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.
80
Quality
73%
Does it follow best practices?
Impact
96%
1.43xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/0xm1kr/doppel-architect/SKILL.mdQuality
Discovery
75%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description has strong completeness with explicit 'Use when' guidance and excellent distinctiveness due to its specific platform focus (Doppel/8004). However, it could improve by listing more concrete actions the skill enables rather than just topic coverage, and by including more natural user phrases alongside the technical terminology.
Suggestions
Replace topic coverage ('Covers streaks, theme adherence') with concrete actions like 'Calculate optimal streak timing, evaluate theme adherence scores, convert reputation to tokens'
Add natural user phrases to trigger terms such as 'how do I earn more tokens', 'building tips', 'reputation guide', or 'Doppel strategy'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Doppel, collaborative worlds) and mentions several concepts (reputation mechanics, token incentives, collaboration tactics, streaks, theme adherence, rep-to-token pipeline), but these are topic areas rather than concrete actions the skill performs. | 2 / 3 |
Completeness | Clearly answers both what ('Build high-quality collaborative worlds in Doppel') and when ('Use when the agent wants to understand 8004 reputation mechanics, token incentives, collaboration tactics, or how to maximize build impact') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like 'Doppel', '8004', 'reputation mechanics', 'token incentives', 'streaks', but these are fairly specialized. Missing common variations or natural phrases users might say like 'how do I earn tokens' or 'building strategy'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting Doppel platform and 8004 mechanics. The combination of 'Doppel', '8004', 'rep-to-token pipeline' creates distinct triggers unlikely to conflict with other skills. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides solid actionable guidance for the Doppel building system with clear API documentation and good structural organization. The main weaknesses are repetitive emphasis on streak importance (could be consolidated) and missing validation/error handling steps in the submission workflow. The content successfully balances domain-specific knowledge with practical implementation details.
Suggestions
Add validation/error handling steps after submission (e.g., 'Check response status, if 4xx then...') to improve workflow clarity
Consolidate the streak messaging - it's mentioned in at least 4 separate sections; one clear section with the mechanics would be more token-efficient
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill contains some unnecessary repetition (the importance of streaks is emphasized multiple times across sections) and motivational language that doesn't add actionable value. However, it's not excessively verbose and most content is relevant to the domain. | 2 / 3 |
Actionability | Provides concrete API endpoints, exact JSON payloads for submissions, specific header requirements, and clear field descriptions. The submission examples are copy-paste ready with proper structure. | 3 / 3 |
Workflow Clarity | The submission flow is clear (create vs update vs delete), but lacks explicit validation checkpoints. No guidance on what to do if a submission fails, no error handling steps, and no verification that a build was accepted before proceeding. | 2 / 3 |
Progressive Disclosure | Well-organized with clear sections, appropriate references to related skills (doppel, block-builder, social-outreach, erc-8004), and external resources. Content is appropriately scoped without deeply nested references. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata.version' is missing | Warning |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
45f9fac
Table of Contents
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.