design-evaluation

Name: design-evaluation
Author: SeanJ1ang

218stars11forks

How to install design-evaluation?

seanj1ang/design-judge-skills/design-evaluation

$npx -y skills add SeanJ1ang/design-judge-skills --skill design-evaluation

Installs into the current project.

Summary

Evaluate one design or a user-approved maturity-mapped batch through a transparent evidence-based rubric. Classify each work, score design quality and presentation, identify Critical risks, report evidence confidence, and optionally shortlist works within separate maturity tracks

Files · 1

View on GitHub

SKILL.md

1	# Design Evaluation
2
3	## Purpose
4
5	Evaluate design quality consistently without pretending that a score is an award outcome. Keep design quality, presentation quality, and evidence confidence separate. Require the user to choose the maturity track.
6
7	## Scope Boundary
8
9	- Evaluate the supplied design and supplied presentation materials.
10	- Classify one primary discipline, one primary sector, and optional secondary labels and focus tags.
11	- Build an evidence ledger before scoring.
12	- Score the general rubric and report Critical findings separately.
13	- Apply an optional award-aligned lens only when the user already names a target award.
14	- Batch-evaluate a fixed corpus only after the user approves the maturity mapping for every included record.
15	- Produce score-based shortlists within each maturity track; never cross-rank Student Concept and Mature Work.
16
17	Do not:
18
19	- infer or change the work maturity;
20	- retrieve award winners inside this skill;
21	- recommend which award to enter;
22	- turn findings into a full redesign proposal;
23	- audit upload limits, filenames, declarations, licences, or portal compliance;
24	- call the result an official iF, Red Dot, or other jury decision;
25	- estimate an exact probability of winning.
26	- label a rank percentile, top-decile membership, or score as a winning probability.
27
28	Route winner retrieval to `$design-award-search`, award selection to `$design-award-match`, concrete redesign work to `$design-optimization` when available, and final package compliance to `$design-submission-check`.
29
30	## Required User Input
31
32	Accept images, a PDF, project text, a portfolio page, video frames, prototype evidence, test records, or a structured brief.
33
34	Maturity is mandatory and must come from the user. Accept exactly:
35
36	- `Student Concept` / `学生概念`
37	- `Mature Work` / `成熟作品`
38
39	If maturity is absent, ask exactly one question and stop scoring:
40
41	`请选择作品成熟度：“学生概念”或“成熟作品”。`
42
43	Never infer maturity from the author's identity, image finish, prototype appearance, commercial branding, or supplied metadata. If evidence conflicts with the selected maturity, preserve the user's selection and record `Maturity evidence mismatch`.
44
45	For a batch, an explicit user-approved mapping rule counts as user selection for every record matched by that rule. Reject unmatched values rather than inferring them. Record the mapping rule and `maturity_source: user` in the batch manifest.
46
47	Offer this template when the user asks how to use the skill:
48
49	```text
50	Project: {name}
51	Maturity: Student Concept \| Mature Work # selected by the user
52	Primary function: {what it does}
53	Target user: {who uses it}
54	Use context: {where and when}
55	Materials: {attachments or links}
56	Evaluation mode: General \| optional named award-aligned lens
57	```
58
59	## Evaluation Workflow
60
61	For batch work, first read [references/batch-evaluation.md](references/batch-evaluation.md). Use `scripts/batch_evaluation.py` for deterministic scoring, failure isolation, and separate-track shortlisting. Use a project adapter for private database access; never bundle database rows, images, signed URLs, or credentials in the public Skill.
62
63	### 1. Confirm the user-selected maturity
64
65	Record:
66
67	```yaml
68	maturity: student_concept \| mature_work
69	maturity_source: user
70	```
71
72	Do not proceed with a numeric score when `maturity_source` is missing or is not `user`.
73
74	### 2. Build the evaluation profile
75
76	Read [references/classification-policy.md](references/classification-policy.md) and `references/profiles/classification.json`.
77
78	Extract:
79
80	- primary function, target user, use context, and claimed outcome;
81	- one primary design discipline and up to two secondary disciplines;
82	- one primary application sector and up to one secondary sector;
83	- zero or more focus tags;
84	- supplied material types and obvious material limitations.
85
86	The classification confidence is separate from evaluation confidence. Ask no additional question when a reasonable classification can be stated as an assumption.
87
88	### 3. Build the evidence ledger
89
90	Read [references/evidence-policy.md](references/evidence-policy.md). For every scored dimension, assign exactly one evidence state:
91
92	- `Verified`
93	- `Supported`
94	- `Claimed`
95	- `Missing`
96
97	Attach concise evidence references and distinguish observable facts from author claims and evaluator inference.
98
99	### 4. Load the rubric
100
101	Read [references/evaluation-framework.md](references/evaluation-framewor

People who liked this also viewed

6 picks

Type

design-evaluation

218stars11forks

View on GitHub

How to install design-evaluation?

seanj1ang/design-judge-skills/design-evaluation

$npx -y skills add SeanJ1ang/design-judge-skills --skill design-evaluation

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Design Evaluation
2
3	## Purpose
4
5	Evaluate design quality consistently without pretending that a score is an award outcome. Keep design quality, presentation quality, and evidence confidence separate. Require the user to choose the maturity track.
6
7	## Scope Boundary
8
9	- Evaluate the supplied design and supplied presentation materials.
10	- Classify one primary discipline, one primary sector, and optional secondary labels and focus tags.
11	- Build an evidence ledger before scoring.
12	- Score the general rubric and report Critical findings separately.
13	- Apply an optional award-aligned lens only when the user already names a target award.
14	- Batch-evaluate a fixed corpus only after the user approves the maturity mapping for every included record.
15	- Produce score-based shortlists within each maturity track; never cross-rank Student Concept and Mature Work.
16
17	Do not:
18
19	- infer or change the work maturity;
20	- retrieve award winners inside this skill;
21	- recommend which award to enter;
22	- turn findings into a full redesign proposal;
23	- audit upload limits, filenames, declarations, licences, or portal compliance;
24	- call the result an official iF, Red Dot, or other jury decision;
25	- estimate an exact probability of winning.
26	- label a rank percentile, top-decile membership, or score as a winning probability.
27
28	Route winner retrieval to `$design-award-search`, award selection to `$design-award-match`, concrete redesign work to `$design-optimization` when available, and final package compliance to `$design-submission-check`.
29
30	## Required User Input
31
32	Accept images, a PDF, project text, a portfolio page, video frames, prototype evidence, test records, or a structured brief.
33
34	Maturity is mandatory and must come from the user. Accept exactly:
35
36	- `Student Concept` / `学生概念`
37	- `Mature Work` / `成熟作品`
38
39	If maturity is absent, ask exactly one question and stop scoring:
40
41	`请选择作品成熟度：“学生概念”或“成熟作品”。`
42
43	Never infer maturity from the author's identity, image finish, prototype appearance, commercial branding, or supplied metadata. If evidence conflicts with the selected maturity, preserve the user's selection and record `Maturity evidence mismatch`.
44
45	For a batch, an explicit user-approved mapping rule counts as user selection for every record matched by that rule. Reject unmatched values rather than inferring them. Record the mapping rule and `maturity_source: user` in the batch manifest.
46
47	Offer this template when the user asks how to use the skill:
48
49	```text
50	Project: {name}
51	Maturity: Student Concept \| Mature Work # selected by the user
52	Primary function: {what it does}
53	Target user: {who uses it}
54	Use context: {where and when}
55	Materials: {attachments or links}
56	Evaluation mode: General \| optional named award-aligned lens
57	```
58
59	## Evaluation Workflow
60
61	For batch work, first read [references/batch-evaluation.md](references/batch-evaluation.md). Use `scripts/batch_evaluation.py` for deterministic scoring, failure isolation, and separate-track shortlisting. Use a project adapter for private database access; never bundle database rows, images, signed URLs, or credentials in the public Skill.
62
63	### 1. Confirm the user-selected maturity
64
65	Record:
66
67	```yaml
68	maturity: student_concept \| mature_work
69	maturity_source: user
70	```
71
72	Do not proceed with a numeric score when `maturity_source` is missing or is not `user`.
73
74	### 2. Build the evaluation profile
75
76	Read [references/classification-policy.md](references/classification-policy.md) and `references/profiles/classification.json`.
77
78	Extract:
79
80	- primary function, target user, use context, and claimed outcome;
81	- one primary design discipline and up to two secondary disciplines;
82	- one primary application sector and up to one secondary sector;
83	- zero or more focus tags;
84	- supplied material types and obvious material limitations.
85
86	The classification confidence is separate from evaluation confidence. Ask no additional question when a reasonable classification can be stated as an assumption.
87
88	### 3. Build the evidence ledger
89
90	Read [references/evidence-policy.md](references/evidence-policy.md). For every scored dimension, assign exactly one evidence state:
91
92	- `Verified`
93	- `Supported`
94	- `Claimed`
95	- `Missing`
96
97	Attach concise evidence references and distinguish observable facts from author claims and evaluator inference.
98
99	### 4. Load the rubric
100
101	Read [references/evaluation-framework.md](references/evaluation-framewor

People who liked this also viewed

6 picks

Type