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 coordination with TDD) but lacks concrete action details and completely omits a 'Use when...' clause, making it difficult for Claude to know when to select this skill. The trigger terms are somewhat relevant but miss common user phrasings, and the description reads more like a title than an informative selection guide.

Suggestions

Add an explicit 'Use when...' clause with trigger scenarios, e.g., 'Use when the user wants to coordinate multiple Claude agents for development tasks, mentions TDD workflows, or asks for test-driven team development.'

List specific concrete actions the skill performs, e.g., 'Orchestrates multiple Claude Code agents to develop features in parallel, enforces test-first development, manages task assignment, and coordinates code integration across agents.'

Include natural keyword variations users might say, such as 'test-driven development', 'multi-agent coding', 'parallel development', 'agent coordination', 'automated testing pipeline'.

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 'creates test files', 'runs test suites', 'assigns 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 'team-based development', 'TDD', and 'pipeline', but misses common user variations like 'test-driven development', 'multi-agent', 'parallel development', 'agent coordination', or 'testing 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 potentially overlap with other collaboration or development workflow skills.	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.

The skill excels at workflow clarity with an exceptionally well-defined 10-step TDD pipeline, explicit quality gates, and clear task dependency chains. However, it is severely over-verbose — repeating the same pipeline information in multiple formats (ASCII diagrams, prose, task chains, parallel execution diagrams) and including extensive detail that should be split into referenced files. Actionability suffers from lack of executable examples and concrete commands.

Suggestions

Reduce content by 50-60%: eliminate redundant representations of the pipeline (keep one diagram + the task dependency chain, remove the prose re-explanation and parallel execution diagram that repeats the same information)

Move the detailed agent roster, inter-agent communication examples, and branch/PR strategy into separate referenced files (e.g., AGENTS.md, COMMUNICATION.md) to make SKILL.md a concise overview

Add concrete, executable examples: show the actual `/spawn-team` command syntax, a real agent frontmatter definition, and the correct environment variable setting (current JSON looks like a comment, not a real config)

Provide bundle files for the referenced agent definitions (.claude/agents/*.md) so the skill's references are verifiable and the progressive disclosure structure is complete

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~350+ lines with massive ASCII art diagrams that repeat information (the pipeline is described three times: as a diagram, as prose steps, and as a task chain). The parallel execution diagram, inter-agent communication examples, and agent roster table all duplicate information already conveyed. Much of this content (what agents do, how task dependencies work) could be conveyed in a fraction of the space.	1 / 3
Actionability	The skill describes a detailed workflow with specific task naming conventions and agent roles, but lacks executable code or commands. The 'Required Setting' JSON is questionable (the env var key looks like a comment, not a real setting). Commands like `/spawn-team` and `/initialize-project` are referenced but never shown with concrete syntax. The agent definition format is deferred to 'see agent files' without examples.	2 / 3
Workflow Clarity	The 10-step pipeline is extremely well-sequenced with explicit task dependencies, blocking rules, and verification checkpoints at each stage. The RED/GREEN verification gates, coverage thresholds (>=80%), and blocking on Critical/High issues are all explicit. Feedback loops are clearly defined (fix and re-request review/scan). The task dependency chain makes it structurally impossible to skip steps.	3 / 3
Progressive Disclosure	References to other skills (base.md, code-review.md, security.md, etc.) and agent definition files are mentioned but the integration table is surface-level. No bundle files are provided despite references to `.claude/agents/` definitions and multiple skill files. The content is monolithic — the massive pipeline diagram, agent roster, task chain, and parallel execution diagrams could all be in separate reference files, keeping SKILL.md as a concise overview.	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: 65efb33

Reviewed: 6 days 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.