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

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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 and strong validation/feedback loops appropriate to its destructive real-machine context. The main weakness is conciseness — repeated scratchpad/seed guidance and large inlined reference-style sections could be consolidated or split into bundled files.

Suggestions

Consolidate the repeated scratchpad dated-subfolder and import-path-depth guidance into a single section; it is currently restated under both 'Develop and Watch a Runner' and 'Non-Chat VS Code Scenarios'.

Move the 'Reuse these patterns' list and the seed-copy rules into a reference file (e.g. scripts/README or a PROFILES.md) and link to it one level deep, reducing inline bulk.

Tighten the 'Profiles and Auth' section by removing redundant invocations already shown in the Chat Workflow examples.

Dimension	Reasoning	Score
Conciseness	Mostly efficient domain-specific guidance, but notable repetition — the scratchpad dated-subfolder convention, import-path-depth, and seed-copy rules are restated across 'Develop and Watch a Runner' and 'Non-Chat VS Code Scenarios', and could be tightened.	3 / 5
Actionability	Fully executable, copy-paste-ready bash and JavaScript snippets with specific flags (--iterations, --heap-snapshot-label, --no-heap-snapshots, --keep-open) covering the common Chat smoke, snapshot, profile, and watch cases.	5 / 5
Workflow Clarity	An explicit 8-step 'Story' sequence with validation checkpoints ('Run a fast smoke', 'Verify the run', 'Verify Before Analyzing' checklist) and feedback loops (validate with --no-heap-snapshots first, fix-and-rerun like-for-like) for destructive real-machine operations.	5 / 5
Progressive Disclosure	Well-signaled one-level-deep references to the checked-in scripts (all three referenced files exist in scripts/) and the heap-snapshot-analysis handoff, but substantial inlined guidance (reuse-patterns list, safety, seed-copy rules) could be split into reference files to improve navigation.	4 / 5
	Total	17 / 20 Passed

Description

96%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 strong, specific description that clearly states capabilities and provides an explicit 'Use when…' trigger clause with concrete, natural trigger phrases. The only minor gap is some overlap risk with the sibling heap-snapshot-analysis skill, which the description partly mitigates by scoping to 'before heap-snapshot analysis'.

Dimension	Reasoning	Score
Specificity	Lists multiple specific 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, or drive a repeatable scenario' — covering the workflow comprehensively.	5 / 5
Completeness	Explicitly answers both what ('Run agent-driven VS Code performance or memory investigations') and when ('Use when asked to launch Code OSS, automate a VS Code scenario...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural terms with synonyms — 'VS Code performance or memory investigations', 'heap snapshots', 'workflow screenshots', 'run summaries', 'Chat memory smoke runner' — phrases a user would naturally say when they need this skill.	5 / 5
Distinctiveness Conflict Risk	Clear niche (VS Code perf/memory automation) with distinct triggers and an explicit handoff boundary ('before heap-snapshot analysis'), but minor overlap risk with the closely related heap-snapshot-analysis sibling skill keeps it just below a 5.	4 / 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: posit-dev/positron
Path: .github/skills/auto-perf-optimize/SKILL.md
Commit: 75a1182

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.