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 'Claude Code native teams' adds some specificity, the overall description reads more like a fragment than a complete skill description.
Suggestions
Add a 'Use when...' clause specifying trigger scenarios, e.g., 'Use when the user wants to parallelize work across multiple Claude agents, distribute tasks, or run concurrent sub-tasks using Claude Code teams.'
List specific concrete actions the skill performs, e.g., 'Spawns N coordinated Claude Code agents, splits a task list into parallel work items, manages a shared task queue, and merges agent outputs.'
Include natural trigger terms users might say, such as 'parallel agents', 'multi-agent', 'distribute work', 'concurrent tasks', 'team of agents', 'swarm'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description is vague — 'N coordinated agents on shared task list' does not describe concrete actions. It hints at a coordination mechanism but doesn't specify what actions are performed (e.g., spawning agents, splitting tasks, merging results). | 1 / 3 |
Completeness | The description partially addresses 'what' (coordinating agents on a shared task list) but is very weak on specifics, and completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'agents', 'shared task list', and 'Claude Code native teams' that a user familiar with multi-agent workflows might use, but misses common natural variations like 'parallel', 'multi-agent', 'distribute work', or 'concurrent tasks'. | 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 extraordinarily comprehensive and actionable, with excellent workflow clarity including validation checkpoints, error recovery, and explicit sequencing. However, it is severely over-engineered for a SKILL.md body — at 800+ lines it includes implementation details (Runtime V2, dynamic scaling, outbox readers, git worktree API reference, legacy comparison tables) that should be split into separate reference files. The content quality is high but the presentation violates token efficiency and progressive disclosure principles.
Suggestions
Extract API reference tables (git worktree functions, outbox readers, getTeamStatus), Runtime V2 details, dynamic scaling, and per-role provider routing into separate reference files (e.g., WORKTREE.md, RUNTIME_V2.md, ROUTING.md) and link to them from the main skill.
Remove the legacy Swarm comparison table entirely — it's historical context that doesn't help Claude execute the skill.
Move the Configuration section (omc.jsonc schemas, env overrides, roleRouting examples) to a CONFIG.md reference file, keeping only a brief mention of configurable options.
Trim explanatory prose throughout — e.g., the 'Goal Workflow Relationship' paragraph, 'Parallel session caveats', and 'Pre-flight Analysis' sections add context Claude can infer from the workflow itself.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~800+ lines. It explains architecture, storage layouts, comparison tables with legacy systems, internal implementation details (outbox readers, worktree APIs, event-driven runtime internals), and configuration schemas that Claude doesn't need in the SKILL.md body. Much of this content (API reference tables, git worktree functions, runtime V2 details, dynamic scaling) should be in separate reference files or is implementation detail that doesn't belong in a skill instruction. | 1 / 3 |
Actionability | The skill provides highly concrete, executable guidance throughout: specific JSON payloads for every tool call (TeamCreate, TaskCreate, TaskUpdate, SendMessage), exact state_write/state_read invocations, complete agent preamble templates, and step-by-step bash commands. The examples are copy-paste ready with realistic data. | 3 / 3 |
Workflow Clarity | The multi-step workflow is exceptionally well-sequenced across 7 phases with clear entry/exit criteria for each pipeline stage. Validation checkpoints are explicit (team-verify stage, fix loops with max attempts, shutdown blocking protocol with exact ordering). Error recovery is thoroughly covered with feedback loops for stuck workers, failed tasks, crashed teammates, and dependency blocks. | 3 / 3 |
Progressive Disclosure | This is a monolithic wall of text with no bundle files to offload content to. The API reference tables (git worktree functions, outbox readers, configuration schemas), the legacy comparison table, Runtime V2 details, dynamic scaling, per-role provider routing, and CLI worker details should all be in separate reference files. Everything is inlined into one massive document with no external references for advanced topics. | 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 (1083 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
3e94567
- 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.