create-epics

Translate approved GDDs + architecture into epics — one epic per architectural module. Defines scope, governing ADRs, engine risk, and untraced requirements. Does NOT break into stories — run /create-stories [epic-slug] after each epic is created.

Quality

80%

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/create-epics/SKILL.md

Quality

Content

92%

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 exemplar of concise, actionable, well-sequenced workflow guidance with strong validation gates. The only weakness is progressive disclosure: large reusable templates and gate patterns are inlined rather than split into one-level-deep reference files within the bundle.

Suggestions

Move the EPIC.md and index.md markdown templates into a bundled reference file (e.g. references/epic-template.md) and link to it, keeping SKILL.md as a lean overview.

Consider bundling the gate-protocol detail (PR-EPIC inputs/verdict handling) into references/ or scripts/ instead of relying on the external .claude/docs/director-gates.md path.

Add clearly signaled one-level-deep navigation links ('See references/epic-template.md') so the overview points to the detailed materials at exactly one level of depth.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive — it never explains what an epic, ADR, or GDD is and each line gives instruction ('Run this skill once per layer', 'Do not create Feature layer epics until Core is nearly complete').	3 / 3
Actionability	It provides executable grep commands, exact file paths to read, copy-paste markdown templates for EPIC.md and index.md, and concrete AskUserQuestion prompts with option lists.	3 / 3
Workflow Clarity	A clear numbered sequence (Parse Arguments through Gate-Check) with explicit validation checkpoints — the PR-EPIC gate before any file writes, per-epic approval, and a revise-and-re-run feedback loop for unrealistics/concerns.	3 / 3
Progressive Disclosure	Sections are well organized, but the substantial EPIC.md/index templates and gate logic live inline in a single monolithic SKILL.md with no bundle reference files to split them into; the only pointers (director-gates.md) are external docs not present in the skill bundle.	2 / 3
	Total	11 / 12 Passed

Description

67%

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 clearly distinguishable, but it omits explicit trigger guidance and relies on domain jargon rather than natural user keywords. Adding a 'Use when...' clause with plain-language triggers would raise the trigger and completeness scores.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when you need to break an approved game design and architecture into epics for the production pipeline.'

Surface natural trigger terms a user would actually say (e.g. 'create epics', 'break the design into epics', 'plan production scope') alongside the GDD/ADR jargon.

Clarify the 'when' context — state that it runs after architecture review and control manifest pass so the trigger condition is explicit rather than implied.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Translate approved GDDs + architecture into epics' and 'Defines scope, governing ADRs, engine risk, and untraced requirements' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	It clearly states what the skill does but offers no explicit 'Use when...' trigger, so the 'when' guidance is only implied — capping completeness at 2 per the guidelines.	2 / 3
Trigger Term Quality	Terms like 'epics', 'GDDs', 'ADRs' are internal pipeline jargon rather than natural user phrasings, and only the action 'create epics' reads as a likely trigger; common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The skill is tied to a highly specific internal pipeline (GDDs, ADRs, TR registry, layer model), giving it a clear niche unlikely to conflict with other skills.	3 / 3
	Total	10 / 12 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/create-epics/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.