CtrlK
BlogDocsLog inGet started
Tessl Logo

day-one-patch

Day-one launch patch — focused fix for known issues found after gold master. Mini-sprint with QA gate and rollback.

63

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/day-one-patch/SKILL.md
SKILL.md
Quality
Evals
Security

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.

The content is an exemplary operational workflow: concrete, well-sequenced, and rich with validation checkpoints and failure-path handling. Its two weaknesses are rhetorical padding in a few prose passages and the inlined patch-record template, which could live in a reference file.

Suggestions

Tighten the philosophical passages in Phase 1 and Phase 5 (e.g. 'the stage is a claim... the gate record is the evidence') into single-line directives such as 'Stage value does not establish gate passage — require a gate-check record'.

Move the Phase 6 patch-record template to a bundle file (e.g. references/patch-record-template.md) and reference it one level deep, keeping SKILL.md at overview scope.

The duplicated test-runner guidance (Phase 4 step 3 and Phase 5 broader regression) could be consolidated into one stated rule.

DimensionReasoningScore

Conciseness

The body is mostly efficient directives (scope rules table, exact prompts, file paths), but several rhetorical passages add tokens without adding instruction — e.g. 'the stage is a claim about where the project is; the gate record is the evidence that it earned the position', 'it is the release gate, arriving late and scoped to the wrong changes', and 'the worst possible audience for an unverified change'. These could be tightened to plain directives; not a 2 because the padding is limited to a few passages within otherwise lean procedural text.

3 / 5

Actionability

Fully actionable instruction-only guidance: exact file paths to read ('production/gate-checks/', 'production/qa/bugs/*.md'), a concrete classification table, exact AskUserQuestion prompts with option lists, a defined output path ('production/releases/day-one-patch-[version].md'), engine-specific test roots, and an explicit fallback when 'commands.test' is unset ('record Tests: NOT RUN').

5 / 5

Workflow Clarity

A clear 7-phase sequence with explicit validation checkpoints throughout: premise verification of the release gate (including FAIL/CONCERNS/missing-record handling), rollback plan required before any code is written, a QA verdict gate where FAIL scopes the fix out and 'NOT ASSESSED... is not a pass' with named recovery paths, and a four-role approval checklist before deploy.

5 / 5

Progressive Disclosure

Well-organized phased sections with a clearly signaled one-level reference to '.claude/docs/directory-structure.md' for engine test roots, and no bundle files exist to over-structure. A 4 rather than 5 because the ~60-line patch-record template is inlined in Phase 6 where a separate template file would keep SKILL.md closer to overview scope.

4 / 5

Total

17

/

20

Passed

Description

70%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, uses natural domain terminology, and carves out a distinct niche in the game release workflow. Its main weakness is the missing explicit 'Use when...' trigger guidance, which caps completeness and leaves 'when to use it' only implied.

Suggestions

Add an explicit trigger clause such as 'Use when a gold master build is locked and known bugs or cert feedback need fixing before launch day'.

Mention the key trigger scenarios users would name — cert feedback and pre-launch playtest findings — to round out keyword coverage.

Name the primary output (a day-one patch record with QA sign-off and rollback plan) so the 'what' fully covers the skill's deliverables.

DimensionReasoningScore

Specificity

Names the domain ('Day-one launch patch', 'known issues found after gold master') and several concrete actions — focused fix, QA gate, and rollback. Falls short of anchor 5 because coverage is not comprehensive (no mention of bug scoping/classification, patch-record generation, or cert feedback handling).

4 / 5

Completeness

The 'what' is clear (focused fix for known issues, mini-sprint with QA gate and rollback), but there is no explicit 'Use when...' clause — the 'when' is only weakly implied by 'found after gold master'. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.

3 / 5

Trigger Term Quality

Natural game-dev trigger phrases like 'day-one launch patch', 'gold master', 'known issues', 'QA gate', and 'rollback' are present. Not a 5 because common variations users might say ('cert feedback', 'post-launch fixes', 'pre-launch bugs') are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (post-gold-master day-one patching in a game release pipeline) with distinct triggers like 'gold master' and 'day-one'. Minimal overlap risk with generic bug-fixing or hotfix skills; the narrow launch context distinguishes it.

5 / 5

Total

16

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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
Reviewed

Table of Contents

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.