auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

Quality

86%

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 thorough, highly actionable workflow skill with clear sequencing, validation checkpoints, and feedback loops. Its main weakness is conciseness — several coaching and general-debugging passages could be trimmed — and minor progressive-disclosure gaps from inlined reference detail and an unreferenced script.

Suggestions

Tighten or relocate the 'Root-Cause, Don't Treat Symptoms' section: it reads as general debugging wisdom Claude already knows; keep only the VS Code-specific lifecycle examples.

Move the detailed flag documentation and 'Seed-copy rules' into a references file (e.g. references/runner-flags.md) and link to it, reducing inlined reference-style content in SKILL.md.

Either document scripts/workbench-css-performance.mts in the 'Checked-in Runners' list or remove it from the bundle so the file listing matches the referenced scripts.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with high-value specifics (exact flags, import-path depth, summary.json fields), but coaching prose like 'The first version of an automation runner is rarely correct' and the general-debugging 'Root-Cause, Don't Treat Symptoms' section pad beyond what Claude needs.	3 / 5
Actionability	Abundant copy-paste-ready commands (node ... --iterations 3 --no-heap-snapshots, npx @playwright/cli invocations, mkdir/heredoc scratchpad setup, a complete compareSnapshots script) cover the common cases with specific flags and paths.	5 / 5
Workflow Clarity	An 8-step 'Story' sequence with explicit validation checkpoints ('Run a fast smoke', 'Verify the run', 'Validate with --no-heap-snapshots first'), a 'Verify Before Analyzing' checklist, and fix→rerun→compare feedback loops for the destructive snapshot runs.	5 / 5
Progressive Disclosure	Good structure with one-level-deep, clearly signaled links to real scripts in ./scripts/, but a fair amount of reference-style detail (flag docs, seed-copy rules) is inlined and scripts/workbench-css-performance.mts exists yet is never referenced.	4 / 5
	Total	17 / 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 well-crafted description that states concrete capabilities and provides an explicit, multi-trigger 'Use when' clause with a clear boundary against the related analysis skill. Only minor missing natural variations keep trigger term quality from a perfect score.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries' — giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both 'what' (agent-driven VS Code performance/memory investigations plus the enumerated actions) and 'when' via a concrete 'Use when asked to...' clause with multiple trigger phrases.	5 / 5
Trigger Term Quality	Strong natural keywords ('VS Code performance', 'memory investigations', 'heap snapshots', 'Code OSS') with synonyms, but lacks file extensions like '.heapsnapshot' and a few common phrasings a user might say.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (VS Code perf/memory + heap-snapshot capture) and explicitly scopes 'before heap-snapshot analysis', drawing a clean boundary with the sibling heap-snapshot-analysis skill.	5 / 5
	Total	19 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 2 missing	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	13 / 16 Passed

Repository: microsoft/vscode
Path: .github/skills/auto-perf-optimize/SKILL.md
Commit: 318df14

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.