agent-teams

Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement

Quality

40%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/agent-teams/SKILL.md

Quality

Discovery

32%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description identifies a specific domain (agent team-based development with TDD) but lacks concrete action verbs, explicit trigger guidance ('Use when...'), and natural user keywords. The word 'default' is ambiguous and doesn't help Claude decide when to select this skill. It reads more like a title than a functional description.

Suggestions

Add an explicit 'Use when...' clause, e.g., 'Use when the user wants to coordinate multiple Claude Code agents to work on a project together, or mentions team-based development, parallel coding, or multi-agent workflows.'

List specific concrete actions the skill performs, e.g., 'Orchestrates multiple Claude Code agents to develop features in parallel, enforces test-driven development by requiring tests before implementation, manages task assignment and pipeline stages.'

Include natural trigger terms users might say, such as 'multi-agent', 'parallel development', 'test-driven development', 'TDD', 'sub-agents', 'agent coordination', 'team coding'.

Dimension	Reasoning	Score
Specificity	Names the domain ('team-based development') and mentions a specific methodology ('strict TDD pipeline enforcement'), but doesn't list concrete actions like 'create tests', 'run pipelines', 'assign tasks to agents', etc.	2 / 3
Completeness	Provides a partial 'what' (team-based development with TDD pipeline enforcement) but completely lacks a 'when' clause or any explicit trigger guidance for when Claude should select this skill.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'TDD', 'team-based development', and 'pipeline', but misses common user variations like 'test-driven development', 'multi-agent', 'parallel agents', 'sub-agents', or 'coding workflow'.	2 / 3
Distinctiveness Conflict Risk	The combination of 'Agent Teams' and 'TDD pipeline enforcement' provides some distinctiveness, but 'team-based development' is broad enough to overlap with other collaboration or multi-agent skills, and 'default' in the description adds ambiguity.	2 / 3
	Total	7 / 12 Passed

Implementation

47%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This skill has excellent workflow clarity with a well-defined, strictly ordered pipeline and explicit quality gates, but suffers significantly from verbosity — the same pipeline information is repeated in multiple formats (ASCII diagrams, tables, step-by-step prose). Actionability is moderate: the workflow is clear conceptually but lacks executable commands and concrete code examples for key operations like agent spawning, task creation, and verification commands.

Suggestions

Eliminate redundant representations of the pipeline — pick ONE format (e.g., the task dependency chain) and remove the duplicate ASCII art diagram and the step-by-step prose that repeats the same information.

Add concrete, executable examples for key operations: actual `TaskCreate` invocations with real parameters, actual agent spawn commands, and actual verification commands rather than just describing what happens.

Move the detailed task dependency chain model, parallel execution diagrams, and inter-agent communication examples into a separate reference file (e.g., TASK-CHAINS.md) and link from the main SKILL.md.

Remove the agent roster ASCII art box since the same information is already in the table below it — keep only the table which is more scannable.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~400+ lines with massive ASCII art diagrams, redundant information (the pipeline is described at least 3 times in different formats), and extensive explanations of concepts that could be conveyed far more efficiently. The task dependency chain is shown as a diagram, then as a parallel execution diagram, then described again in the feature agent workflow section. The agent roster is shown as ASCII art AND as a table.	1 / 3
Actionability	Provides concrete task naming conventions, branch naming patterns, and a clear pipeline structure, but lacks executable code/commands for most operations. References like `/spawn-team`, `/ralph-loop`, and `/code-review` are mentioned but never shown with actual invocation syntax. The agent definition format is deferred to 'see agent files' without examples. The settings.json example is present but the env var value looks like a placeholder.	2 / 3
Workflow Clarity	The 10-step pipeline is extremely well-defined with explicit task dependencies, blocking rules, and verification checkpoints at every stage. Quality gates are clearly specified (RED verify, GREEN verify, coverage >= 80%), feedback loops exist (fix and re-request review/scan), and the ordering enforcement via task dependencies is explicitly called out as structurally impossible to skip.	3 / 3
Progressive Disclosure	References other skills (base.md, code-review.md, security.md, etc.) and agent definition files, but the SKILL.md itself is monolithic with all content inline. The ASCII diagrams, tables, and detailed workflows could be split into referenced files. No bundle files are provided despite the skill referencing agent definition templates in `agents/` subdirectory, and the integration table references many skills without clear navigation paths.	2 / 3
	Total	8 / 12 Passed

Validation

90%

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 — 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: alinaqi/claude-bootstrap
Commit: f584bd0

Reviewed: 1 minute 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.