CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

day-one-patch

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

Quality

78%

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

88%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.

An unusually actionable, well-gated workflow: every phase has concrete inputs, explicit approval prompts, and defined failure paths. The only real weaknesses are a handful of rhetorical passages and a large inline output template that could live in a bundled reference file.

Suggestions

Move the Phase 6 patch-record template into a bundled reference (e.g. references/patch-record-template.md) and keep a short field summary in the body.

Trim the editorial justifications in Phase 1 and Phase 5 to one-line decision rules (e.g. 'NOT ASSESSED is not a pass — obtain the result or defer to 1.1').

DimensionReasoningScore

Conciseness

Largely lean — tables, exact prompts, and a ready-made record template with little padding — but a few rhetorical asides ('the gate record is the evidence that it earned the position', 'the worst possible audience for an unverified change') could be trimmed to pure decision rules. Not 3: the asides are minor and mostly justify real agent decisions.

4 / 5

Actionability

Fully executable for an orchestration skill: exact file paths (e.g. 'production/qa/bugs/*.md'), verbatim AskUserQuestion prompts with option lists, named agents per phase, a copy-paste patch-record template, and explicit fallbacks like recording 'Tests: NOT RUN — commands.test unset'.

5 / 5

Workflow Clarity

Seven phases are clearly sequenced with explicit validation checkpoints (rollback plan required before implementation, QA verdict gate, approvals checklist) and genuine feedback loops (FAIL → scope the fix out and defer to 1.1; NOT ASSESSED → obtain the result or defer).

5 / 5

Progressive Disclosure

Well-sectioned single file with clear phase headers and one legitimate external pointer ('.claude/docs/directory-structure.md'), but at ~250 lines the large Phase 6 patch-record template is inlined where a leaner overview pointing to a template file would fit better.

4 / 5

Total

18

/

20

Passed

Description

61%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.

A terse, domain-fluent description that clearly identifies its niche, but it omits any explicit 'when to use this' trigger guidance and understates its actual scope (cert feedback, patch notes, bug triage). Adding a trigger clause and one more concrete capability would lift it substantially.

Suggestions

Add an explicit trigger clause, e.g. 'Use when a gold master has passed the release gate and known bugs or cert feedback need a safe day-one fix before launch.'

Mention cert-feedback fixes and player-facing patch notes as concrete capabilities so the description covers the skill's full scope, not just the QA/rollback half.

Include natural trigger variations users might say ('day 1 update', 'launch day patch', 'cert feedback fixes') to broaden keyword coverage.

DimensionReasoningScore

Specificity

Names the domain ('Day-one launch patch', 'gold master') plus a few concrete action labels ('focused fix for known issues', 'QA gate and rollback'), but they remain terse labels rather than stated capabilities, and coverage has more than minor gaps (cert-feedback handling and patch-note generation are unmentioned).

3 / 5

Completeness

The 'what' is clear ('focused fix for known issues... Mini-sprint with QA gate and rollback'), but there is no 'Use when...' clause or equivalent trigger guidance; timing is only weakly implied by 'found after gold master', which caps completeness at 3.

3 / 5

Trigger Term Quality

Natural game-dev phrasings like 'day-one launch patch', 'gold master', and 'known issues' are present, but common variations ('day 1 update', 'launch day fixes') are missing and 'cert feedback' — a key trigger — appears only in the argument-hint, not the description.

4 / 5

Distinctiveness Conflict Risk

'Day-one launch patch... after gold master' carves a clear niche distinct from generic hotfix or patch-management skills, with only minor overlap risk against closely related release-workflow skills.

4 / 5

Total

14

/

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

Path

.claude/skills/day-one-patch/SKILL.md

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.