release-checklist

Pre-release checklist — build verification, certification requirements, store metadata, launch readiness.

Quality

74%

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/release-checklist/SKILL.md

Quality

Content

73%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.

The body is exceptionally actionable and well-sequenced — copy-paste templates for every config branch, explicit NOT ASSESSED semantics, and a deterministic Go/No-Go rule — but it pays for this with noticeable redundancy: the same cert_tier-vs-argument rule is argued in four places. Consolidating the defensive meta-commentary would raise conciseness without losing any operational content.

Suggestions

Consolidate the four restatements of the device-argument vs platform.cert_tier rule into one authoritative section (e.g. keep the Phase 1 explanation and the 'console collision' caveat, drop the mobile and certification-preamble repetitions).

Move the defensive blockquotes (lines 45-49, 199-203, 252-262) into a single 'Common misreadings' reference or trim them to one-line pointers, keeping the operational rule inline once.

State 'Unset is not none' once (in the cert_tier rule block) and reference it from the certification section rather than re-deriving it in both places.

Dimension	Reasoning	Score
Conciseness	The device-argument vs platform.cert_tier distinction is restated four times (Phase 1, the mobile blockquote, the certification preamble, and the closing 'console means two things' blockquote), 'Unset is not none' appears twice, and blockquotes re-argue against misreadings rather than instruct. This is 'noticeably verbose; several unnecessary explanations or padded sections' — more than the 'some unnecessary explanation' of anchor 3, though not the concept-explaining padding of anchor 1.	2 / 5
Actionability	Fully executable throughout: copy-paste-ready markdown templates for every cert tier and device block, exact emitted lines ('Certification: omitted — cert_tier is none (internal build, alpha or jam release).'), concrete Grep/Read patterns for bug files, and explicit per-workflow bug thresholds. Specific examples cover the common cases, matching the top anchor.	5 / 5
Workflow Clarity	Phases 1-6 are clearly sequenced with explicit validation checkpoints: denominator reporting for every count, NOT ASSESSED markers distinguishing absent from clean evidence, a first-match-wins Go/No-Go ordering rule (NOT READY > NOT ASSESSED > READY), and an ask-before-write gate in Phase 5. This matches the anchor for clear sequence with explicit validation and feedback handling.	5 / 5
Progressive Disclosure	No bundle files exist, and the external doc references (.claude/docs/effects-map.md, automation-modes.md, config-resolution.md, code-root-resolution.md) are one level deep, clearly signaled, and bounded ('Grep its heading, then a bounded Read'). Structure is good with phase headers, but the ~330-line body inlines lengthy defensive rule commentary that could live in a reference file — minor organization gaps, so anchor 4 rather than the clean-split anchor 5.	4 / 5
	Total	16 / 20 Passed

Description

66%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 is specific and distinct, cleanly listing four concrete coverage areas in third person, but it omits any explicit 'when to use it' trigger guidance, which caps its completeness. Adding a Use-when clause with a few natural synonyms would lift two dimensions at once.

Suggestions

Append an explicit trigger clause, e.g. 'Use when preparing to ship a build, running a go/no-go review, or when the user mentions release readiness, store submission, or certification.'

State the action explicitly (e.g. 'Generates a pre-release checklist covering...') so the 'what' reads as a capability rather than a bare topic list.

Add one or two natural trigger synonyms users would actually say — 'ship readiness', 'go/no-go', 'release gate' — to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('Pre-release checklist') and lists four concrete coverage areas ('build verification, certification requirements, store metadata, launch readiness'), matching the 'several specific actions; minor gaps in coverage' anchor. Not 5 because the areas are topical nouns rather than explicit actions and coverage gaps exist (no QA/bug-scan or codebase-health terms); not 3 because four specific areas exceed the 1-2 the lower anchor allows.	4 / 5
Completeness	The 'what' is clear (a pre-release checklist spanning four named areas) but there is no 'Use when...' clause or equivalent explicit trigger guidance, and 'when' is only weakly implied by 'Pre-release'. Per the judging guideline, a missing 'Use when' clause caps completeness at 3 — it cannot score 4, and it does not fall to 2 since the 'what' is concrete.	3 / 5
Trigger Term Quality	'Pre-release checklist', 'launch readiness', and 'certification requirements' are natural phrases a user would say when needing this skill, but common synonyms like 'ship', 'go/no-go', 'release readiness', or 'store submission' are missing. This fits the 'good keyword coverage; a few natural terms missing' anchor rather than the comprehensive-synonym anchor at 5.	4 / 5
Distinctiveness Conflict Risk	The game-release/certification niche is mostly distinct, but 'launch readiness' creates minor overlap risk with a sibling launch-checklist skill (the body itself references /launch-checklist). This matches 'mostly distinct; minor overlap risk with closely related skills' rather than the clear-niche anchor at 5.	4 / 5
	Total	15 / 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/release-checklist/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.