running-tests

running tests at various levels from smoke tests to full suite to randomized tests

1.75x

Quality

77%

Does it follow best practices?

Impact

100%

1.75x

Average score across 3 eval scenarios

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/running-tests/SKILL.md

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.

The content is highly actionable with fully executable commands and a clearly sequenced, validated test-level workflow backed by checklists. Its only real weaknesses are minor flag repetition that could be tightened and the lack of any external reference files for the sizeable inline test-name catalog.

Suggestions

Define the quiet-output flags ('--ll fatal -r simple --disable-dots --abort') once and reference them, instead of repeating the full set in every example block and the ALWAYS list.

Move the 'Example Test Names by Area' catalog into a references/ file and link to it from Level 2, keeping only a few representative examples inline.

Optionally extract the sanitizer/extra-checks configure-and-rebuild recipes into a references/ file to slim the Level 4–5 sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient commands and tables with no conceptual padding about what tests are, but the quiet-output flags ('--ll fatal -r simple --disable-dots --abort') are repeated across many blocks and the ALWAYS section restates them, giving minor over-explanation that could be trimmed — matching anchor 4 rather than the lean anchor 5.	4 / 5
Actionability	Fully executable, copy-paste-ready commands throughout ('./stellar-core test ...', 'make check', './configure ...') with specific examples covering common cases such as tag patterns, sanitizer configs, and parallel execution, matching anchor 5.	5 / 5
Workflow Clarity	Levels 1–5 are clearly sequenced 'in order of increasing cost' with explicit 'Stop at the first failure' validation, build verification before sanitizers, a tx-meta baseline check, and ALWAYS/NEVER checklists — matching anchor 5's clear sequence with validation steps and feedback loops.	5 / 5
Progressive Disclosure	Well organized into clear sections with good navigation, but it is a single 380-line file with no bundle references, and the 'Example Test Names by Area' catalog is inline material that could be split into a reference file — matching anchor 4's 'good structure; minor organization gaps' rather than anchor 5.	4 / 5
	Total	18 / 20 Passed

Description

66%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.

The description clearly communicates what the skill does and lists concrete test levels, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Trigger terms and specificity are solid, and it is reasonably distinct from unrelated skills.

Suggestions

Add an explicit trigger clause, e.g. 'Use when running tests after code changes, especially for tiered/progressive test execution from smoke tests to the full suite'.

Include common synonyms such as 'unit tests' and 'test suite' to broaden natural-keyword coverage.

Clarify the randomized-tests reference (e.g. mention RNG-seeded/fuzz tests) so it reads as a concrete action rather than a generic level.

Dimension	Reasoning	Score
Specificity	Names the domain (running tests) and several concrete test levels — 'smoke tests', 'full suite', 'randomized tests' — giving multiple specific actions with only minor gaps, matching the anchor 4 'lists several specific actions'.	4 / 5
Completeness	Has a clear 'what' (running tests at various levels) but no explicit 'Use when...' / trigger clause; per the judging guidelines a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains natural phrases a developer would say ('running tests', 'smoke tests', 'full suite', 'randomized tests') with good coverage, though it misses synonyms like 'unit tests' or 'test suite', fitting anchor 4 rather than the comprehensive anchor 5.	4 / 5
Distinctiveness Conflict Risk	Targets a distinct niche (tiered test execution by cost) and is unlikely to fire for unrelated skills, with only minor overlap risk against other testing-related skills, matching anchor 4.	4 / 5
	Total	15 / 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: stellar/stellar-core
Path: .claude/skills/running-tests/SKILL.md
Commit: 457f20b

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.