agent-teams

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

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/agent-teams/SKILL.md

Quality

Content

70%Weight 40%Scale 1-5

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

The content delivers a clear, well-validated multi-agent TDD workflow with concrete commands and strong feedback loops, but it is verbose due to triple-rendering the same pipeline and lacks progressive disclosure into reference files. Consolidating the pipeline into one canonical definition and splitting agent templates into reference files would improve both dimensions.

Suggestions

Render the 10-step pipeline once and reference it from the Feature Agent Workflow and Task Dependency Chain sections instead of repeating it three times.

Move the detailed agent roster and per-agent frontmatter templates into reference files under references/ (e.g. references/agent-roster.md) and link from the body, enabling progressive disclosure.

Move the ASCII diagrams or lengthy task-chain examples into a reference file, keeping SKILL.md as a concise overview that points to details.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but the 10-step pipeline is rendered three times (Core Principle diagram, Feature Agent Workflow steps, and Task Dependency Chain diagram), which is noticeable redundancy that could be tightened.	3 / 5
Actionability	It provides concrete, executable guidance such as 'git checkout -b feature/{feature-name}', 'gh pr create', 'polyphony spawn "$FEATURE" --type feature', exact file paths, and a concrete >= 80% coverage gate, with only minor gaps in some agent prompts.	4 / 5
Workflow Clarity	The multi-step pipeline is explicitly sequenced with validation checkpoints (RED verify, GREEN verify, validate, code review, security scan) enforced by task dependencies, plus feedback loops ('If tests fail or coverage insufficient -> fix and re-request') and a checklist for PR creation.	5 / 5
Progressive Disclosure	No bundle files exist under references/, scripts/, or assets/, and the ~440-line body is monolithic with distinct components (agent roster templates, pipeline spec) that could live in separate reference files; section headers provide structure but content that should be split is inline.	3 / 5
	Total	15 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 clearly names a distinctive niche and its core mechanism, but is missing an explicit 'when to use' trigger clause and lists few concrete actions. Adding a 'Use when...' phrase and enumerating key actions would raise completeness and specificity.

Suggestions

Add an explicit trigger clause to the description, e.g. 'Use when spawning agent teams for parallel feature development with TDD pipeline enforcement'.

List concrete actions (spawns per-feature agents, enforces RED/GREEN verification, runs code review and security scans, creates feature branches and PRs) to improve specificity.

Include natural synonyms a user might say ('multi-agent development', 'parallel feature work') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain ('team-based development') and one concrete mechanism ('strict TDD pipeline enforcement'), but does not enumerate the specific actions the skill performs (spawning agents, creating PRs, running reviews).	3 / 5
Completeness	It gives a clear 'what' (default team-based development with TDD enforcement) but the description field lacks any 'Use when...' trigger clause; per the guideline a missing explicit trigger caps completeness at 3.	3 / 5
Trigger Term Quality	It includes relevant terms like 'agent teams', 'team-based development', and 'TDD pipeline', but leans technical and omits natural synonyms a user might say; the complementary when-to-use field adds 'parallel feature development' but is not part of the description itself.	3 / 5
Distinctiveness Conflict Risk	'Agent Teams' with strict TDD pipeline enforcement is a clear niche with minimal conflict risk, though it overlaps slightly with related team-coordination skills (which the body notes are superseded).	4 / 5
	Total	13 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: alinaqi/claude-bootstrap
Path: skills/agent-teams/SKILL.md
Commit: abc600e

Reviewed: 3 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.