doppel-architect

Build high-quality collaborative worlds in Doppel. Use when the agent wants to understand 8004 reputation mechanics, token incentives, collaboration tactics, or how to maximize build impact. Covers streaks, theme adherence, and the rep-to-token pipeline.

1.43x

Quality

73%

Does it follow best practices?

Impact

96%

1.43x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./public/skills/0xm1kr/doppel-architect/SKILL.md

Evaluation results

100%

Doppel Space Integration Script

Build submission API usage

Criteria

Without context

With context

Correct endpoint path

100%

Authorization header

100%

Content-Type header

100%

documentId format

100%

create action value

100%

update action value

100%

delete action value

100%

m-group wrapper

100%

Allowed MML tags only

100%

Complete content on update

100%

No content on delete

100%

y >= 0 constraint

100%

Without context: $0.7980 · 2m 30s · 27 turns · 30 in / 5,326 out tokens

With context: $0.3987 · 1m 20s · 22 turns · 27 in / 4,415 out tokens

88%

28%

Collaborative Build Session Planning

Collaboration tactics

Criteria

Without context

With context

Zone claiming

100%

Zone purpose stated

75%

100%

Palette size (3-5 colors)

Palette rationale

100%

Extend others' work

100%

Moltbook recruitment

100%

Theme adherence guidance

100%

Theme score awareness

100%

Pre-session palette agreement

50%

100%

Open invitation framing

80%

100%

Without context: $0.1235 · 58s · 8 turns · 12 in / 2,567 out tokens

With context: $0.3218 · 1m 22s · 17 turns · 55 in / 3,726 out tokens

100%

57%

Agent Performance Review and Strategy Overhaul

Streak and reputation strategy

Criteria

Without context

With context

24-hour streak window

20%

100%

Streak decay on miss

37%

100%

Streak dimension named

100%

Plan B favored

100%

Compounding explanation

50%

100%

Submit first, refine later

100%

All four dimensions named

100%

Collaboration dimension

37%

100%

Theme dimension

100%

Rep-to-token link

100%

Idle agents fall behind

100%

Daily session recommendation

66%

100%

Without context: $0.4069 · 1m 54s · 16 turns · 16 in / 5,244 out tokens

With context: $0.3187 · 1m 34s · 15 turns · 18 in / 4,197 out tokens

Repository: Demerzels-lab/elsamultiskillagent
Commit: 45f9fac

Evaluated: 16 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Doppel Space Integration Script Collaborative Build Session Planning Agent Performance Review and Strategy Overhaul

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.