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
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillEvaluation — 100%
↑ 2.17xAgent success when using this skill
Validation for skill structure
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 is functional with clear 'what' and 'when' components and a distinct niche. However, it could benefit from more specific action descriptions and broader trigger term coverage to help users who might describe their needs differently (e.g., 'virtual world', 'metaverse').
Suggestions
Expand trigger terms to include natural variations like 'virtual world', 'metaverse', '3D environment', 'multiplayer space', or 'collaborative building'
Make actions more concrete - instead of 'register an identity', specify what that means (e.g., 'create agent profile with name and credentials')
| 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 high-level and could be more concrete about what each action entails. | 2 / 3 |
Completeness | Clearly answers both what (collaborative multi-agent 3D world builder with identity/avatar/space features) and when ('Use this skill when the agent wants to...') with explicit trigger conditions. | 3 / 3 |
Trigger Term Quality | Includes some relevant terms like '3D avatar', 'spaces', 'identity', but missing common variations users might say like 'virtual world', 'metaverse', '3D environment', 'multiplayer', or 'collaborative building'. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche - 'Doppel' is a specific product name, and the combination of multi-agent 3D world building with avatar/space management is unlikely to conflict with other skills. | 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 functional, actionable skill with clear API documentation and a well-defined join workflow. The main weaknesses are moderate verbosity (redundant summary section, some repeated concepts) and a monolithic structure that could benefit from splitting the detailed API reference into a separate file. The MML output rules section at the top feels disconnected from the rest of the skill.
Suggestions
Remove or significantly condense the Summary section since it largely repeats information already provided in the API sections above
Consider moving the detailed API reference to a separate REFERENCE.md file, keeping only the quick-start flow in SKILL.md
Integrate or relocate the MML output rules section - it appears disconnected from the main Doppel connection/registration purpose of this skill
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient but includes some redundancy (summary section repeats earlier content, MML rules section feels disconnected). The API documentation is dense but necessary; however, some explanatory text could be trimmed. | 2 / 3 |
Actionability | Provides concrete, executable guidance with specific endpoints, HTTP methods, request/response formats, and code examples (TypeScript WebSocket snippet). API paths and authentication headers are clearly specified and copy-paste ready. | 3 / 3 |
Workflow Clarity | The 'Join a space' section provides a clear 3-step sequence (JWT → session token → WebSocket). The flow is explicit with numbered steps and references to specific APIs. Error handling (503 with Retry-After) is mentioned. | 3 / 3 |
Progressive Disclosure | Content is organized into logical sections (Public, Session, Agent, Chat APIs) but everything is inline in one file. The 'Next step' section references other skills appropriately, but the main content could benefit from splitting detailed API reference into a separate file. | 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 | |
- 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.