CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

hotfix

Emergency fix bypassing normal sprint process — hotfix branch, approvals tracked, backport verified, full audit trail.

Quality

80%

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/hotfix/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 exceptionally well-engineered operational workflow: every phase has executable commands, verbatim prompts, explicit approval gates, and failure-mode handling (including the NOT ASSESSED anti-drift guardrail and the smoke-FAIL re-entry loop). The only weaknesses are minor — a few justificatory asides that could be trimmed, and a long single-file body that could split its templates into a reference file.

DimensionReasoningScore

Conciseness

The body is almost entirely concrete directives — exact git commands, verbatim AskUserQuestion prompts, templates, file paths — with no explanation of concepts Claude already knows; a handful of justificatory asides ("an emergency flow earns its audit trail by approving the change *before* it exists", "which is exactly why it is written down here") could be trimmed, keeping it at anchor 4 rather than 5.

4 / 5

Actionability

Fully executable guidance throughout: exact commands ("git checkout -b hotfix/[short-name] [base-ref]", "git tag --list", "git branch --list 'release/*'"), verbatim prompts with enumerated options, concrete paths (production/hotfixes/, production/qa/bugs/), copy-paste record and summary templates, and a named test-command source (commands.test from project.yaml) with its failure mode. Not 4 — there are no significant gaps in the common-case coverage.

5 / 5

Workflow Clarity

Phases 1–7 are clearly sequenced with explicit validation checkpoints and feedback loops: severity confirmation, pre-implementation approval, three-way approver sign-off, a QA gate whose NOT ASSESSED outcome is explicitly treated as unmet, a smoke-FAIL path that loops back to Phase 4, an unconditional deploy gate, and post-deploy verification covering all three verdicts. This matches the anchor with feedback loops for error recovery.

5 / 5

Progressive Disclosure

Single-file skill with no bundle directories; clear "## Phase" section headers make navigation easy, matching the good-structure anchor. Not 5 because at ~245 lines the under-50-lines exception doesn't apply and some content (the hotfix/fix record templates, the NOT ASSESSED policy) could arguably live in a one-level-deep reference file.

4 / 5

Total

18

/

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 communicates a clear, fairly specific emergency-hotfix niche with distinct positioning against the normal sprint process, but it lacks any explicit "Use when..." trigger clause, which both caps completeness and leaves natural trigger phrasings under-covered. Adding an explicit trigger sentence with user-natural terms (hotfix, emergency/urgent fix, critical production bug) would lift the weakest dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user reports a critical or urgent production bug needing an emergency fix outside the normal sprint/bug-fix process."

Include natural user phrasings and synonyms — "urgent fix", "critical bug", "production issue", "patch now" — alongside the existing "emergency fix" and "hotfix" terms.

Optionally surface one or two more of the skill's actual capabilities (severity triage, QA gate, patch-tag deployment) so the "what" coverage matches the skill's full scope.

DimensionReasoningScore

Specificity

Lists several concrete capabilities — "hotfix branch, approvals tracked, backport verified, full audit trail" — as a compressed pipeline, matching the several-specific-actions anchor; not 5 because coverage has gaps (severity triage, QA gating, and deployment are part of the skill but absent from the description).

4 / 5

Completeness

The "what" is clear (emergency fix with branch, approvals, backport, audit trail), but there is no "Use when..." clause or equivalent explicit trigger guidance — "when" is only weakly implied by "Emergency", which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

"Emergency fix" and "hotfix branch" are natural phrasings a user would say, giving good keyword coverage; not 5 because common variations like "urgent fix", "critical bug", or "production issue" are missing, and "backport"/"audit trail" are process jargon rather than trigger terms.

4 / 5

Distinctiveness Conflict Risk

"Emergency fix bypassing normal sprint process" carves out a clear hotfix niche and explicitly distinguishes it from the normal bug-fix workflow; not 5 because it could still overlap with a general bug-fix or release skill since the triggers are not fully distinct.

4 / 5

Total

15

/

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/hotfix/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.