review-performance

Use when reviewing a branch diff for performance defects — redundant database round trips, N+1 queries, unbounded reads, per-request layer rebuilds, wasted client fetches, and build steps that ship a broken artefact — and reporting findings with P-C/W/I IDs in the four-field format.

Quality

92%

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

92%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 tightly engineered review skill with executable code, explicit validation feedback loops, and clean one-level-deep progressive disclosure into a verified reference file. The only weak spot is mild verbosity in the repeated skeleton-preservation philosophy passages.

Suggestions

Consolidate the repeated 'never rewrite the skeleton, only edit' guidance (currently restated in Step 0, Step 2, and the final check) into one statement to trim redundancy in the conciseness dimension.

Tighten the report-shape philosophy paragraphs in Step 0 — the argument for writing the skeleton first could be one sentence instead of a multi-paragraph justification.

Dimension	Reasoning	Score
Conciseness	Dense and purposeful with no padding of concepts Claude already knows, and it usefully explains repo-specific facts (D1 per-statement cost, the inWedding idiom, gh-merge-base), but the repeated 'do not rewrite the skeleton' warnings and discursive report-shape philosophy are minor redundancy that could be trimmed.	4 / 5
Actionability	Copy-paste-ready bash (skeleton cat-heredoc, git diff routing, shape-check grep), a concrete finding-format template, and specific fix idioms (EXISTS column, Promise.all, Effect.all with concurrency: 'unbounded') with a named copyable example file cover the common cases fully.	5 / 5
Workflow Clarity	Clearly sequenced Step 0 → Step 1 → Step 2 flow with explicit validation checkpoints (grep -c must print 4) at both mid-run and finish, plus feedback loops (shape failure → restore headings → re-edit) for a batch/destructive report-writing operation.	5 / 5
Progressive Disclosure	SKILL.md is a well-organized overview that keeps the most-exercised sections inline and offloads ten remaining checklist sections one level deep to the real references/checklists.md file with a clear, signaled pointer, making navigation easy.	5 / 5
	Total	19 / 20 Passed

Description

92%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 highly specific, well-triggered description that clearly states both what it does and when to use it, with concrete defect classes and a distinctive report format. Slightly short of perfect only on trigger-term breadth, where a few natural synonyms are absent.

Dimension	Reasoning	Score
Specificity	Names the domain (reviewing branch diffs for performance defects) and lists multiple concrete defect classes — 'redundant database round trips, N+1 queries, unbounded reads, per-request layer rebuilds, wasted client fetches, and build steps that ship a broken artefact' — plus a concrete reporting action with P-C/W/I IDs and a four-field format; comprehensive coverage, not minor gaps.	5 / 5
Completeness	Explicitly answers both what (find the listed performance defect classes and report findings with P-C/W/I IDs in the four-field format) and when ('Use when reviewing a branch diff for performance defects') with concrete trigger phrasing.	5 / 5
Trigger Term Quality	Natural phrases a user would say ('reviewing a branch diff', 'performance defects') and strong defect synonyms ('N+1 queries', 'round trips', 'unbounded reads') are present, but a few natural variations and any file-extension-style triggers are missing, so it is not exhaustive.	4 / 5
Distinctiveness Conflict Risk	Scoped tightly to performance review of a branch diff with specific defect classes and a unique P-C/W/I report format, giving it a clear niche with minimal overlap with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: xchromo/osn
Path: .claude/skills/review-performance/SKILL.md
Commit: 5438649

Reviewed: 13 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.