qsv-performance

Performance guide covering index files, stats cache, and frequency cache accelerators for qsv

Quality

75%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skills/qsv-performance/SKILL.md

Quality

Content

92%

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

The body is a lean, highly actionable performance reference with a clear size-based decision tree and concrete commands. Its only weakness is that all material is inline with no progressive disclosure to reference files.

Dimension	Reasoning	Score
Conciseness	The body is dense and table-driven with no explanation of concepts Claude already knows; every section (benefit tables, decision tree, tips) earns its tokens.	3 / 3
Actionability	It gives fully executable commands and concrete thresholds throughout (e.g. 'qsv index', 'qsv stats --cardinality --stats-jsonl', 'mcp__qsv__qsv_to_parquet', 'slice --len N', and the 10MB/100MB/1GB tiers).	3 / 3
Workflow Clarity	The 'Large File Decision Tree' sequences decisions by file size with explicit per-tier actions and rules, and the Timeout Handling section provides an error-recovery feedback loop (exit 124 -> Polars alternative or split).	3 / 3
Progressive Disclosure	The content is well-organized into clear sections but everything lives inline in one ~115-line file with no one-level-deep references to split out the large tables or Parquet details, matching the 'content that should be separate is inline' anchor.	2 / 3
	Total	11 / 12 Passed

Description

57%

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 specific to qsv and names concrete accelerators, but it omits any explicit 'Use when' trigger guidance and relies on a weak action verb. Adding trigger conditions would lift completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when working with large CSVs in qsv, speeding up repeated qsv commands, or choosing memory-efficient qsv commands.'

Replace the generic verb 'covering' with concrete actions like 'Speeds up qsv by creating index files, building stats/frequency caches, and selecting Polars commands.'

Include natural user phrases such as 'large CSV', 'speed up qsv', and 'qsv performance' alongside the technical cache names.

Dimension	Reasoning	Score
Specificity	The phrase 'covering index files, stats cache, and frequency cache accelerators' names several concrete accelerators, but the only action verb is the generic 'covering', so it names the domain and items without comprehensive concrete actions.	2 / 3
Completeness	It states what the skill covers ('Performance guide covering...accelerators for qsv') but provides no 'Use when...' trigger guidance, so the 'when' is entirely missing and completeness is capped at 2 per the guidelines.	2 / 3
Trigger Term Quality	'Performance', 'index files', 'stats cache', 'frequency cache', and 'qsv' give some relevant keywords, but common user variations like 'speed up', 'fast', or 'large CSV' are missing and the cache terms are somewhat technical.	2 / 3
Distinctiveness Conflict Risk	Tying the description explicitly to 'qsv' and its specific accelerators gives it a clear niche that is unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 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: dathere/qsv
Path: .claude/skills/skills/qsv-performance/SKILL.md
Commit: 17c10db

Reviewed: about 6 hours 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.