team
N coordinated agents on shared task list using Claude Code native teams
39
38%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/team/SKILL.mdQuality
Discovery
22%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 description is too terse and vague to effectively guide skill selection. It lacks concrete actions, explicit trigger conditions, and natural user-facing keywords. While the mention of 'Claude Code native teams' provides a hint of specificity, the overall description fails to communicate what the skill does or when it should be used.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user wants to distribute work across multiple Claude Code agents, run parallel tasks, or coordinate a multi-agent workflow.'
List specific concrete actions the skill performs, e.g., 'Spawns N parallel Claude Code agents, assigns tasks from a shared task list, monitors progress, and aggregates results.'
Include natural trigger terms users would say, such as 'parallel agents', 'multi-agent', 'distribute tasks', 'concurrent work', 'fan-out', 'orchestrate agents'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description is vague — 'N coordinated agents on shared task list' does not describe concrete actions. It doesn't specify what the agents do, how they coordinate, or what outcomes are produced. | 1 / 3 |
Completeness | The description partially addresses 'what' (coordinated agents on a shared task list) but is very weak on specifics, and there is no 'when' clause or explicit trigger guidance at all. Per the rubric, a missing 'Use when...' clause caps completeness at 2, and the weak 'what' brings it to 1. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'agents', 'shared task list', and 'Claude Code native teams' that could match user queries about multi-agent coordination, but misses common variations like 'parallel', 'multi-agent', 'concurrent tasks', 'distribute work', or 'orchestrate'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Claude Code native teams' provides some distinctiveness, but 'coordinated agents on shared task list' is broad enough to overlap with other orchestration or task management skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is exceptionally thorough and actionable — every workflow step has concrete JSON payloads, clear sequencing, and explicit validation checkpoints. However, it is massively over-engineered as a single document: at 700+ lines it includes implementation details (Runtime V2, dynamic scaling, git worktree API, legacy comparison tables, per-role routing specs) that should be split into referenced sub-documents. The token cost is very high relative to what's needed for the core team orchestration workflow.
Suggestions
Split into a concise SKILL.md (core workflow: parse → decompose → create → spawn → monitor → complete, ~150 lines) with references to separate files: CLI-WORKERS.md, ROUTING.md, WORKTREES.md, RUNTIME-V2.md, CONFIGURATION.md
Remove the 'Comparison: Team vs Legacy Swarm' table entirely — the legacy system is deprecated and this comparison wastes tokens on every context load
Move the detailed Agent Preamble template, Communication Patterns examples, and Outbox monitoring details into referenced bundle files rather than inlining them
Remove explanatory content Claude already knows (e.g., what tmux panes are, how JSON files work, what git worktrees do conceptually) and keep only the specific API calls and constraints
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~700+ lines. It explains architecture diagrams, comparison tables with legacy systems, detailed internal state schemas, event-driven runtime details, git worktree APIs, dynamic scaling, and per-role provider routing — much of which is implementation documentation rather than actionable instruction. Claude doesn't need lengthy explanations of JSON file storage layouts or exhaustive comparison tables with deprecated systems. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance throughout: specific JSON payloads for every API call (TeamCreate, TaskCreate, TaskUpdate, SendMessage), complete agent preamble templates ready to inject, exact state_write/state_read calls with field schemas, and step-by-step shutdown protocols with specific message formats. Code examples are copy-paste ready. | 3 / 3 |
Workflow Clarity | The multi-step pipeline is clearly sequenced (team-plan → team-prd → team-exec → team-verify → team-fix) with explicit entry/exit criteria per stage, validation checkpoints (verify/fix loop with bounded retries), a detailed shutdown protocol marked as BLOCKING with exact ordering requirements, and error recovery paths for stuck/crashed/failed teammates. The watchdog policy adds time-based validation. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files to offload content to. The architecture diagrams, comparison tables, CLI worker details, git worktree API reference, runtime V2 details, dynamic scaling, per-role routing configuration, and outbox monitoring could all be separate referenced files. Everything is inlined into a single massive document, making it extremely difficult to navigate. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1041 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- Yeachan-Heo/oh-my-claudecode
- Commit
679b418
- 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.