vertical-slice

Pre-Production validation — build a production-quality end-to-end build to confirm the full game loop is achievable before committing to Production. Run after GDDs, architecture, and UX specs are complete. Produces a PROCEED/PIVOT/KILL verdict that gates the Pre-Production → Production transition.

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/vertical-slice/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.

The body is a highly actionable, well-sequenced multi-phase workflow with strong validation checkpoints, but it carries some verbosity (repeated general playtesting techniques and restated constraints) and does not use progressive disclosure to offload detail into bundle files.

Suggestions

Move the four playtesting methodology variants and the report template/fallback structure into a `references/` file, keeping SKILL.md as an overview with a one-level-deep pointer.

Trim the closing "Important Constraints" section to only constraints not already stated inline, or remove the restated day-3/scope/effort rules.

Cut or compress the general explanations of think-aloud and Wizard of Oz techniques to the specific guidance unique to vertical-slice testing.

Dimension	Reasoning	Score
Conciseness	Mostly efficient process prose, but the four playtesting variants (think-aloud, Wizard of Oz, async remote, silent walkthrough) explain general UX techniques Claude already knows, and the closing "Important Constraints" repeats earlier day-3/scope/effort rules; could be tightened without losing the score-3 lean benchmark.	2 / 3
Actionability	Copy-paste-ready throughout: exact quoted prompts to say, concrete file paths (e.g. `prototypes/[concept-name]-vertical-slice/REPORT.md`), a required file header block, and explicit checklists — fully executable guidance.	3 / 3
Workflow Clarity	Eight numbered phases are clearly sequenced with explicit validation checkpoints (day-3 sunk-cost checkpoint, pre-build scope confirmation, KILL soundness checklist) and feedback loops for error recovery, matching the top anchor.	3 / 3
Progressive Disclosure	The file is a ~360-line monolith with well-organized phase sections but no skill-bundled reference files (references/scripts/assets are absent); content that could be split (playtesting techniques, report template, KILL/PIVOT procedures) is inline rather than one level deep.	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.

The description is specific and distinct, clearly conveying what the skill does and its project-stage niche, but it lacks natural user-facing trigger terms (notably "vertical slice") and an explicit "Use when..." clause, which cap completeness and trigger quality at the middle level.

Suggestions

Add an explicit trigger clause, e.g. "Use when validating a vertical slice before entering Production, or when the user mentions vertical slices / pre-production validation."

Include the natural term "vertical slice" in the description so it matches what a user would actually say.

Keep the concrete actions but tighten "build a production-quality end-to-end build" to avoid the repeated "build...build" phrasing.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "build a production-quality end-to-end build to confirm the full game loop is achievable" and "Produces a PROCEED/PIVOT/KILL verdict that gates the... transition" — matching the top anchor for specific concrete actions.	3 / 3
Completeness	The "what" is clearly stated, and a timing condition ("Run after GDDs, architecture, and UX specs are complete") is present, but there is no "Use when..." user-trigger clause; per the judging guidelines a missing explicit trigger caps completeness at 2.	2 / 3
Trigger Term Quality	Relevant domain keywords appear ("Pre-Production", "game loop", "PROCEED/PIVOT/KILL") but the natural term a user would say ("vertical slice") is absent from the description and common phrasings are not covered, landing at the middle anchor.	2 / 3
Distinctiveness Conflict Risk	The pre-production gating niche ("gates the Pre-Production → Production transition") and verdict vocabulary give it a clear, distinct trigger set unlikely to fire for unrelated skills.	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/vertical-slice/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.