repro-flaky-tests

Reproduce and investigate flakiness in a test.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/repro-flaky-tests/SKILL.md

Quality

Content

92%

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

The body is highly actionable, concise, and sequenced with validation checkpoints and feedback loops — strong across actionability, conciseness, and workflow clarity. The only gap is progressive disclosure: everything lives inline in one file with no separate reference materials.

Suggestions

Split per-agent detail (local-repro, bot-repro, fix-test) into separate reference files linked from a short overview in SKILL.md to improve progressive disclosure.

Consider extracting the stressor-bot command matrix and screenshot/auth caveats into a dedicated reference so the main body stays a concise overview.

Dimension	Reasoning	Score
Conciseness	The body is lean and operational with exact commands, flags, and durations, and never explains concepts Claude already knows; every line earns its place.	3 / 3
Actionability	It provides fully executable commands with real flags (e.g. `git cl try -B devtools-frontend/try -b e2e_stressor_linux ...`) and concrete examples like the results table, all copy-paste ready with clearly marked placeholders.	3 / 3
Workflow Clarity	The multi-agent process is clearly sequenced (local-repro, bot-repro, fix-test) with explicit validation checkpoints ("at least one test ran to completion", "always verify by running the tests again") and a retry feedback loop for failed fixes.	3 / 3
Progressive Disclosure	Sections are well-organized but the skill is a single monolithic SKILL.md with no bundle files and inlines a long per-agent workflow that could be split out, rather than being an overview pointing to separate detailed materials.	2 / 3
	Total	11 / 12 Passed

Description

50%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is short and on-domain but lacks an explicit "when to use" trigger and richer natural-language keywords. It clears the bar over the vague bad examples yet misses the explicit-trigger completeness required for a top score.

Suggestions

Add an explicit trigger clause, e.g. ".Use when a test fails intermittently or the user reports a flaky test."

Broaden natural keywords to phrases users actually say, such as "flaky test," "intermittent test failure," or "test failing sometimes."

List more concrete actions (reproduce locally, run stressor bots, propose a fix) to lift specificity from two actions to a comprehensive set.

Dimension	Reasoning	Score
Specificity	"Reproduce and investigate flakiness" names the domain (flaky tests) and two concrete actions, but does not list a comprehensive set of specific actions like the top anchor requires.	2 / 3
Completeness	It states what the skill does ("Reproduce and investigate flakiness in a test") but provides no "Use when..." trigger clause, so per the guidelines completeness is capped at 2.	2 / 3
Trigger Term Quality	"flakiness" and "test" are natural enough terms, but coverage is sparse and omits common variations a user would actually say such as "flaky test" or "intermittent test failure."	2 / 3
Distinctiveness Conflict Risk	"flakiness in a test" carves a reasonably specific niche but is terse and could still overlap with general test-running skills since no distinct triggers are spelled out.	2 / 3
	Total	8 / 12 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: ChromeDevTools/devtools-frontend
Path: .agents/skills/repro-flaky-tests/SKILL.md
Commit: 184a74d

Reviewed: 3 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.