team-coordinate
Universal team coordination skill with dynamic role generation. Uses team-worker agent architecture with role-spec files. Only coordinator is built-in -- all worker roles are generated at runtime as role-specs and spawned via team-worker agent. Beat/cadence model for orchestration. Triggers on "Team Coordinate ".
76
71%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/team-coordinate/SKILL.mdQuality
Discovery
57%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 communicates a distinctive architectural approach to team coordination with a specific trigger phrase, which helps with disambiguation. However, it leans heavily on internal implementation details (role-specs, beat/cadence model) rather than describing concrete user-facing capabilities, and it lacks a proper 'Use when...' clause with natural language trigger terms that users would actually say.
Suggestions
Add a 'Use when...' clause describing user scenarios, e.g., 'Use when the user needs to coordinate multiple agents, delegate tasks across roles, or orchestrate complex multi-step workflows.'
Include natural trigger terms users might say, such as 'delegate tasks', 'assign roles', 'multi-agent coordination', 'orchestrate work', 'team workflow'.
Replace implementation-focused language (beat/cadence model, role-spec files) with concrete action descriptions like 'Generates specialized worker roles on demand, delegates subtasks, and coordinates parallel workstreams.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (team coordination) and mentions some architectural details (team-worker agent architecture, role-spec files, beat/cadence model), but the actual concrete actions the skill performs are vague — 'coordination' and 'dynamic role generation' are abstract rather than specific user-facing capabilities. | 2 / 3 |
Completeness | The 'what' is partially addressed (team coordination with dynamic role generation and agent architecture), and there is a trigger statement ('Triggers on Team Coordinate'), but there is no explicit 'Use when...' clause describing the situations or user needs that should invoke this skill. The trigger phrase alone is narrow and doesn't constitute full 'when' guidance. | 2 / 3 |
Trigger Term Quality | It includes the explicit trigger phrase 'Team Coordinate' which is helpful, but this is a command-style trigger rather than natural language. It lacks common variations users might say like 'delegate tasks', 'assign roles', 'manage team', 'orchestrate work', or 'multi-agent'. | 2 / 3 |
Distinctiveness Conflict Risk | The description is quite distinctive — the combination of 'team-worker agent architecture', 'role-spec files', 'beat/cadence model', and the specific trigger phrase 'Team Coordinate' creates a clear niche that is unlikely to conflict with other skills. | 3 / 3 |
Total | 9 / 12 Passed |
Implementation
85%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured coordination skill with strong actionability and clear workflow sequencing. The spawn templates, user commands, error handling, and session management are all concrete and executable. The main weakness is moderate verbosity — the full session directory tree and JSON schema could potentially be moved to referenced spec files to reduce token cost, though their inclusion is defensible for quick reference.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly detailed and well-structured, but includes some content that could be tightened — the architecture ASCII diagram, the extensive session directory tree, and the full JSON schema are borderline verbose for a SKILL.md that references separate spec files. Some of this could live in the referenced specs rather than inline. | 2 / 3 |
Actionability | Provides concrete spawn templates with actual Agent() invocation syntax, specific CLI commands, exact file paths, JSON schemas, and precise user commands with their actions. The coordinator lifecycle, worker spawn template, and completion action with AskUserQuestion are all copy-paste ready. | 3 / 3 |
Workflow Clarity | The Phase 0-5 lifecycle is clearly sequenced with explicit steps. The session resume workflow includes reconciliation and state auditing. Error handling table covers failure scenarios with specific resolutions. The dependency graph model and inner loop determination logic provide clear decision criteria for orchestration. | 3 / 3 |
Progressive Disclosure | Excellent structure with a clear overview in SKILL.md and well-signaled one-level-deep references to specs (pipelines.md, role-spec-template.md, quality-gates.md, knowledge-transfer.md) and the coordinator role file. The inline content is appropriately scoped to what the coordinator needs immediately, with details delegated to referenced files. | 3 / 3 |
Total | 11 / 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 |
|---|---|---|
allowed_tools_field | 'allowed-tools' contains unusual tool name(s) | Warning |
Total | 10 / 11 Passed | |
- Repository
- catlog22/Claude-Code-Workflow
- Commit
0f8e801
- 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.