment details and its rubric criteria.
17
18	```
19	get_assignment_details(course_identifier, assignment_id)
20	```
21
22	Then get the rubric. Use `get_assignment_rubric_details` if the rubric is already linked to the assignment, or `list_all_rubrics` to browse all rubrics in the course:
23
24	```
25	get_assignment_rubric_details(course_identifier, assignment_id)
26	list_all_rubrics(course_identifier)
27	get_rubric_details(course_identifier, rubric_id)
28	```
29
30	Record the criterion IDs (often prefixed with underscore, e.g., `_8027`) and rating IDs from the rubric response. These are required for rubric-based grading.
31
32	### Step 2: List Submissions
33
34	Retrieve all student submissions to determine how many need grading:
35
36	```
37	list_submissions(course_identifier, assignment_id)
38	```
39
40	Note the `user_id` for each submission and the `workflow_state` (submitted, graded, pending_review). Count the submissions that need grading to determine which strategy to use.
41
42	### Step 3: Choose a Grading Strategy
43
44	Use this decision tree based on the number of submissions to grade:
45
46	```
47	How many submissions need grading?
48	\|
49	+-- 1-9 submissions
50	\| Use grade_with_rubric (one call per submission)
51	\|
52	+-- 10-29 submissions
53	\| Use bulk_grade_submissions (concurrent batch processing)
54	\| Set max_concurrent: 5, rate_limit_delay: 1.0
55	\| ALWAYS run with dry_run: true first
56	\|
57	+-- 30+ submissions OR custom grading logic needed
58	Use execute_typescript with bulkGrade function
59	99.7% token savings -- grading logic runs locally
60	ALWAYS run with dry_run: true first
61	```
62
63	### Strategy A: Single Grading (1-9 submissions)
64
65	Call `grade_with_rubric` once per student:
66
67	```
68	grade_with_rubric(
69	course_identifier,
70	assignment_id,
71	user_id,
72	rubric_assessment: {
73	"criterion_id": {
74	"points": <number>,
75	"rating_id": "<string>", // optional
76	"comments": "<string>" // optional per-criterion feedback
77	}
78	},
79	comment: "Overall feedback" // optional
80	)
81	```
82
83	### Strategy B: Bulk Grading (10-29 submissions)
84
85	Always dry run first. Build the grades dictionary mapping each user ID to their grade data, then validate before submitting:
86
87	```
88	bulk_grade_submissions(
89	course_identifier,
90	assignment_id,
91	grades: {
92	"user_id_1": {
93	"rubric_assessment": {
94	"criterion_id": {"points": 85, "comments": "Good analysis"}
95	},
96	"comment": "Overall feedback"
97	},
98	"user_id_2": {
99	"grade": 92,
100	"comment": "Excellent work"
101	}
102	},
103	dry_run: true, // VALIDATE FIRST
104	max_concurrent: 5,
105	rate_limit_delay: 1.0
106	)
107	```
108
109	Review the dry run output. If everything looks correct, re-run with `dry_run: false`.
110
111	### Strategy C: Code Execution (30+ submissions)
112
113	For large classes or custom grading logic, use `execute_typescript` to run grading locally. This avoids loading all submission data into the conversation context.
114
115	```
116	execute_typescript(code: `
117	import { bulkGrade } from './canvas/grading/bulkGrade.js';
118
119	await bulkGrade({
120	courseIdentifier: "COURSE_ID",
121	assignmentId: "ASSIGNMENT_ID",
122	gradingFunction: (submission) => {
123	// Custom grading logic runs locally -- no token cost
124	const notebook = submission.attachments?.find(
125	f => f.filename.endsWith('.ipynb')
126	);
127
128	if (!notebook) return null; // skip ungraded
129
130	return {
131	points: 100,
132	rubricAssessment: { "_8027": { points: 100 } },
133	comment: "Graded via automated review"
134	};
135	}
136	});
137	`)
138	```
139
140	Use `search_canvas_tools("grading", "signatures")` to discover available TypeScript modules and their function signatures before writing code.
141
142	## Token Efficiency
143
144	The three strategies have very different token costs:
145
146	\| Strategy \| When \| Token Cost \| Why \|
147	\|----------\|------\|------------\|-----\|
148	\| `grade_with_rubric` \| 1-9 submissions \| Low \| Few round-trips, small payloads \|
149	\| `bulk_grade_submissions` \| 10-29 submissions \| Medium \| One call with batch data \|
150	\| `execute_typescript` \| 30+ submissions \| Minimal \| Grading logic runs locally; only the code string is sent. 99.7% savings vs loading all submissions into context \|
151
152	The key insight: as submission count grows, s

People who liked this also viewed

6 picks

Type