arn-code-execute-plan-teams
This skill should be used when the user says "execute plan with teams", "run plan teams", "execute with agent teams", "team execution", "execute plan with agent teams instead of subagents", "teams mode", "agent teams mode", "execute with teams", or wants to execute a structured project plan using Claude Code's experimental Agent Teams feature. Creates a team of executor, reviewer, and architect teammates that collaborate on task implementation with built-in quality gates. Requires the experimental Agent Teams feature to be enabled. For standard subagent-based execution, use arn-code-execute-plan instead.
90
88%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that excels across all dimensions. It provides comprehensive trigger phrases, clearly explains what the skill does and when to use it, and explicitly differentiates itself from a closely related skill. The only minor weakness is that the long list of quoted trigger phrases at the beginning feels somewhat mechanical, but this is a stylistic concern rather than a functional one.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists specific concrete actions: creates a team of executor, reviewer, and architect teammates that collaborate on task implementation with built-in quality gates. Also specifies the prerequisite (experimental Agent Teams feature) and differentiates from the alternative skill. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates a team of executor, reviewer, and architect teammates that collaborate on task implementation with quality gates) and 'when' (explicit list of trigger phrases plus the general condition of wanting to execute a plan using Agent Teams). Also includes a disambiguation clause pointing to the alternative skill. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger phrases users would say: 'execute plan with teams', 'run plan teams', 'team execution', 'teams mode', 'agent teams mode', 'execute with teams'. These are realistic phrases a user would naturally type. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear differentiation from the related 'arn-code-execute-plan' skill. The 'teams' and 'agent teams' trigger terms create a clear niche, and the explicit disambiguation clause ('For standard subagent-based execution, use arn-code-execute-plan instead') further reduces conflict risk. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill for orchestrating Claude Code Agent Teams. Its greatest strengths are the clear 6-step workflow with explicit validation gates, intervention triggers, and error recovery paths. The main weakness is its length — the detailed teammate spawn prompt specifications and cost considerations add bulk that could be extracted or trimmed, though the complexity of the orchestration task partially justifies the verbosity.
Suggestions
Consider extracting the detailed teammate spawn prompt specifications (executor, reviewer, architect) into a separate reference file to reduce the main skill's length while preserving the high-level team composition overview inline.
Trim the cost considerations section — Claude doesn't need explanations like 'Each teammate is a full Claude Code session with its own context window'; a simple cost multiplier note suffices.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably efficient for its complexity but includes some sections that could be tightened — the cost considerations section explains obvious implications, and some spawn prompt details are overly verbose. However, most content is necessary given the multi-teammate orchestration complexity. | 2 / 3 |
Actionability | Provides highly concrete, executable guidance throughout: specific bash commands to check env vars, exact JSON config snippets, precise directory structures, specific task naming conventions (IMPL-N/REVIEW-N), exact test targeting commands (pytest/jest patterns), and clear verdict logic with specific actions for each outcome. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear sequencing (Steps 1-6), explicit validation checkpoints (env var check, project structure verification, task list verification), feedback loops (needs-fixes -> executor fixes -> re-review, with escalation after 2 cycles), and well-defined intervention triggers for error recovery. | 3 / 3 |
Progressive Disclosure | The skill references external files appropriately (pattern-refresh.md, INTRODUCTION.md, templates) and positions itself in a pipeline, but the main body is quite long and monolithic. The detailed spawn prompt specifications for each teammate could potentially be extracted to reference files. No bundle files were provided to verify referenced paths. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- AppsVortex/arness
- Commit
1fe948f
- Reviewed
Table of Contents
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.