design-award-search

Name: design-award-search
Author: SeanJ1ang

218stars11forks

How to install design-award-search?

seanj1ang/design-judge-skills/design-award-search

$npx -y skills add SeanJ1ang/design-judge-skills --skill design-award-search

Installs into the current project.

Summary

Find and verify award-winning designs in the same or adjacent functional category through eight explicit relevance dimensions: problem and user, core function, sensing technology, intervention mechanism, physical form, use context and workflow, system architecture, and visual lan

Files · 1

View on GitHub

SKILL.md

1	# Design Award Search
2
3	## Purpose
4
5	Retrieve a small, high-precision set of verified award-winning designs. Keep the functional design category as a mandatory boundary, then search separately across eight relevance dimensions. Search public official sources at request time. Do not connect to, package, or depend on a private award database.
6
7	## Scope Boundary
8
9	- Identify the user's canonical design category.
10	- Search selected relevance dimensions independently.
11	- Verify award identity, year, category, relation evidence, and official URL.
12	- Explain exactly which dimension makes each result relevant.
13	- Stop after retrieval. Do not score the design, predict winning probability, recommend changes, or select an award to enter.
14
15	## User Interaction Contract
16
17	Accept a project description, image set, PDF, project page, or brief. Accept optional dimensions, award sources, years, and result count.
18
19	Require enough information to identify the object or service and its primary function. If the primary function remains ambiguous, ask exactly one short question: `What is the design's primary function and who uses it?` Otherwise state reasonable assumptions and continue.
20
21	When the user does not select dimensions, use balanced mode across every dimension supported by the supplied evidence. Use user images to infer physical-form and visual-language terms. If no image is supplied, do not activate visual-language relevance unless the user supplies explicit visual descriptors.
22
23	Offer this template when the user asks how to use the skill:
24
25	```text
26	Project: {name or object}
27	Primary function: {problem solved or job performed}
28	Target user: {optional}
29	Use context: {optional}
30	Relevance dimensions: {all or selected dimensions}
31	Preferences: {optional award sources, years, and result count}
32	```
33
34	## Retrieval Workflow
35
36	### 1. Build the profile
37
38	Read [../design-judge-shared/category-taxonomy.md](../design-judge-shared/category-taxonomy.md) and [references/relevance-dimensions.md](references/relevance-dimensions.md). Extract:
39
40	- canonical and adjacent categories;
41	- designed object or service;
42	- problem and target user;
43	- primary function;
44	- sensing technology;
45	- intervention mechanism;
46	- physical form and wear mode;
47	- use context and workflow;
48	- system components and information flow;
49	- visible form and CMF descriptors;
50	- source, year, dimension, and result-count constraints.
51
52	Classify by primary function before appearance. Keep physical form and visual language separate.
53
54	### 2. Select dimensions
55
56	Use these eight dimension keys:
57
58	1. `problem-user`
59	2. `core-function`
60	3. `sensing-technology`
61	4. `intervention-mechanism`
62	5. `physical-form`
63	6. `use-context`
64	7. `system-architecture`
65	8. `visual-language`
66
67	Search only user-selected dimensions. Otherwise activate every dimension supported by the input and use balanced mode.
68
69	### 3. Generate official-source queries
70
71	Read [../design-judge-shared/source-registry.md](../design-judge-shared/source-registry.md). Use `scripts/build_search_queries.py` when a shell is available. Translate profile terms into concise English first.
72
73	Example:
74
75	```powershell
76	python scripts/build_search_queries.py `
77	--category "Medical and Health" `
78	--function "detect stress and prevent relapse" `
79	--object "wearable health monitor" `
80	--problem "alcohol use disorder relapse" `
81	--user "people in addiction recovery" `
82	--sensing "ECG HRV stress detection" `
83	--intervention "haptic paced breathing biofeedback" `
84	--form "adhesive chest patch" `
85	--context "daily out-of-clinic high-risk moments" `
86	--system "wearable sensor app personalized feedback" `
87	--visual "discreet soft white blue medical wearable"
88	```
89
90	Execute dimension queries progressively. Stop searching a dimension after its target quota has enough verified candidates. Use official gallery search when available; otherwise use site-restricted discovery queries.
91
92	For visual-language retrieval, first build a visual-review pool of up to five same-category candidates found through every active dimension. Use visual-specific queries only when that pool is too small. Keep visual queries short: combine the designed object, physical form, and two or three unquoted visual descriptors. A domain-restricted image search may discover candidates, but only official project-page images can verify them. Do not use visual similarity outside the canonical or declared

People who liked this also viewed

6 picks

Type

design-award-search

218stars11forks

View on GitHub

How to install design-award-search?

seanj1ang/design-judge-skills/design-award-search

$npx -y skills add SeanJ1ang/design-judge-skills --skill design-award-search

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Design Award Search
2
3	## Purpose
4
5	Retrieve a small, high-precision set of verified award-winning designs. Keep the functional design category as a mandatory boundary, then search separately across eight relevance dimensions. Search public official sources at request time. Do not connect to, package, or depend on a private award database.
6
7	## Scope Boundary
8
9	- Identify the user's canonical design category.
10	- Search selected relevance dimensions independently.
11	- Verify award identity, year, category, relation evidence, and official URL.
12	- Explain exactly which dimension makes each result relevant.
13	- Stop after retrieval. Do not score the design, predict winning probability, recommend changes, or select an award to enter.
14
15	## User Interaction Contract
16
17	Accept a project description, image set, PDF, project page, or brief. Accept optional dimensions, award sources, years, and result count.
18
19	Require enough information to identify the object or service and its primary function. If the primary function remains ambiguous, ask exactly one short question: `What is the design's primary function and who uses it?` Otherwise state reasonable assumptions and continue.
20
21	When the user does not select dimensions, use balanced mode across every dimension supported by the supplied evidence. Use user images to infer physical-form and visual-language terms. If no image is supplied, do not activate visual-language relevance unless the user supplies explicit visual descriptors.
22
23	Offer this template when the user asks how to use the skill:
24
25	```text
26	Project: {name or object}
27	Primary function: {problem solved or job performed}
28	Target user: {optional}
29	Use context: {optional}
30	Relevance dimensions: {all or selected dimensions}
31	Preferences: {optional award sources, years, and result count}
32	```
33
34	## Retrieval Workflow
35
36	### 1. Build the profile
37
38	Read [../design-judge-shared/category-taxonomy.md](../design-judge-shared/category-taxonomy.md) and [references/relevance-dimensions.md](references/relevance-dimensions.md). Extract:
39
40	- canonical and adjacent categories;
41	- designed object or service;
42	- problem and target user;
43	- primary function;
44	- sensing technology;
45	- intervention mechanism;
46	- physical form and wear mode;
47	- use context and workflow;
48	- system components and information flow;
49	- visible form and CMF descriptors;
50	- source, year, dimension, and result-count constraints.
51
52	Classify by primary function before appearance. Keep physical form and visual language separate.
53
54	### 2. Select dimensions
55
56	Use these eight dimension keys:
57
58	1. `problem-user`
59	2. `core-function`
60	3. `sensing-technology`
61	4. `intervention-mechanism`
62	5. `physical-form`
63	6. `use-context`
64	7. `system-architecture`
65	8. `visual-language`
66
67	Search only user-selected dimensions. Otherwise activate every dimension supported by the input and use balanced mode.
68
69	### 3. Generate official-source queries
70
71	Read [../design-judge-shared/source-registry.md](../design-judge-shared/source-registry.md). Use `scripts/build_search_queries.py` when a shell is available. Translate profile terms into concise English first.
72
73	Example:
74
75	```powershell
76	python scripts/build_search_queries.py `
77	--category "Medical and Health" `
78	--function "detect stress and prevent relapse" `
79	--object "wearable health monitor" `
80	--problem "alcohol use disorder relapse" `
81	--user "people in addiction recovery" `
82	--sensing "ECG HRV stress detection" `
83	--intervention "haptic paced breathing biofeedback" `
84	--form "adhesive chest patch" `
85	--context "daily out-of-clinic high-risk moments" `
86	--system "wearable sensor app personalized feedback" `
87	--visual "discreet soft white blue medical wearable"
88	```
89
90	Execute dimension queries progressively. Stop searching a dimension after its target quota has enough verified candidates. Use official gallery search when available; otherwise use site-restricted discovery queries.
91
92	For visual-language retrieval, first build a visual-review pool of up to five same-category candidates found through every active dimension. Use visual-specific queries only when that pool is too small. Keep visual queries short: combine the designed object, physical form, and two or three unquoted visual descriptors. A domain-restricted image search may discover candidates, but only official project-page images can verify them. Do not use visual similarity outside the canonical or declared

People who liked this also viewed

6 picks

Type