agent-host-e2e-tests

Use when writing, recording, updating, validating, or troubleshooting the agent host end-to-end tests under src/vs/platform/agentHost/test/node/e2e (black-box tests that drive the whole agent host over the AHP protocol, using a CapiReplayProxy record/replay system for Claude/Copilot/Codex). Covers adding a cross-provider test, re-recording fixtures after an SDK bump, cross-platform Azure validation, gating non-deterministic or platform-specific tests, and diagnosing replay cache misses.

Quality

94%

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

96%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 lean, highly actionable skill body with clearly sequenced workflows and explicit validation/feedback loops for record/replay operations. Progressive disclosure is well-handled via the README pointer, though no bundled reference files accompany it.

Dimension	Reasoning	Score
Conciseness	Dense and directive throughout; it assumes Claude's competence (no explanation of AHP, protocols, or test frameworks) and every section carries actionable specifics with no padding.	5 / 5
Actionability	Provides copy-paste-ready commands (AGENT_HOST_REPLAY_RECORD=1 ./scripts/test-integration.sh --run …, gh auth token), concrete gate patterns ((RECORD ? test : test.skip)('…'), !isWindows), and named APIs (hostOnlyTest, dispatchTurn, waitForNotification).	5 / 5
Workflow Clarity	Four numbered workflows (A–D) with explicit validation checkpoints and feedback loops — review the diff, confirm green in plain replay, re-record after normalization fixes, cross-platform Azure validation before merge.	5 / 5
Progressive Disclosure	Clearly signals the e2e README as a one-level-deep source of truth and keeps the skill to workflows, with well-organized sections; no bundle files are present, so structure rests on in-skill organization and source-path references.	4 / 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 strong, specific, third-person description that clearly states both capabilities and trigger conditions for a well-bounded niche. Trigger terms are domain-accurate but lean technical, leaving slight room for more natural phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — writing, recording, updating, validating, troubleshooting e2e tests, adding cross-provider tests, re-recording fixtures after SDK bumps, Azure validation, gating, and diagnosing cache misses — giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (black-box tests driving the agent host over AHP via a CapiReplayProxy record/replay system) and when (Use when writing/recording/updating/validating/troubleshooting these tests) with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural trigger coverage ('writing, recording, updating, validating, or troubleshooting') for the niche, but the terms are heavily technical with few synonyms or lay variations.	4 / 5
Distinctiveness Conflict Risk	Tightly scoped to a specific test path, the AHP protocol, and CapiReplayProxy, giving a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/vscode
Path: .github/skills/agent-host-e2e-tests/SKILL.md
Commit: 123cec2

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.