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 ".

Quality

53%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/team-coordinate/SKILL.md

Quality

Content

50%

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

This is a structurally ambitious coordination skill that establishes a clear architecture and provides some concrete patterns (spawn template, completion action), but suffers from being simultaneously too verbose in some areas (inline schemas, directory trees) and too vague in others (actual phase execution logic deferred to missing referenced files). The workflow lacks explicit validation checkpoints between phases, and the absence of bundle files makes it impossible to verify that the referenced specs and role definitions actually exist and contain the needed detail.

Suggestions

Add explicit validation checkpoints between phases (e.g., 'Verify task-analysis.json has ≥1 task before proceeding to Phase 2', 'Validate generated role-specs against template before spawning workers') to improve workflow clarity.

Move the session directory tree and team-session.json schema into a referenced spec file (e.g., specs/session-schema.md) to reduce inline verbosity while keeping the SKILL.md focused on orchestration logic.

Include the actual bundle files (especially roles/coordinator/role.md and specs/role-spec-template.md) or inline the critical phase execution logic so the skill is actionable without external dependencies.

Consolidate the CLI tool references — they appear in both the architecture diagram and a separate table — into a single location to improve conciseness.

Dimension	Reasoning	Score
Conciseness	The skill is moderately efficient but includes verbose sections like the full session directory tree, JSON schema, and architecture diagram that could be in referenced spec files. Some tables repeat information (e.g., CLI tools listed twice). However, it avoids explaining basic concepts Claude already knows.	2 / 3
Actionability	The spawn template and completion action provide concrete, copy-paste-ready patterns, but many sections are descriptive rather than executable. The lifecycle is described as a flow diagram rather than precise step-by-step instructions. Phase 1-5 details are deferred to referenced files (roles/coordinator/role.md, specs/) without inline fallback, making the skill incomplete on its own.	2 / 3
Workflow Clarity	The lifecycle flow and phase sequence are outlined, and session resume has clear steps. However, validation checkpoints are largely absent — there's no explicit 'validate before proceeding' step in the main pipeline. Error handling is listed as a table but lacks feedback loops (e.g., what happens after a blocker is reported, how coordinator verifies worker output quality before advancing).	2 / 3
Progressive Disclosure	References to specs/ and roles/ files are well-signaled with a clear table, and the architecture separates coordinator from workers. However, no bundle files were provided, so all referenced files (specs/pipelines.md, specs/role-spec-template.md, roles/coordinator/role.md, etc.) are unverifiable. The SKILL.md itself is quite long with inline content (session schema, directory tree) that would be better placed in referenced files.	2 / 3
	Total	8 / 12 Passed

Description

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 establishes a distinctive architectural identity and provides an explicit 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 the trigger mechanism is a synthetic command rather than natural language terms users would actually use.

Suggestions

Add natural trigger terms users would actually say, such as 'delegate tasks', 'coordinate team members', 'assign roles', 'multi-agent workflow', or 'parallel task execution'.

Expand the 'when' clause beyond just the command trigger — describe scenarios like 'Use when the user needs to break a complex task into subtasks handled by specialized roles' or 'when multiple distinct expertise areas are needed simultaneously'.

Replace abstract architectural language ('beat/cadence model', 'role-spec files') with concrete action descriptions like 'spawns specialized worker agents, distributes subtasks, and aggregates results'.

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 clause ('Triggers on "Team Coordinate"'), but the 'when' guidance is minimal — it only specifies a command prefix rather than describing scenarios or user intents that should activate this skill.	2 / 3
Trigger Term Quality	It includes the explicit trigger phrase 'Team Coordinate' but this is a synthetic command rather than a natural keyword a user would say. It lacks natural language variations like 'delegate tasks', 'assign roles', 'manage team', 'orchestrate workflow', etc.	2 / 3
Distinctiveness Conflict Risk	The description carves out a clear niche with its specific architecture (team-worker agent, role-spec files, beat/cadence model) and explicit trigger phrase 'Team Coordinate', making it unlikely to conflict with other skills.	3 / 3
	Total	9 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	10 / 11 Passed

Repository: catlog22/Claude-Code-Workflow
Commit: 07491b0

Reviewed: 20 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.