team-combat

Orchestrate the combat team: coordinates game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, and qa-tester to design, implement, and validate a combat feature end-to-end.

Quality

63%

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 ./.claude/skills/team-combat/SKILL.md

Quality

Content

62%

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

The content shines on workflow clarity — a well-sequenced multi-phase pipeline with explicit decision gates and a thorough error-recovery protocol. Conciseness and actionability are good but held back by duplicated role descriptions and descriptive rather than executable per-phase prompts, and progressive disclosure is middling because there are no bundle files and inline external-path references.

Suggestions

De-duplicate the 'Team Composition' and 'How to Delegate' sections into a single table mapping role → subagent_type → responsibility, removing the repeated descriptions.

Add a concrete Task-tool prompt template or example invocation for at least one phase so the delegation guidance is copy-paste ready rather than descriptive.

Move detailed per-phase role responsibilities into a referenced file (e.g. references/team-roles.md) so the SKILL.md body stays a lean overview with well-signaled one-level-deep references.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and task-focused, but the repeated 'Team Composition' and 'How to Delegate' sections re-state the same role descriptions twice, and some commentary restates concepts Claude already knows, so it could be tightened.	2 / 3
Actionability	It gives concrete delegation guidance (specific subagent_type values, file paths, AskUserQuestion option labels), but much of the per-phase instruction is descriptive rather than executable — there is no concrete prompt template or code to spawn agents, and several outputs are abstract ('architecture sketch', 'audio event list').	2 / 3
Workflow Clarity	The pipeline is a clearly sequenced Phase 0–6 with explicit approval gates via AskUserQuestion, an Error Recovery Protocol with feedback loops (surface, assess dependencies, offer options, partial report), and validation in Phase 5 — matching the rubric's anchor for clear sequence with explicit checkpoints and error-recovery loops.	3 / 3
Progressive Disclosure	There are no bundle files (references/, scripts/, assets/ are absent) and the body references external docs inline (e.g. '.claude/docs/technical-preferences.md', 'design/gdd/', 'production/review-mode.txt') without a one-level-deep reference structure, so content that could be split out is inline; as a no-bundle skill it is reasonably organized but not exemplary of progressive disclosure.	2 / 3
	Total	9 / 12 Passed

Description

65%

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 is strong on specificity — clearly naming the coordinated roles and end-to-end pipeline phases — but is missing an explicit 'Use when...' trigger clause, which the rubric caps at completeness 2. Trigger-term quality is moderate because the keywords are internal role names rather than the natural language a user would say.

Suggestions

Add an explicit 'Use when ...' clause stating when to invoke this skill (e.g. 'Use when designing, implementing, and validating a combat feature such as a melee parry, ranged weapon spread, or enemy AI behavior').

Broaden trigger terms to natural user-facing phrases like 'combat system', 'weapon mechanics', 'enemy AI', 'melee', 'ranged', and 'boss fights' rather than internal role names.

Clarify distinctiveness by contrasting with sibling team skills (e.g. '/team-polish', '/balance-check') so it is clear when to use this versus another orchestration skill.

Dimension	Reasoning	Score
Specificity	It lists multiple concrete actions — 'coordinates game-designer, gameplay-programmer, ai-programmer, technical-artist, sound-designer, and qa-tester to design, implement, and validate a combat feature end-to-end' — naming both the actors and the specific phases of work.	3 / 3
Completeness	It clearly answers 'what does this do' but has no explicit 'Use when...' clause or equivalent trigger guidance, which the rubric states should cap completeness at 2.	2 / 3
Trigger Term Quality	It uses domain terms like 'combat feature', 'game-designer', 'qa-tester', but lacks the natural phrases a user would actually say when they need it (e.g. 'combat system', 'weapon', 'enemy AI', 'melee', 'ranged') and the trigger vocabulary is mostly internal role names rather than user-facing language.	2 / 3
Distinctiveness Conflict Risk	The combat-team orchestration niche is reasonably specific and unlikely to conflict broadly, but the lack of explicit 'use when' triggers and reliance on generic role names leaves some overlap with sibling team-orchestration skills.	2 / 3
	Total	9 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/team-combat/SKILL.md
Commit: 984023d

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.