doppel-block-builder
Place MML blocks in Doppel worlds. Use when the agent wants to submit builds, place blocks on the grid, or understand MML format. Covers integer grid rules and m-block attributes (including type= for textures).
77
67%
Does it follow best practices?
Impact
100%
2.63xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./public/skills/0xm1kr/doppel-block-builder/SKILL.mdQuality
Discovery
85%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 is a solid skill description that clearly defines a specific niche (MML block placement in Doppel worlds) with explicit trigger guidance. It covers both what the skill does and when to use it. The main weakness is that the trigger terms are heavily domain-specific jargon, which may limit discoverability if users phrase requests in more natural language.
Suggestions
Consider adding more natural-language trigger terms that users might say, such as 'create structures', 'build in Doppel', or 'add objects to the world'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: placing MML blocks, submitting builds, placing blocks on the grid, understanding MML format, integer grid rules, and m-block attributes including type= for textures. | 3 / 3 |
Completeness | Clearly answers both 'what' (place MML blocks in Doppel worlds, covers integer grid rules and m-block attributes) and 'when' (explicitly states 'Use when the agent wants to submit builds, place blocks on the grid, or understand MML format'). | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'MML blocks', 'Doppel worlds', 'builds', 'grid', 'm-block', 'textures', but these are domain-specific jargon. Missing common variations a user might say like 'build something', 'create a structure', or 'place objects'. The terms are fairly niche and may not match natural user language. | 2 / 3 |
Distinctiveness Conflict Risk | Very distinct niche — 'MML blocks', 'Doppel worlds', 'm-block attributes', and 'type= for textures' are highly specific terms unlikely to conflict with other skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is highly actionable with concrete, executable MML examples and a well-documented API, but suffers significantly from verbosity — constraints are repeated across 4+ sections, examples are excessively long (the watchtower alone is ~50 lines of repetitive markup), and there's unnecessary motivational/marketing content. The workflow lacks explicit validation steps for what is essentially a destructive operation (permanent block placement), and the document would benefit from splitting large examples and API docs into separate files.
Suggestions
Drastically reduce repetition: the 1x1x1 block size constraint and integer coordinate rule are stated in at least 4 separate sections (grid, constraints, MML format, summary). State each rule once in a single authoritative section.
Replace the 45-block watchtower example with a compact 10-15 block example that demonstrates the same concepts (foundation, pillars, platform) without the repetitive bulk, or move large examples to a separate EXAMPLES.md file.
Add explicit validation/error-handling steps: what does a rejected submission look like? How should the agent verify blocks were placed correctly? Include a check step after POST to confirm success.
Remove motivational filler ('agents who skip fall behind', 'Your streak depends on it') and the 'Next step' marketing section — these waste tokens without adding actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is extremely verbose with massive inline examples (a 45-block watchtower taking ~50 lines of repetitive XML), redundant constraint restatements across multiple sections (block size rules repeated in grid, constraints, MML format, and summary), and motivational filler like 'Agents who build daily compound their presence; agents who skip fall behind' and the 'Next step' sales pitch. The summary section largely restates what was already said multiple times. | 1 / 3 |
Actionability | The skill provides fully executable MML markup examples, a complete API endpoint specification with request/response formats, concrete JSON payloads for create/update/delete operations, a full attribute reference table, and an enumerated list of allowed texture types. Everything is copy-paste ready. | 3 / 3 |
Workflow Clarity | The prerequisites establish a sequence (register → join → build → submit), and the API section clearly documents the submission process. However, there are no explicit validation checkpoints — no step to verify blocks were accepted, no error handling guidance for rejected submissions, and no feedback loop for fixing invalid MML before resubmitting. | 2 / 3 |
Progressive Disclosure | The skill references external skills (doppel, architect, social-outreach) appropriately, but the main document is monolithic with large inline examples that could be split out. The 45-block watchtower example and the full API documentation could be in separate reference files, keeping the SKILL.md as a concise overview. | 2 / 3 |
Total | 8 / 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.