design-award-match

Name: design-award-match
Author: SeanJ1ang

218stars11forks

How to install design-award-match?

seanj1ang/design-judge-skills/design-award-match

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

Installs into the current project.

Summary

Match a design project to supported design-award programs, tracks, and entry categories; apply structural eligibility gates; verify current official rules; compare published criteria and cautiously described winner trends; and output fit, evidence confidence, and submission prior

Files · 1

View on GitHub

SKILL.md

1	# Design Award Match
2
3	## Purpose
4
5	Identify the most defensible award, program, track, and category for a design project. Treat fit scores as transparent decision aids, never as probabilities of winning.
6
7	## Scope
8
9	- Extract decision-relevant project facts.
10	- Pre-filter the configured award allowlist with stable eligibility gates.
11	- Verify all dynamic requirements on current official pages.
12	- Compare project evidence with published criteria and observable winner trends.
13	- Score, rank, and explain strategic fit.
14	- Stop after recommendation; do not audit every submission file or redesign the project.
15
16	Use `$design-award-search` for verified same-category winners. Route file format, size, naming, declarations, and upload completeness to `$design-submission-check`.
17
18	## Input Contract
19
20	Accept a brief, images, PDF, portfolio page, or structured JSON. Extract or request only facts that can change the recommendation:
21
22	- primary function, target user, and use context;
23	- innovation and supporting evidence;
24	- project state and completion, launch, or release date;
25	- applicant type, student status, country or region;
26	- candidate awards, intended cycle, budget, and geographic constraints.
27
28	Use the canonical values in [references/category-crosswalk.json](references/category-crosswalk.json). If the primary function is unclear, ask one short question. If an eligibility fact is missing, continue with `Eligibility: Unknown`; never assume a pass.
29
30	Offer this template when the user asks how to use the skill:
31
32	```text
33	Project: {name and one-sentence description}
34	Primary function: {job performed or problem solved}
35	Target user / context: {optional}
36	Innovation and evidence: {optional}
37	Development status / launch date: {optional}
38	Applicant: {student, individual, studio, company; country/region}
39	Candidate awards: {optional; omit to search the supported allowlist}
40	Submission cycle / constraints: {optional year, region, budget}
41	```
42
43	## Workflow
44
45	### 1. Build the project profile
46
47	Read [../design-judge-shared/category-taxonomy.md](../design-judge-shared/category-taxonomy.md) and [references/category-crosswalk.json](references/category-crosswalk.json). Classify by primary function before appearance. Record one canonical category, no more than two adjacent categories, project state, applicant type, evidence, timing, and constraints. Label material inferences.
48
49	For command-line pre-filtering, prepare JSON like [examples/project-profile.example.json](examples/project-profile.example.json).
50
51	### 2. Validate and load the supported award set
52
53	Read [references/awards/index.json](references/awards/index.json) and [references/award-profile-guide.md](references/award-profile-guide.md). Analyze only the programs in the allowlist. Treat Red Dot Product and Red Dot Design Concept as separate programs. If a requested award is absent, return `Unsupported` rather than researching and silently adding it.
54
55	When a shell is available, validate configuration before analysis:
56
57	```powershell
58	python scripts/validate_award_profiles.py --pretty
59	```
60
61	Build a focused candidate set, normally three to five routes:
62
63	```powershell
64	python scripts/build_candidate_set.py examples/project-profile.example.json --limit 5 --pretty
65	```
66
67	Use `--award` repeatedly to restrict candidates. Award ids and declared aliases are accepted.
68
69	### 3. Apply stable gates
70
71	Use each selected profile's `routes`, `required_project_fields`, and `stable_constraints`. When needed, run:
72
73	```powershell
74	python scripts/filter_eligible_awards.py examples/project-profile.example.json --include-ineligible --pretty
75	```
76
77	Assign:
78
79	- `Eligible`: all stable and current official gates pass.
80	- `Ineligible`: a confirmed rule excludes the entry.
81	- `Unknown`: a project fact is missing or any live gate remains unchecked.
82
83	Exclude `Ineligible` routes from ranking but state the exact reason. Keep `Unknown` routes conditional.
84
85	### 4. Verify dynamic rules live
86
87	Read only the selected award profiles under `references/awards/`. For every `dynamic_gate` and relevant `dynamic_field`, verify current official pages at request time:
88
89	- cycle status and absolute deadlines;
90	- applicant, geography, age, enrollment, and graduation rules;
91	- completion, publication, distribution, or launch windows;
92	- exact track

People who liked this also viewed

6 picks

Type

design-award-match

218stars11forks

View on GitHub

How to install design-award-match?

seanj1ang/design-judge-skills/design-award-match

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Design Award Match
2
3	## Purpose
4
5	Identify the most defensible award, program, track, and category for a design project. Treat fit scores as transparent decision aids, never as probabilities of winning.
6
7	## Scope
8
9	- Extract decision-relevant project facts.
10	- Pre-filter the configured award allowlist with stable eligibility gates.
11	- Verify all dynamic requirements on current official pages.
12	- Compare project evidence with published criteria and observable winner trends.
13	- Score, rank, and explain strategic fit.
14	- Stop after recommendation; do not audit every submission file or redesign the project.
15
16	Use `$design-award-search` for verified same-category winners. Route file format, size, naming, declarations, and upload completeness to `$design-submission-check`.
17
18	## Input Contract
19
20	Accept a brief, images, PDF, portfolio page, or structured JSON. Extract or request only facts that can change the recommendation:
21
22	- primary function, target user, and use context;
23	- innovation and supporting evidence;
24	- project state and completion, launch, or release date;
25	- applicant type, student status, country or region;
26	- candidate awards, intended cycle, budget, and geographic constraints.
27
28	Use the canonical values in [references/category-crosswalk.json](references/category-crosswalk.json). If the primary function is unclear, ask one short question. If an eligibility fact is missing, continue with `Eligibility: Unknown`; never assume a pass.
29
30	Offer this template when the user asks how to use the skill:
31
32	```text
33	Project: {name and one-sentence description}
34	Primary function: {job performed or problem solved}
35	Target user / context: {optional}
36	Innovation and evidence: {optional}
37	Development status / launch date: {optional}
38	Applicant: {student, individual, studio, company; country/region}
39	Candidate awards: {optional; omit to search the supported allowlist}
40	Submission cycle / constraints: {optional year, region, budget}
41	```
42
43	## Workflow
44
45	### 1. Build the project profile
46
47	Read [../design-judge-shared/category-taxonomy.md](../design-judge-shared/category-taxonomy.md) and [references/category-crosswalk.json](references/category-crosswalk.json). Classify by primary function before appearance. Record one canonical category, no more than two adjacent categories, project state, applicant type, evidence, timing, and constraints. Label material inferences.
48
49	For command-line pre-filtering, prepare JSON like [examples/project-profile.example.json](examples/project-profile.example.json).
50
51	### 2. Validate and load the supported award set
52
53	Read [references/awards/index.json](references/awards/index.json) and [references/award-profile-guide.md](references/award-profile-guide.md). Analyze only the programs in the allowlist. Treat Red Dot Product and Red Dot Design Concept as separate programs. If a requested award is absent, return `Unsupported` rather than researching and silently adding it.
54
55	When a shell is available, validate configuration before analysis:
56
57	```powershell
58	python scripts/validate_award_profiles.py --pretty
59	```
60
61	Build a focused candidate set, normally three to five routes:
62
63	```powershell
64	python scripts/build_candidate_set.py examples/project-profile.example.json --limit 5 --pretty
65	```
66
67	Use `--award` repeatedly to restrict candidates. Award ids and declared aliases are accepted.
68
69	### 3. Apply stable gates
70
71	Use each selected profile's `routes`, `required_project_fields`, and `stable_constraints`. When needed, run:
72
73	```powershell
74	python scripts/filter_eligible_awards.py examples/project-profile.example.json --include-ineligible --pretty
75	```
76
77	Assign:
78
79	- `Eligible`: all stable and current official gates pass.
80	- `Ineligible`: a confirmed rule excludes the entry.
81	- `Unknown`: a project fact is missing or any live gate remains unchecked.
82
83	Exclude `Ineligible` routes from ranking but state the exact reason. Keep `Unknown` routes conditional.
84
85	### 4. Verify dynamic rules live
86
87	Read only the selected award profiles under `references/awards/`. For every `dynamic_gate` and relevant `dynamic_field`, verify current official pages at request time:
88
89	- cycle status and absolute deadlines;
90	- applicant, geography, age, enrollment, and graduation rules;
91	- completion, publication, distribution, or launch windows;
92	- exact track

People who liked this also viewed

6 picks

Type