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

92%

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

85%

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

A highly actionable, well-sequenced workflow with strong validation checkpoints and correctly externalized runner scripts. The main weakness is conciseness: the body is long and repeats profile/auth guidance across sections that could be consolidated.

Suggestions

Consolidate the recurring --keep-open / sign-in-once / persistent-profile guidance into a single 'Profiles and Auth' reference and link to it from the Chat workflow and watch-loop sections instead of restating it each time.

The 'Develop and Watch a Runner' and 'Non-Chat VS Code Scenarios' sections overlap on scratchpad folder conventions and reuse patterns; merge the duplicated naming/import-depth and reuse-pattern guidance into one place.

Tighten the Playwright @playwright/cli checkpoint list and the 'Important runner behavior' list by folding near-duplicate bullets (e.g., auth/keep-open handling) into single statements, removing repetition without losing the safety warnings.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational rather than explaining known concepts, but at ~270 lines it repeats the '--keep-open / sign-in-once / persistent-profile' pattern across the Chat workflow, Profiles and Auth, and watch-loop sections, and could be consolidated. It is mostly efficient but not tight, matching the level-2 anchor rather than the lean level-3.	2 / 3
Actionability	Copy-paste-ready bash and JavaScript examples, concrete flags (--no-heap-snapshots, --heap-snapshot-label, --keep-open, --user-data-dir), and explicit file paths give fully executable guidance, matching the top anchor.	3 / 3
Workflow Clarity	The 8-step 'Story' is clearly sequenced with explicit validation checkpoints — fast smoke with snapshots disabled, a 'Verify Before Analyzing' summary.json checklist, and an error-recovery loop (screenshot + incremental summary.json when stuck) — matching the level-3 anchor.	3 / 3
Progressive Disclosure	Heavy runner detail is externalized into the verified-present scripts/ bundle (chat-memory-smoke.mts, chat-session-switch-smoke.mts, userDataProfile.mts), each linked and described one level deep with a clear handoff to the heap-snapshot-analysis skill; no nested references. Matches the well-signaled one-level-deep anchor.	3 / 3
	Total	11 / 12 Passed

Description

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.

A strong, third-person description that pairs a concrete capability statement with an explicit 'Use when' trigger list and a well-scoped niche. Voice is correct and over-claiming is absent. No changes needed.

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' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Clearly answers both 'what' ('Run agent-driven VS Code performance or memory investigations') and 'when' (explicit 'Use when asked to...' clause), matching the top anchor.	3 / 3
Trigger Term Quality	Natural terms a user would say ('VS Code', 'memory', 'heap snapshots', 'screenshots', 'scenario') appear with an explicit 'Use when asked to...' trigger covering several common phrasings; not merely technical jargon.	3 / 3
Distinctiveness Conflict Risk	Niche is clearly scoped to VS Code/Code OSS performance and memory investigation, and it even distinguishes itself from heap-snapshot-analysis ('before heap-snapshot analysis'), making cross-skill conflict unlikely.	3 / 3
	Total	12 / 12 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: b87c504

Reviewed: 2 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.