CtrlK
BlogDocsLog inGet started
Tessl Logo

blockrun

BlockRun works with Claude Code and Google Antigravity.

34

Quality

30%

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 ./skills/blockrun/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%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 highly actionable with executable SDK examples and clear trigger routing, but it suffers from redundant pricing/setup blocks and inlines reference material that a longer skill should split into separate files. Validation for the autonomous-spending workflow is only optionally documented.

Suggestions

De-duplicate pricing: keep a single cost table and remove the repeated model/pricing entries from the Philosophy and Cost Reference sections.

Move the full xAI Live Search parameter reference and model catalog into a separate reference file linked from SKILL.md to improve progressive disclosure.

Promote budget validation from "Optional" into the main call workflow with an explicit validate-before-spend checkpoint and retry guidance.

DimensionReasoningScore

Conciseness

The body is mostly efficient with executable code, but pricing is duplicated across the Philosophy table, Available Models table, and Cost Reference table, and the QR-code setup block appears twice, so it could be tightened.

3 / 5

Actionability

It provides concrete, copy-paste-ready Python for the common cases (setup_agent_wallet, client.chat with search=True, ImageClient.generate) with only minor gaps, fitting the mostly-executable anchor.

4 / 5

Workflow Clarity

Trigger routing and a numbered setup sequence are present, but validation (budget checking) lives only in an "Optional" section while the main autonomous-spending flow lacks explicit verify checkpoints, so the destructive/batch cap of 3 applies.

3 / 5

Progressive Disclosure

Section headers organize the content well, but at ~285 lines with no bundle files, material that belongs in separate references (full xAI Live Search reference, model/cost tables) is all inlined with no one-level-deep navigation.

3 / 5

Total

13

/

20

Passed

Description

3%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 is too vague to function as a skill trigger: it states no concrete capabilities and provides no usage guidance, relying only on product names. It would rarely surface when a user actually needs BlockRun's image-generation or live-X-data features.

Suggestions

Rewrite the description to list concrete actions, e.g. "Generate images via DALL-E, fetch real-time X/Twitter data via Grok Live Search, and get LLM second opinions using x402 micropayments."

Add an explicit "Use when..." clause naming natural trigger phrases users would say (e.g. "generate an image", "check what's trending on X", "get a GPT second opinion").

Avoid the generic "works with Claude Code" framing, which conflicts with nearly every other Claude Code skill; lead with the distinctive paid-capability niche instead.

DimensionReasoningScore

Specificity

The description only states "works with Claude Code and Google Antigravity" — it names no concrete actions, matching the entirely-vague anchor "Helps with documents".

1 / 5

Completeness

The "what" is extremely vague ("works with") and there is no "when"/Use-when clause at all, matching the anchor where both what and when are missing or extremely vague.

1 / 5

Trigger Term Quality

It contains only product names ("Claude Code", "Google Antigravity") with no natural user phrases like "generate images" or "real-time X data", fitting the jargon-only anchor.

1 / 5

Distinctiveness Conflict Risk

"works with Claude Code" is extremely broad and would overlap with virtually any Claude Code skill, though "Google Antigravity" adds slight specificity, placing it just above the most-generic anchor.

2 / 5

Total

5

/

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.