agent-teams
Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement
40
40%
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/agent-teams/SKILL.mdQuality
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 domain (team-based agent development with TDD) but lacks concrete action verbs, explicit trigger guidance, and natural user-facing keywords. It reads more like a label than a functional description, making it difficult for Claude to reliably select this skill from a large pool.
Suggestions
Add a 'Use when...' clause with explicit triggers, e.g., 'Use when the user asks to coordinate multiple agents, run a TDD workflow, or manage team-based development tasks.'
List specific concrete actions the skill performs, e.g., 'Orchestrates sub-agents for parallel development, enforces test-first coding, runs automated test pipelines, and coordinates code integration across team members.'
Include natural keyword variations users might say, such as 'test-driven development', 'multi-agent', 'parallel coding', 'sub-agents', 'automated testing workflow'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain ('team-based development') and mentions a specific methodology ('strict TDD pipeline enforcement'), but does not list concrete actions like 'write tests first', 'run test suites', 'assign tasks to agents', etc. | 2 / 3 |
Completeness | It partially addresses 'what' (team-based development with TDD pipeline) but provides no 'when' clause or explicit trigger guidance. The rubric caps completeness at 2 for missing 'Use when...' and this description is also weak on the 'what', so it scores 1. | 1 / 3 |
Trigger Term Quality | Contains some relevant keywords like 'TDD', 'team-based development', and 'pipeline', but misses common user-facing terms like 'test-driven development', 'multi-agent', 'parallel tasks', 'sub-agents', or 'workflow'. Users may not naturally say 'pipeline enforcement'. | 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. The word 'default' further reduces distinctiveness. | 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 rigorous validation checkpoints and dependency enforcement, but suffers significantly from verbosity — the same 10-step pipeline is rendered in at least 3 different formats (ASCII diagram, numbered steps, task chain model). The content is more of a comprehensive reference document than a lean skill file, with substantial redundancy that wastes token budget. Actionability is moderate: the conceptual framework is solid but lacks executable orchestration code.
Suggestions
Reduce redundancy by describing the 10-step pipeline once (pick either the ASCII diagram OR the numbered steps, not both plus the task chain model) — this alone could cut 30-40% of content.
Remove explanatory content Claude already knows (e.g., what agents are, how task dependencies enforce ordering, what TDD means) and focus only on project-specific conventions and configurations.
Extract the detailed task dependency chain model, inter-agent communication patterns, and Polyphony container details into separate reference files, keeping SKILL.md as a concise overview with links.
Add executable code or concrete command examples for key operations like spawning agents, creating task chains, and running verification steps instead of describing them procedurally.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~350+ lines with extensive ASCII art diagrams, redundant information (the pipeline is described 3+ times in different formats), and explanations of concepts Claude already understands (what agents do, how task dependencies work). The parallel execution diagram, inter-agent communication examples, and multiple renderings of the same 10-step pipeline are highly redundant. | 1 / 3 |
Actionability | Provides a clear conceptual framework with specific task naming conventions, agent roles, and git commands, but lacks executable code for the core orchestration. References like `/spawn-team`, `/ralph-loop`, and `/code-review` are mentioned without concrete implementation. The branch/PR strategy section has actionable git commands, but most guidance is procedural description rather than executable instructions. | 2 / 3 |
Workflow Clarity | The workflow is exceptionally clear with explicit sequencing, task dependency chains, validation checkpoints at every stage (RED verify, GREEN verify, code review gates, security gates), and explicit blocking rules. Feedback loops are well-defined — if tests don't fail/pass or reviews find issues, the agent must fix and re-request verification. | 3 / 3 |
Progressive Disclosure | References other skills (base.md, code-review.md, security.md) and agent definition files in `.claude/agents/`, but the SKILL.md itself is monolithic with all content inline. The integration table is a good navigation aid, but the massive pipeline diagrams, agent roster, and detailed workflows could be split into separate reference files. No bundle files are provided to support progressive disclosure. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%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
7e5f7a2
- 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.