CtrlK
BlogDocsLog inGet started
Tessl Logo

maxia

Connect to MAXIA AI-to-AI marketplace on Solana. Discover, buy, sell AI services. Earn USDC. 13 MCP tools, A2A protocol, DeFi yields, sentiment analysis, rug detection.

56

Quality

65%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/maxia/SKILL.md

The canonical home for this skill is maxia in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

65%Weight 40%Scale 1-5

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

The body is action-dense and mostly token-efficient, built around concrete curl examples, but it presents the entire API surface inline with no progressive disclosure and lacks validation checkpoints for the payment-bearing workflow. A syntax error in the execute example slightly undercuts its copy-paste readiness.

Suggestions

Move the per-endpoint curl reference into a bundle reference file (e.g. references/api.md) and keep SKILL.md as an overview with one or two representative examples plus a clear pointer.

Add an explicit numbered workflow for the register -> authenticate -> sell/buy/execute path, including a validation step (e.g. verify the returned api_key and confirm on-chain payment status before executing).

Fix the /execute curl example (unclosed JSON string) so all snippets are copy-paste ready.

DimensionReasoningScore

Conciseness

The body is dominated by lean, executable curl commands with minimal prose, though the full base URL is repeated in every example and the 'Key facts' section includes light padding ('50 Python modules, 18 monitored APIs').

4 / 5

Actionability

Provides copy-paste-ready curl commands for the common free and authenticated operations, but the /execute example has an unclosed JSON string and the placeholder substitution steps are implicit, leaving minor gaps.

4 / 5

Workflow Clarity

A rough register-then-authenticate sequence exists, but it is not explicitly numbered and there are no validation checkpoints; because the workflow involves on-chain USDC payments (destructive/financial), the missing validation caps workflow clarity at 3.

3 / 5

Progressive Disclosure

Sections are reasonably organized and external docs/RAG links are provided, but the full 13-tool API reference is inlined in SKILL.md with no bundle reference files to offload it, fitting the 'content that should be separate is inline' anchor.

3 / 5

Total

14

/

20

Passed

Description

66%Weight 40%Scale 1-5

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 conveys a clear, distinctive capability with concrete actions and reasonable trigger terms, but it lacks an explicit 'when to use' clause, capping its completeness. It is slightly feature-list heavy rather than trigger-phrase oriented.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers (e.g. 'Use when the user wants to buy or sell AI agent services, check crypto sentiment or DeFi yields, or detect Solana rug pulls').

Lead with trigger phrases users would naturally say rather than feature-name drops like '13 MCP tools, A2A protocol'.

Convert passive feature listings into concrete third-person actions to lift specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Lists several concrete actions ('Discover, buy, sell AI services. Earn USDC') plus 'sentiment analysis, rug detection', but items like '13 MCP tools, A2A protocol' are feature-name drops rather than actions, leaving minor coverage gaps.

4 / 5

Completeness

Has a clear 'what' (connect to MAXIA marketplace, discover/buy/sell services, earn USDC) but no explicit 'Use when...' trigger clause, so per the missing-trigger-guidance rule completeness is capped at 3.

3 / 5

Trigger Term Quality

Includes natural user phrases like 'buy AI services', 'crypto sentiment', 'DeFi yields', and 'rug detection' that a user would plausibly say, though a few common synonyms (e.g. 'token risk', 'wallet analysis') are under-represented.

4 / 5

Distinctiveness Conflict Risk

The AI-to-AI marketplace on Solana / A2A / MCP niche is distinct, with minor overlap risk against generic crypto/DeFi or sentiment-analysis skills.

4 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.