Tessl • The management layer for AI agent skills

SkillPublic

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

Quality

89%

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

88%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.

An exceptionally actionable, dense skill: executable commands for every workflow, explicit statistical validation, and a genuinely useful CI bisecting guide. The main improvement opportunity is moving the CI-artifacts and mock-server detail into reference files to slim the main document.

Suggestions

Move the CI artifacts/retention table and the 'Finding and reading historic runs' gh command details into a references/ci.md file, keeping only the bisecting workflow inline.

Move the mock-server endpoint list and IS_SCENARIO_AUTOMATION setup details into a reference file, retaining just the one-line role of the mock server in the architecture section.

Trim the key-flags table to the most-used flags (--runs, --scenario, --build, --baseline-build, --no-baseline) and defer the rest to `pnpm run perf:chat --help`.

Dimension	Reasoning	Score
Conciseness	Nearly all content is operational knowledge Claude cannot infer — flags, exit codes, statistical methodology, retention windows — with no concept tutoring. Not 5 because the 20-row flags table, mock-server endpoint list, and CI artifact-retention details are fully inlined where `--help` or a reference file could carry some of the load.	4 / 5
Actionability	Copy-paste-ready commands throughout — `pnpm run perf:chat --scenario text-only --runs 3`, `--resume <path>` examples, `gh run list`/`gh api` with jq filters — covering the common cases, plus concrete interpretation thresholds (">2.0 MB/msg — likely leak"). Fully executable with no pseudocode.	5 / 5
Workflow Clarity	Clear sequences with explicit validation checkpoints: statistical significance gates before flagging regressions, exit code semantics, a resume feedback loop for inconclusive results, and the numbered 4-step regression-pinpointing workflow that includes "Confirm it's real vs. measurement noise" before deep-diving.	5 / 5
Progressive Disclosure	Well-organized sections with clearly signaled one-level-deep references to real repo files (`common/perf-scenarios.js`, `.github/workflows/chat-perf.yml`) and a pointer to `--help` for the full scenario list. Not 5 because no bundle reference files exist — CI artifact/retention detail and mock-server internals are inlined in SKILL.md where they could be split out for a ~310-line document.	4 / 5
	Total	18 / 20 Passed

Description

87%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 description: concrete actions, explicit targets, and a well-formed 'Use when' clause with three specific trigger scenarios. The only gap is that it undersells the skill's comparison and CI capabilities documented in the body.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions — "Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version" — matching the 'several specific actions, minor gaps' anchor. Not 5 because capabilities documented in the body (two-build comparison, CI gating, settings A/B testing) are not reflected in the description; not 3 because it goes beyond 1-2 generic actions with explicit build targets.	4 / 5
Completeness	Explicitly answers both: what ("Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version") and when ("Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks"), matching the anchor with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural trigger phrases — "chat rendering regressions", "perf-sensitive changes to chat UI", "memory leaks in the chat response pipeline" — that users investigating chat performance would plausibly say. Not 5 because common synonyms like "chat is slow", "laggy", or "janky" are missing; well above the 'generic keywords only' anchors.	4 / 5
Distinctiveness Conflict Risk	Clear niche — VS Code chat performance benchmarking and leak detection — with distinct, specific triggers; minimal overlap risk with generic document or code skills.	5 / 5
	Total	18 / 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: 4 missing, 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: microsoft/vscode
Path: .github/skills/chat-perf/SKILL.md
Revision: f357833

Reviewed: 6 days ago

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.

chat-perf

Table of Contents

Is this your skill?