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

90%

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

81%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.

A strong, action-oriented skill body with executable commands, a validated multi-step workflow, and clear section structure. The main drag is redundant restatement of the same safety boundaries across sections, which costs tokens without adding information.

Suggestions

Consolidate the 'accept does not move funds or reserve capacity' boundary so it is stated once authoritatively (e.g. in Rent or purchase semantics) and only back-referenced elsewhere, rather than repeated verbatim in step 6 and Unsupported operations.

De-duplicate 'ECC itself does no browser automation' and the ITO_API_KEY-forwarding rule, each currently stated twice, into a single statement per topic.

Consider moving the MCP stdio JSON config and the live-node-qualification flag checklist into reference files to keep the overview shorter and let SKILL.md act as a clearer index.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and high-signal, but the same boundaries are restated several times ('does not move funds or reserve capacity' appears in step 6, the Rent/purchase section, and Unsupported operations; 'ECC itself does no browser automation' and the ITO_API_KEY forwarding rule each repeat), so it could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready commands throughout — a complete `ecc ito find` example with every flag, an `ecc ito evals` example, `ecc ito accept rfq_<ticket-id>`, and a full MCP stdio JSON config block.	5 / 5
Workflow Clarity	A clear 7-step CLI workflow with explicit validation checkpoints: a required-field RFQ checklist, the count == nodes * gpus-per-node invariant, and a status-check feedback loop after an ambiguous transport failure before retrying find.	5 / 5
Progressive Disclosure	Well-organized into clearly headed sections (Install, CLI workflow, Live node qualification, MCP workflow, Rent/purchase semantics, Unsupported operations) with no nested references, but at ~160 lines all content is inline and the MCP config or qualification detail could be split out for a leaner overview.	4 / 5
	Total	17 / 20 Passed

Description

100%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.

A dense, well-constructed description that explicitly answers both what the skill does and when to use it, with concrete actions and natural trigger phrases. Its only weakness is that it packs everything into one long compound sentence, but no content is fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — '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' — giving comprehensive coverage rather than vague abstractions.	5 / 5
Completeness	Both 'what' (five concrete capabilities via the canonical CLI) and 'when' ('Use when a user asks to find H100/H200 capacity...') are explicitly stated with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user-facing triggers with synonyms are present: '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'.	5 / 5
Distinctiveness Conflict Risk	A clear niche (Itô fixed-rate GPU compute RFQs, device credential revocation, gated node qualification) with distinct triggers and minimal overlap with other skills.	5 / 5
	Total	20 / 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: e04ea0b

Reviewed: 2 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.