evergreen

Evergreen CI infrastructure, configuration validation. Use when modifying .evergreen/ config, preparing to submit changes or understanding the Evergreen test matrix.

Quality

73%

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/evergreen/SKILL.md

Quality

Content

72%

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

A compact, well-structured skill with executable commands and clear sections. The main gaps are a verbose patch-build explanation and a missing validation-failure recovery loop.

Suggestions

Trim the explanatory sentence after 'evergreen patch -u' to a one-line note, since the command is largely self-explanatory.

Add an explicit feedback loop for validation failures, e.g. 'If validation reports errors, fix the config and re-run evergreen validate before submitting.'

Dimension	Reasoning	Score
Conciseness	The body is lean overall, but the patch-build paragraph ('This uploads your uncommitted and committed local changes as a patch build ...') re-explains what the command does and could be tightened.	2 / 3
Actionability	Two concrete, copy-paste-ready executable commands are provided: 'evergreen validate .evergreen/.evg.yml' and 'evergreen patch -u', matching the anchor-3 example.	3 / 3
Workflow Clarity	The validate-then-patch-test sequence has an explicit validation gate ('Always run this before submitting changes'), but there is no error-recovery feedback loop for when validation fails.	2 / 3
Progressive Disclosure	The skill is under 50 lines, single-purpose, and organized into clear sections with no need for external references, satisfying the simple-skills scoring note.	3 / 3
	Total	10 / 12 Passed

Description

75%

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 clear, well-triggered description for a narrow CI niche that answers both what and when explicitly. It is held back only by thin action enumeration and somewhat limited trigger-term coverage.

Suggestions

Add a short list of concrete capabilities (e.g. 'validate .evergreen config, create patch builds, inspect the test matrix') to raise specificity to the anchor-3 level.

Broaden trigger terms to include common variations users might say, such as 'patch build', 'CI build', or 'Evergreen config'.

Dimension	Reasoning	Score
Specificity	It names the domain ('Evergreen CI infrastructure') and one concrete action ('configuration validation'), but does not list multiple specific concrete actions, so it falls short of the anchor-3 example.	2 / 3
Completeness	It explicitly states both what ('Evergreen CI infrastructure, configuration validation') and when via an explicit 'Use when ...' trigger clause, matching the anchor-3 example.	3 / 3
Trigger Term Quality	Natural phrases like 'modifying .evergreen/ config', 'preparing to submit changes', and 'Evergreen test matrix' are present, but coverage is narrow and misses common variations such as 'patch build', 'CI', or 'Evergreen config'.	2 / 3
Distinctiveness Conflict Risk	The MongoDB Evergreen CI niche and the distinctive '.evergreen/ config' trigger make it clearly distinguishable and unlikely to fire for the wrong skill.	3 / 3
	Total	10 / 12 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: mongodb/mongo-java-driver
Path: .agents/skills/evergreen/SKILL.md
Commit: dd814f8

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.