design-award-pipeline

Name: design-award-pipeline
Author: SeanJ1ang

218stars11forks

How to install design-award-pipeline?

seanj1ang/design-judge-skills/design-award-pipeline

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

Installs into the current project.

Summary

Route and coordinate an end-to-end design-award workflow across winner research, evidence-based evaluation, award matching, entry-text preparation, and final submission checking. Use when a user asks for a complete award plan, does not know which Design Judge skill to use, wants

Files · 1

View on GitHub

SKILL.md

1	# Design Award Pipeline
2
3	Coordinate the specialist Design Judge skills without duplicating their rules.
4
5	## Route the request
6
7	Choose the smallest sufficient route:
8
9	\| User goal \| Route \|
10	\|---\|---\|
11	\| Find comparable winners \| `design-award-search` \|
12	\| Diagnose or score the design \| `design-evaluation` \|
13	\| Select an award, route, or category \| `design-award-match` \|
14	\| Prepare entry fields and copy \| `design-information-prep` \|
15	\| Audit a concrete submission package \| `design-submission-check` \|
16	\| Complete journey \| evaluation or match → information prep → submission check; add search only when precedents are needed \|
17
18	If the user has not provided enough information to select a route, ask at most one short question. Otherwise proceed with explicit assumptions.
19
20	## Maintain the handoff
21
22	Create or update a compact handoff record using [references/handoff-schema.json](references/handoff-schema.json). Keep these concepts separate:
23
24	- user-supplied facts;
25	- evidence-backed findings;
26	- model inferences;
27	- missing facts and live-rule checks;
28	- decisions already approved by the user;
29	- the next recommended specialist skill.
30
31	Do not copy long specialist outputs into the handoff. Store identifiers, decisions, blockers, source links, and artifact paths.
32
33	## Coordinate stages
34
35	1. State the selected route and why it is sufficient.
36	2. Invoke or follow the relevant specialist Skill exactly.
37	3. Preserve its uncertainty labels, evidence confidence, and blockers.
38	4. Stop for user approval when the target award, maturity track, or another consequential choice changes downstream work.
39	5. Hand off only facts supported by user material or cited official sources.
40	6. End with the completed stage, unresolved blockers, and the next optional stage.
41
42	## Boundaries
43
44	- Never merge fit score, design score, and evidence confidence into one number.
45	- Never claim or estimate a probability of winning.
46	- Never treat observed winners as official jury weights.
47	- Never mark a package ready when time-sensitive official rules remain unverified.
48	- Never invoke all specialist skills when one is enough.

People who liked this also viewed

6 picks

Type

design-award-pipeline

218stars11forks

View on GitHub

How to install design-award-pipeline?

seanj1ang/design-judge-skills/design-award-pipeline

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Design Award Pipeline
2
3	Coordinate the specialist Design Judge skills without duplicating their rules.
4
5	## Route the request
6
7	Choose the smallest sufficient route:
8
9	\| User goal \| Route \|
10	\|---\|---\|
11	\| Find comparable winners \| `design-award-search` \|
12	\| Diagnose or score the design \| `design-evaluation` \|
13	\| Select an award, route, or category \| `design-award-match` \|
14	\| Prepare entry fields and copy \| `design-information-prep` \|
15	\| Audit a concrete submission package \| `design-submission-check` \|
16	\| Complete journey \| evaluation or match → information prep → submission check; add search only when precedents are needed \|
17
18	If the user has not provided enough information to select a route, ask at most one short question. Otherwise proceed with explicit assumptions.
19
20	## Maintain the handoff
21
22	Create or update a compact handoff record using [references/handoff-schema.json](references/handoff-schema.json). Keep these concepts separate:
23
24	- user-supplied facts;
25	- evidence-backed findings;
26	- model inferences;
27	- missing facts and live-rule checks;
28	- decisions already approved by the user;
29	- the next recommended specialist skill.
30
31	Do not copy long specialist outputs into the handoff. Store identifiers, decisions, blockers, source links, and artifact paths.
32
33	## Coordinate stages
34
35	1. State the selected route and why it is sufficient.
36	2. Invoke or follow the relevant specialist Skill exactly.
37	3. Preserve its uncertainty labels, evidence confidence, and blockers.
38	4. Stop for user approval when the target award, maturity track, or another consequential choice changes downstream work.
39	5. Hand off only facts supported by user material or cited official sources.
40	6. End with the completed stage, unresolved blockers, and the next optional stage.
41
42	## Boundaries
43
44	- Never merge fit score, design score, and evidence confidence into one number.
45	- Never claim or estimate a probability of winning.
46	- Never treat observed winners as official jury weights.
47	- Never mark a package ready when time-sensitive official rules remain unverified.
48	- Never invoke all specialist skills when one is enough.

People who liked this also viewed

6 picks

Type