vertical-slice

Pre-production validation — end-to-end build to confirm the full loop is achievable before committing to Production. After GDDs, architecture, UX specs.

Quality

76%

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

81%Weight 40%Scale 1-5

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-engineered process skill: every phase gives concrete commands, verbatim prompts, exact paths, and templates, with validation checkpoints and feedback loops throughout. Its only real weakness is repetition (velocity-log and scope-discipline points made multiple times) and some optional playtesting guidance that inflates the body and would sit better in a reference file.

Dimension	Reasoning	Score
Conciseness	The body is dense with actionable, non-obvious guidance and never explains concepts Claude already knows, but there is noticeable repetition that could be tightened: the velocity-log importance is stated three times (Phases 3, 6 twice), and the cut-scope-not-quality rule is repeated across Phases 2, 3, and the Constraints section. Fits the anchor for mostly efficient with some tightening possible; not 4 because the repetition is more than minor.	3 / 5
Actionability	Guidance is fully executable: an exact shell command to run, verbatim user-facing prompts for every question, exact file paths (session checkpoint, REPORT.md, PIVOT-NOTE.md, GRAVEYARD.md), a per-language comment-syntax table for file headers, a fallback report structure, and a copy-paste graveyard entry template. Matches the anchor for copy-paste-ready guidance covering the common cases.	5 / 5
Workflow Clarity	Eight clearly sequenced phases with explicit validation checkpoints: user confirmation before every write, a day-3 sunk-cost stop-and-reassess rule, a multi-turn build/fix feedback loop, a KILL soundness checklist, and complete verdict logic including the NOT ASSESSED edge case with resume instructions. Matches the anchor for clear sequencing with explicit validation, feedback loops, and checklists.	5 / 5
Progressive Disclosure	Detail is appropriately deferred to clearly signaled, one-level-deep project docs (director gate files, automation modes, the report template with an inline fallback structure, config resolution). Good structure with minor gaps: the ~415-line body carries several long optional playtesting-technique passages (think-aloud, async recording, Wizard of Oz) that could be split into a reference file. Not 5 for that remaining inline bulk; not 3 because references are well signaled and content is mostly appropriately placed.	4 / 5
	Total	17 / 20 Passed

Description

62%Weight 40%Scale 1-5

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 what the skill does and when in the project lifecycle it applies, using appropriately concrete game-dev terminology. Its main weaknesses are the absence of the skill's own natural name ("vertical slice") as a trigger term and the lack of an explicit "Use when..." invocation clause, which together leave trigger quality and completeness short of the top anchors.

Suggestions

Include "vertical slice" in the description — it is the industry-standard term a user would naturally say when they need this skill, and it is currently only present in the skill name.

Add an explicit trigger clause, e.g. "Use when validating the full game loop before committing to Production, or after GDDs, architecture, and UX specs are complete."

List one or two more concrete actions (e.g. builds a playable [start → challenge → resolution] loop and generates a verdict report with velocity data) to raise specificity.

Dimension	Reasoning	Score
Specificity	"end-to-end build to confirm the full loop is achievable" names the domain (pre-production validation) plus one concrete action, matching the anchor for 1-2 concrete actions without comprehensive coverage. It is not 4 because no list of several specific actions is given, and not 2 because the action stated is concrete rather than generic.	3 / 5
Completeness	The "what" is clear (end-to-end build confirming the full loop is achievable) and the "when" is explicitly stated as lifecycle timing ("After GDDs, architecture, UX specs" ... "before committing to Production"). Not 5 because it lacks a "Use when..." trigger clause naming what the user would say; not 3 because the when is explicitly written, not merely implied.	4 / 5
Trigger Term Quality	Keywords like "Pre-production", "GDDs", "full loop", and "Production" are relevant, but the most natural term a user would actually say for this skill — "vertical slice" — is absent from the description. Fits the anchor for some relevant keywords while missing common variations or synonyms.	3 / 5
Distinctiveness Conflict Risk	The vocabulary (GDDs, UX specs, Production gate, full game loop) anchors it firmly in game-development pre-production, making it mostly distinct with only minor overlap risk against a closely related concept-prototype/prototype skill. Not 5 because "pre-production validation" is still a broadly phrased activity that a sibling skill could share.	4 / 5
	Total	14 / 20 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: b21fa0f

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.