ito-compute

Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô compute status, validate GPU nodes, revoke Itô access, or rent or purchase GPU compute and needs the supported boundary explained.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%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 and workflow-structured with strong validation checkpoints, and it never wastes tokens explaining concepts Claude already knows. The main improvement lever is tighter boundary-enumeration prose and optionally splitting install/MCP detail into reference files.

Suggestions

Collapse the repeated 'cannot rent/launch/recover/repair/reset/purchase/order' enumerations into a single stated boundary and reference it, to reduce token cost without losing clarity.

Move the install/build block and the full MCP JSON config into a references file (e.g. references/install.md) and link to it from SKILL.md to improve progressive disclosure.

Tighten the `ecc ito login` prose (the macOS Keychain / file-token fallback aside) into a one-line note, keeping only the actionable handoff instruction.

Dimension	Reasoning	Score
Conciseness	Dense and operation-specific with no padding about what GPUs or RFQs are, but repeated boundary enumerations (e.g. 'cannot rent, launch, recover, repair, reset, purchase, or order resources') and slightly verbose login prose could be trimmed.	4 / 5
Actionability	Provides fully executable, copy-paste-ready guidance: the complete `ecc ito find` invocation with all flags, install/build steps, the MCP stdio JSON config, and the `evals` command cover the common cases concretely.	5 / 5
Workflow Clarity	A clearly numbered login→auth→authority→find→status→logout workflow with explicit validation checkpoints (count==nodes*gpus-per-node, post-failure status check, firm-quote confirmation) and a login-handoff error-recovery path; the destructive-cap does not apply since validation is present.	5 / 5
Progressive Disclosure	No bundle files exist and the ~150-line body is organized into well-labeled sections with no nested references, but a fair amount of inline detail (install/build steps, full MCP config) could be offloaded to one-level-deep reference files.	4 / 5
	Total	18 / 20 Passed

Description

87%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 strong: it lists specific capabilities, provides an explicit 'Use when' trigger clause with natural buyer language, and carves out a clear niche. The only weak spot is keyword coverage, which could add a few more synonyms buyers naturally say.

Dimension	Reasoning	Score
Specificity	Enumerates five distinct concrete actions (query GPU inventory, submit authenticated fixed-rate RFQ, inspect RFQ/procurement status, revoke device credentials, run gated node qualification) through the canonical CLI, with only minor gaps in crispness.	4 / 5
Completeness	Explicitly states both what the skill does (the enumerated actions) and when to use it via a concrete 'Use when a user asks to...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('find H100/H200 capacity', 'request a fixed compute rate', 'rent or purchase GPU compute') but is missing a few common synonyms or shorthand variants buyers might use.	4 / 5
Distinctiveness Conflict Risk	Targets a narrow niche (Itô compute RFQs, H100/H200 capacity) with distinct, domain-specific triggers that are unlikely to collide with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: affaan-m/ECC
Path: skills/ito-compute/SKILL.md
Commit: d8409a4

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.