agentteams-test

Complete AgentTeams test cycle including installation, uninstallation, running tests, and exporting debug logs for analysis. Use for (1) verifying AgentTeams functionality (2) CI/CD test validation (3) issue diagnosis and debugging (4) pre-merge testing. Trigger words: test AgentTeams, run AgentTeams tests, agentteams test, make test, verify AgentTeams installation.

Quality

81%

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

76%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.

Highly actionable content with concrete executable commands and good structure, undermined by missing validation checkpoints around destructive cleanup/uninstall operations. Progressive disclosure is sound with a real reference file.

Suggestions

Add explicit validation checkpoints before destructive steps — e.g., confirm tests passed before 'make uninstall', and prompt/verify before 'docker rm -f' and 'rm -rf ./agentteams' in the Cleanup section.

De-duplicate the git clone instructions between Quick Start and Step 1, and trim the raw ANSI-escape-laden terminal output in Test Results Interpretation to a clean summary.

Resolve the troubleshooting overlap: keep diagnosis steps in references/troubleshooting.md and have the Common Issue Diagnosis section briefly signal to it rather than inlining the same PHASE_DONE/@manager analysis.

Dimension	Reasoning	Score
Conciseness	Mostly lean command-driven content with minor repetition (clone appears in both Quick Start and Step 1) and a slightly noisy raw terminal dump including ANSI escape codes in Test Results Interpretation.	4 / 5
Actionability	Dense copy-paste-ready bash commands throughout — clone, config, make test, docker exec/log inspection, debug script invocations — covering the common cases concretely.	5 / 5
Workflow Clarity	Steps are clearly sequenced (Step 1-3, install→test→uninstall) but the workflow involves destructive/batch operations (make uninstall, docker rm -f, rm -rf) with no explicit validation checkpoints before them, capping clarity at 3 per the destructive-operations guideline.	3 / 5
Progressive Disclosure	Well-organized sections with a one-level-deep reference to references/troubleshooting.md (a real file) plus external README links; minor overlap where troubleshooting content is both inlined and referenced.	4 / 5
	Total	16 / 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 that explicitly covers both capabilities and use-when triggers with natural trigger words. Minor specificity gap where actions are slightly high-level rather than fully granular.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'installation, uninstallation, running tests, and exporting debug logs' — covering the test cycle, but the actions are somewhat high-level compared to the granular anchor-5 example.	4 / 5
Completeness	Clearly answers both 'what' (complete test cycle: install/uninstall/test/export logs) and 'when' via an explicit 'Use for (1)...(4)' clause with concrete trigger cases.	5 / 5
Trigger Term Quality	Explicit 'Trigger words: test AgentTeams, run AgentTeams tests, agentteams test, make test, verify AgentTeams installation' gives good natural-phrase coverage, though most are variations on 'test' with a few synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Scoped to a specific 'AgentTeams test cycle' niche with distinct triggers (make test, agentteams test), giving minimal overlap risk with other 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: 1 missing	Warning

	Total	15 / 16 Passed

Repository: agentscope-ai/AgentTeams
Path: tests/skills/agentteams-test/SKILL.md
Commit: 69c5849

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.