team
N coordinated agents on shared task list using Claude Code native teams
52
42%
Does it follow best practices?
Impact
Pending
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 language. The cryptic 'N coordinated agents' phrasing and absence of a 'Use when...' clause make it difficult for Claude to know when to apply this skill.
Suggestions
Add a 'Use when...' clause specifying triggers like 'parallel tasks', 'multiple agents', 'team coordination', or 'concurrent work'
Replace vague 'coordinated agents on shared task list' with specific actions like 'Spawns multiple Claude agents to work in parallel, manages task distribution, and synchronizes results'
Include natural trigger terms users would say such as 'parallelize', 'multi-agent', 'split work', 'concurrent execution', or 'team mode'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague language like 'coordinated agents' and 'shared task list' without explaining what concrete actions the skill performs. It doesn't specify what tasks are accomplished or how. | 1 / 3 |
Completeness | The description only vaguely hints at 'what' (coordinating agents) but provides no 'when' clause or explicit trigger guidance. There's no 'Use when...' statement explaining when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'agents', 'Claude Code', and 'teams' that users might mention, but lacks common variations and natural phrases users would say when needing multi-agent coordination. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Claude Code native teams' provides some specificity, but 'coordinated agents' and 'shared task list' are generic enough to potentially overlap with other task management or agent-related skills. | 2 / 3 |
Total | 6 / 12 Passed |
Implementation
62%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides exceptionally detailed and actionable guidance for team orchestration with clear workflows and validation checkpoints. However, it is severely over-engineered for a SKILL.md file - the extreme verbosity (800+ lines) wastes context window budget by explaining concepts Claude already understands and repeating information multiple times. The content would be more effective split into a concise overview with linked reference documents.
Suggestions
Reduce the main SKILL.md to ~150 lines covering core workflow, move detailed sections (Agent Preamble, CLI Workers, Git Worktree Integration, Comparison tables) to linked reference files
Remove redundant explanations - shutdown protocol is explained in detail 3+ times, consolidate to one authoritative section
Cut explanatory prose that describes what tools do (Claude knows what SendMessage does) and keep only the specific parameters and patterns unique to this skill
Move the extensive Gotchas section to a separate GOTCHAS.md file and link to it, keeping only the 2-3 most critical gotchas inline
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~800+ lines, explaining concepts Claude already knows (what PDF is, how tmux works, basic git operations). Contains extensive redundant explanations, multiple repetitions of the same concepts (shutdown protocol explained 3+ times), and excessive detail that could be condensed significantly. | 1 / 3 |
Actionability | Provides fully executable JSON examples for all tool calls (TeamCreate, TaskCreate, TaskUpdate, SendMessage), complete code snippets, specific command formats, and copy-paste ready templates including the full agent preamble and state management calls. | 3 / 3 |
Workflow Clarity | Excellent multi-step workflow with clear phases (Parse → Analyze → Create Team → Create Tasks → Spawn → Monitor → Completion), explicit validation checkpoints (verify completion before shutdown, wait for responses before TeamDelete), and detailed error recovery procedures with specific actions for each failure mode. | 3 / 3 |
Progressive Disclosure | Content is monolithic with everything inline rather than split into reference files. The 800+ line document could benefit from separating the agent preamble, CLI worker details, git worktree integration, and configuration into linked reference files. Some structure exists with clear headers but too much detail is inline. | 2 / 3 |
Total | 9 / 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 (969 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
48ffaac
- 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.