team-polish

Orchestrate the polish team: coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden a feature or area for release quality.

Quality

72%

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-polish/SKILL.md

Quality

Content

77%

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

A well-sequenced, actionable orchestration pipeline with strong workflow clarity and error recovery, slightly weakened by redundant team-roster text and a monolithic structure with no progressive disclosure.

Suggestions

Merge 'Team Composition' and 'How to Delegate' into a single section to remove the duplicated role descriptions and recover tokens.

Extract detailed per-agent task lists into a bundled reference file (e.g. references/agents.md) with one-level-deep links to improve progressive disclosure.

Verify that referenced command skills (/perf-profile, /release-checklist, /gate-check, /architecture-decision, /create-stories, /sprint-plan) exist, since actionability depends on them.

Dimension	Reasoning	Score
Conciseness	The body is mostly directive and assumes Claude's competence (no explanations of profiling or QA concepts), but the team roster is described twice — once in 'Team Composition' and again with near-identical text in 'How to Delegate' — which could be tightened; not a 3 due to that redundancy, not a 1 because it avoids concept padding.	2 / 3
Actionability	Gives concrete, executable guidance per phase: exact subagent_types to spawn, specific per-agent task lists and outputs, and named command skills to invoke; as an instruction-only orchestrator, the absence of code is not penalized and the guidance is copy-paste ready in its domain.	3 / 3
Workflow Clarity	A clearly sequenced Phase 0–6 pipeline with explicit checkpoints (AskUserQuestion approval at each transition), a sign-off gate, and a dedicated Error Recovery Protocol with feedback loops (surface, assess, offer options, always produce a partial report); matches the 'clear sequence with explicit validation steps and feedback loops' anchor.	3 / 3
Progressive Disclosure	The skill is a single monolithic file with no bundle references and well-organized sections, but per-agent detail and the team roster are inline rather than split into one-level-deep reference files; not a 3 because content that could be separate is inline, not a 1 because sections are clearly headed and navigable.	2 / 3
	Total	10 / 12 Passed

Description

67%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, role-grounded description with a clear niche, but it lacks an explicit 'Use when' trigger clause, which caps completeness and weakens trigger-term coverage.

Suggestions

Append an explicit trigger clause, e.g. 'Use when polishing, optimizing, or hardening a feature or area for release quality.'

Add natural user phrasings to the trigger (e.g. 'polish for release', 'release readiness', 'optimize the game') to improve trigger-term coverage.

Consider trimming internal role jargon ('polish team') in favor of user-facing language to reduce conflict risk with general optimization skills.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ("coordinates performance-analyst, technical-artist, sound-designer, and qa-tester to optimize, polish, and harden") tied to specific roles, matching the 'lists multiple specific concrete actions' anchor; not a 2 because it is comprehensive rather than naming only some actions.	3 / 3
Completeness	Clearly answers 'what' (orchestrate the team to optimize/polish/harden for release) but provides no explicit 'Use when...' or equivalent trigger guidance, so per the judging guidelines completeness is capped at 2; not a 3 because 'when' is only implied, not a 1 because the 'what' is strong.	2 / 3
Trigger Term Quality	Terms like 'polish', 'optimize', 'harden', and 'release quality' are reasonably natural, but it leans on internal role jargon ('polish team') and omits common variations and an explicit trigger clause; not a 3 because coverage of natural user phrasings is incomplete, not a 1 because several relevant keywords are present.	2 / 3
Distinctiveness Conflict Risk	The named team composition and 'release quality hardening' niche give it a clear, distinctive scope unlikely to trigger for unrelated skills; not a 2 because the role names and purpose make it more specific than a generic overlap case.	3 / 3
	Total	10 / 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-polish/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.