CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

68

1.43x
Quality

55%

Does it follow best practices?

Impact

96%

1.43x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

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

Quality

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.

The description effectively identifies a clear niche (Doppel world-building) and includes an explicit 'Use when' clause with specific trigger scenarios, making it strong on completeness and distinctiveness. However, it describes topics covered rather than concrete actions the skill performs, and the reference to '8004' is unclear and potentially confusing. The trigger terms are domain-specific but could benefit from more natural user phrasings.

Suggestions

Replace topic-based language ('Covers streaks, theme adherence...') with concrete action verbs describing what the skill does (e.g., 'Calculates optimal streak strategies, evaluates theme adherence scores, models rep-to-token conversion rates').

Clarify or remove the '8004' reference — if it's a version number or game mechanic, make that explicit (e.g., 'Doppel 8004 mode' or 'round 8004 reputation mechanics').

DimensionReasoningScore

Specificity

The description names the domain (Doppel collaborative worlds) and mentions several specific concepts like 'reputation mechanics', 'token incentives', 'collaboration tactics', 'streaks', 'theme adherence', and 'rep-to-token pipeline', but it doesn't list concrete actions the skill performs (e.g., 'calculate optimal streak timing', 'generate build strategies'). It describes topics covered rather than actions taken.

2 / 3

Completeness

The description clearly answers both 'what' (covers reputation mechanics, token incentives, collaboration tactics, streaks, theme adherence, rep-to-token pipeline) and 'when' (explicit 'Use when the agent wants to understand...' clause with specific trigger scenarios).

3 / 3

Trigger Term Quality

Includes some relevant keywords like 'Doppel', 'reputation mechanics', 'token incentives', 'streaks', 'theme adherence', and 'rep-to-token pipeline' that users familiar with the platform might use. However, '8004' appears to be a typo or unclear reference, and common user phrasings like 'how do I earn more tokens' or 'build strategy' are not well covered.

2 / 3

Distinctiveness Conflict Risk

The description targets a very specific niche — the Doppel platform's collaborative world-building mechanics. Terms like 'Doppel', 'rep-to-token pipeline', and '8004 reputation mechanics' are highly distinctive and unlikely to conflict with other skills.

3 / 3

Total

10

/

12

Passed

Implementation

35%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The skill provides useful domain-specific information about the Doppel building ecosystem, particularly the API submission details and reputation dimensions. However, it is significantly over-written with repetitive motivational content about streaks and consistency that inflates the token count without adding actionable value. The lack of validation steps for submissions and error handling weakens the workflow for what is essentially a time-sensitive, consequential operation.

Suggestions

Cut repetitive motivational content about streaks and consistency — state the mechanic once with the decay rule, then move on. This could easily reduce the document by 40%.

Add validation after submission: show how to check the HTTP response for success/failure, and how to verify your build appears in the space (e.g., a GET endpoint or WebSocket confirmation).

Merge 'What earns reputation' and 'What costs you reputation' into a single concise table with positive/negative columns instead of two verbose lists that mirror each other.

Move the detailed per-service reputation breakdown into a separate REPUTATION.md reference file and link to it, keeping only the high-level summary inline.

DimensionReasoningScore

Conciseness

Extremely verbose with extensive motivational language ('Your reputation compounds or decays every 24 hours...'), repeated concepts (streak importance is hammered at least 5 times across sections), and explanations of incentive mechanics that Claude doesn't need spelled out repeatedly. The summary section largely restates everything already said. Sections like 'What earns reputation' and 'What costs you reputation' are largely mirrors of each other.

1 / 3

Actionability

The submission endpoint section provides concrete API details with JSON examples and a clear field table, which is good. However, much of the skill is motivational/strategic advice rather than executable guidance, and the MML content itself is deferred to another skill. The collaboration tactics are vague directives ('claim zones before building') without concrete implementation.

2 / 3

Workflow Clarity

The submission flow (create → update → delete) is reasonably clear, and the prerequisite chain is stated. However, there are no validation checkpoints — no guidance on checking if a submission succeeded, no error handling for failed submissions, and no feedback loop for verifying reputation changes after building. For a system where missed deadlines cause decay, this is a significant gap.

2 / 3

Progressive Disclosure

References to other skills (doppel, block-builder, social-outreach) and external resources are present and clearly signaled. However, the main document is quite long with content that could be split out (e.g., the detailed reputation dimension breakdown, collaboration tactics). The inline reputation breakdown is extensive and could be a separate reference file.

2 / 3

Total

7

/

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.

Validation9 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.