blockrun

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek")

Quality

72%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

npx tessl skill review --optimize ./.agent/skills/blockrun/SKILL.md

Quality

Content

72%

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

This skill is well-structured with good progressive disclosure through sub-skill references and provides actionable, executable code examples. Its main weaknesses are some redundancy between the 'When to Use' and 'Example User Prompts' tables, and a lack of error handling/validation workflows for edge cases like insufficient balance or failed API calls. The content effectively communicates when and how to use BlockRun without over-explaining concepts Claude already understands.

Suggestions

Merge the 'When to Use' and 'Example User Prompts' tables into a single reference table to reduce redundancy and improve conciseness.

Add error handling guidance for common failure modes (insufficient balance, API errors, network failures) to improve workflow clarity.

Dimension	Reasoning	Score
Conciseness	The skill is mostly efficient with good use of tables for quick reference, but includes some unnecessary content like the 'Philosophy' section ('You have a wallet...') and the 'Example User Prompts' table which largely duplicates the 'When to Use' table. The pricing table is useful but some explanatory text could be trimmed.	2 / 3
Actionability	Provides fully executable Python code for wallet setup, balance checking, budget tracking, and QR code generation. The code snippets are copy-paste ready with proper imports and realistic usage patterns. The trigger tables give concrete guidance on when to act.	3 / 3
Workflow Clarity	The budget control section has a reasonable workflow with spending checks, but the overall skill lacks a clear sequential workflow for the main use cases (e.g., first-time setup flow, or the full sequence from receiving a request to delivering results). There's no validation or error handling guidance for failed API calls or insufficient balance scenarios.	2 / 3
Progressive Disclosure	The skill provides a clear overview with well-organized sections and links to 6 sub-skills for detailed topics (basic chat, X search, image generation, etc.). The main SKILL.md stays at the right level of abstraction while pointing to one-level-deep references for specifics.	3 / 3
	Total	10 / 12 Passed

Description

72%

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 excels at trigger term coverage and distinctiveness, making it easy for Claude to know when to select this skill. However, it lacks a clear statement of what the skill actually does — it tells Claude when to use it but not what actions it performs. Adding a brief 'what' clause describing the concrete mechanism (e.g., 'Routes requests to external AI models and returns their outputs') would significantly improve it.

Suggestions

Add a concrete 'what' clause at the beginning describing the skill's actions, e.g., 'Routes requests to external AI models (Grok, GPT, DALL-E, DeepSeek) and returns their outputs.'

Specify the concrete outputs or results the skill produces (e.g., 'returns generated images, fetched tweets, or model responses').

Dimension	Reasoning	Score
Specificity	The description names some specific capabilities (image generation, real-time X/Twitter data) and mentions specific external models, but doesn't clearly describe what concrete actions the skill performs (e.g., 'routes requests to external models', 'generates images via DALL-E', 'fetches tweets via Grok').	2 / 3
Completeness	The 'when' is explicitly and thoroughly covered with a 'Use when...' clause and specific trigger scenarios. However, the 'what' is weak — it describes when to use the skill but not what the skill actually does (e.g., how it interfaces with external models, what it returns).	2 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users would actually say: 'blockrun', 'use grok', 'use gpt', 'dall-e', 'deepseek', 'image generation', 'real-time X/Twitter data'. These are highly specific and match real user language patterns.	3 / 3
Distinctiveness Conflict Risk	Highly distinctive with very specific triggers like 'blockrun', 'use grok', 'use gpt', 'dall-e', 'deepseek'. The niche of delegating to external models is clear and unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 Passed

Validation

81%

Warnings & errors only

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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	9 / 11 Passed

Repository: Dokhacgiakhoa/antigravity-ide
Commit: c4a059b

Reviewed: 5 days ago

Table of Contents

Discovery Implementation Validation

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.