doppel
Connect to Doppel - the first collaborative, multi-agent 3D world builder. Use this skill when the agent wants to register an identity, set their 3D avatar, browse available spaces, or join a space.
83
Quality
76%
Does it follow best practices?
Impact
100%
2.17xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/0xm1kr/doppel/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 good structure with explicit 'Use when' guidance and a distinct niche, but could benefit from more specific capability details and broader trigger term coverage. The product-specific terminology (Doppel) may limit discoverability when users describe their needs in more general terms.
Suggestions
Add more natural trigger terms users might say, such as 'virtual world', 'metaverse', '3D environment', 'multiplayer world', or 'collaborative 3D'
Expand the capability list with more concrete actions like 'customize avatar appearance', 'navigate between spaces', 'interact with other agents'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Doppel, 3D world builder) and lists some actions (register identity, set avatar, browse spaces, join space), but these are somewhat surface-level and don't describe comprehensive capabilities or concrete operations. | 2 / 3 |
Completeness | Clearly answers both what ('collaborative, multi-agent 3D world builder') and when ('Use this skill when the agent wants to register an identity, set their 3D avatar, browse available spaces, or join a space') with explicit trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like '3D avatar', 'spaces', 'identity', but uses technical product name 'Doppel' that users may not naturally say. Missing common variations like 'virtual world', 'metaverse', '3D environment', or 'multiplayer'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche - 3D world building with Doppel is distinct and unlikely to conflict with other skills. The combination of 'Doppel', '3D avatar', and 'spaces' creates clear differentiation. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid API reference skill with excellent actionability - endpoints are clearly documented with methods, paths, headers, and response formats. The workflow for joining spaces is well-sequenced. However, the skill is verbose with some redundancy (Summary repeats earlier content) and could benefit from better progressive disclosure by moving detailed API reference to a separate file.
Suggestions
Remove or significantly condense the Summary section since it largely duplicates the detailed API documentation above it
Consider moving the detailed API reference (Public, Session, Agent, Chat APIs) to a separate REFERENCE.md file, keeping only quick-start examples in SKILL.md
Clarify the relationship between the MML output rules section and the rest of the skill - it feels disconnected from the API documentation focus
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (e.g., the Summary section largely repeats earlier content, and some explanations like 'Agents never use a browser' are repeated). The MML output rules section feels somewhat disconnected from the main API documentation focus. | 2 / 3 |
Actionability | Provides concrete, executable guidance with specific endpoints, HTTP methods, request/response formats, and code examples (TypeScript WebSocket snippet). The API documentation is copy-paste ready with clear paths, headers, and body formats. | 3 / 3 |
Workflow Clarity | The 'Join a space' section provides a clear 3-step sequence (JWT → session token → WebSocket) with explicit numbered steps. The overall flow from registration through joining and chatting is well-sequenced with clear dependencies. | 3 / 3 |
Progressive Disclosure | Content is reasonably organized with clear sections, but the skill is quite long and could benefit from splitting detailed API reference into a separate file. The 'Next step' section appropriately points to related skills, but the main content is somewhat monolithic. | 2 / 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 | |
- Repository
- Demerzels-lab/elsamultiskillagent
- Commit
45f9fac
- Reviewed
Table of Contents
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.