gate-check

Validate readiness to advance between development phases. Produces a PASS/CONCERNS/FAIL verdict with specific blockers and required artifacts. Use when user says 'are we ready to move to X', 'can we advance to production', 'check if we can start the next phase', 'pass the gate'.

Quality

88%

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

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 content is highly actionable with strong workflow sequencing and an explicit verification step, but it is long and somewhat redundant and keeps the entire gate-definition catalog inline rather than splitting it into bundle reference files.

Suggestions

Collapse the repeated 'recommended, not blocking' caveats into a single shared note and consolidate the long Follow-Up Actions list into a separate reference file to reduce token cost.

Split the seven per-gate definitions (Section 2) into individual reference files under references/ and keep SKILL.md as an overview pointing to them, improving progressive disclosure.

Trim asides that re-teach known context (e.g., the 'Why prototype before epics?' GDC rationale) to essentials, trusting Claude's competence.

Dimension	Reasoning	Score
Conciseness	Individual sections are efficient, but the body is ~540 lines with notable redundancy — 'recommended, not blocking' is repeated per-item across multiple gates, the follow-up action catalog and closing widgets pad heavily, and rationales like the GDC postmortem aside add context Claude largely already knows. It is mostly efficient but could be tightened, matching the 'some unnecessary explanation or could be tightened' anchor rather than the lean top level.	2 / 3
Actionability	Provides exact artifact paths, concrete globs (Glob('design/gdd/gdd-cross-review-*.md')), copy-paste commands (echo -n "Production" > production/stage.txt), and precise verdict rules — fully executable, specific, and copy-paste ready rather than pseudocode or vague direction.	3 / 3
Workflow Clarity	Clear 8-phase sequence with explicit validation checkpoints, a dedicated Chain-of-Verification step mandating tool actions, and verdict upgrade/downgrade feedback loops (re-validate, upgrade PASS->CONCERNS on missed blocker) — matching the 'clear sequence with explicit validation steps and feedback loops' anchor.	3 / 3
Progressive Disclosure	No bundle files exist (references/scripts/assets absent), so the seven full gate definitions are all inline as one large block; content that could be split into per-gate reference files is monolithic. External doc references (director-gates.md, templates) are one-level deep and signaled, but the inline gate catalog keeps this at 'some structure but content that should be separate is inline' rather than the well-split top level.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 excellent: third-person voice, concrete actions, an explicit 'Use when' clause with natural trigger phrases, and a clearly delineated niche. It hits every dimension at the top anchor.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Validate readiness to advance between development phases', 'Produces a PASS/CONCERNS/FAIL verdict with specific blockers and required artifacts' — matching the 'lists multiple specific concrete actions' anchor rather than the single-action level below.	3 / 3
Completeness	Explicitly answers both what (validate readiness, produce a PASS/CONCERNS/FAIL verdict) and when via a 'Use when...' clause with concrete triggers, matching the 'clearly answers both what AND when' anchor and exceeding the 'when implied' level below.	3 / 3
Trigger Term Quality	Quotes natural user phrasings verbatim ('are we ready to move to X', 'can we advance to production', 'check if we can start the next phase', 'pass the gate'), giving strong coverage of terms users would actually say rather than only some relevant keywords.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (formal phase-gate verdicts) with distinct trigger phrasing unlikely to fire for unrelated skills; the body even draws an explicit distinction from /project-stage-detect.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (543 lines); consider splitting into references/ and linking	Warning
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	13 / 16 Passed

Repository: Donchitos/Claude-Code-Game-Studios
Path: .claude/skills/gate-check/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.