qzcli
Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list jobs", "batch submit", or needs to manage distributed training jobs on a Qizhi instance.
71
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Risky
Do not use without reviewing
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that clearly identifies the tool (qzcli), the platform (Qizhi), and the specific actions it supports. It includes a comprehensive 'Use when' clause with both English and Chinese trigger terms, making it highly discoverable. The description is concise, uses third-person voice, and is clearly distinguishable from other skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple concrete actions: manage GPU compute jobs, submit job, stop job, batch submit, list jobs, check compute groups, and manage distributed training jobs. These are specific, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers both 'what' (manage GPU compute jobs on the Qizhi platform using qzcli) and 'when' (explicit 'Use when' clause with a comprehensive list of trigger terms and scenarios). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms including both English and Chinese variants: 'qzcli', '启智平台', 'submit job', 'stop job', '查计算组', 'avail', 'list jobs', 'batch submit', and 'distributed training jobs'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a specific platform (Qizhi/启智), a specific CLI tool (qzcli), and a specific domain (GPU compute job management). Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, highly actionable skill that provides comprehensive CLI reference for the qzcli tool with concrete, executable examples throughout. Its main weakness is length — the document tries to be both a quick reference and a comprehensive guide in one file, which hurts conciseness and progressive disclosure. The workflow clarity is excellent with dry-run validation steps and a clear quick-start sequence.
Suggestions
Split detailed sections (batch config format, HPC jobs, full parameter table, troubleshooting) into separate referenced files to improve progressive disclosure and reduce the main SKILL.md to a concise overview.
Consolidate the authentication section — the four login variants could be reduced to two (interactive + scripted) with a brief note about other options.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient and avoids explaining basic concepts, but it's quite long with some redundancy (e.g., multiple authentication examples that could be condensed, the env-var passthrough section adds marginal value). The parameter table and troubleshooting table are useful but the overall document could be tightened by ~20-30%. | 2 / 3 |
Actionability | Excellent actionability throughout — every section provides concrete, copy-paste-ready commands with real flags and arguments. The batch config JSON example is complete and executable, the parameter table is specific, and even the troubleshooting section maps problems to concrete fixes. | 3 / 3 |
Workflow Clarity | The Quick Start section provides a clear numbered sequence (login → discover resources → check availability → list jobs). Job submission includes a dry-run validation step before actual submission. Batch submission includes --dry-run and --continue-on-error flags. The troubleshooting table serves as an error recovery guide. The workflow is well-sequenced throughout. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear section headers and logical grouping, but it's a monolithic document that could benefit from splitting detailed sections (batch config format, HPC jobs, troubleshooting) into separate referenced files. For a skill of this length (~200+ lines), keeping everything inline reduces scannability. No bundle files are provided to offload detail. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
81%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 | |
- Commit
66b974e
- 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.