create-epics

Turn GDDs plus architecture into epics — one per architectural module, with untraced requirements. Then /create-stories [epic-slug].

Quality

72%

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

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 a strongly engineered workflow: fully executable commands and templates, explicit validation gates with feedback loops, and careful tier-conditional behavior for a batch write operation. Its main weakness is repetition — the minimal-tier optionality note is restated several times — and a long single-file body that could move the EPIC.md template and tier matrix into a reference file.

Suggestions

Collapse the repeated minimal-tier notes (opening blockquote, 'When to run', Step 2a, Step 3, tier-adjustment block) into one canonical tier table plus a single forward reference, cutting significant duplicated prose.

Move the full EPIC.md/index.md templates into a references/ file (e.g. references/epic-template.md) and keep only the field summary inline, shortening the always-loaded body.

Trim the story_granularity and docs.density explanation paragraphs to a compact mapping table (tier → count / density) since the detailed prose mostly restates config semantics.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational — exact Grep invocations, bounded Read(offset, limit) instructions, and full templates — but the minimal-tier caveat ("at minimal /create-stories synthesizes the epic; this skill is optional") is repeated at least four times (the opening blockquote, 'When to run', the Step 2a skip rule, the Step 3 note, and the tier-adjustment block), and the story_granularity/docs.density prose runs long. Mostly efficient but could be tightened to a single canonical tier note.	3 / 5
Actionability	Guidance is fully executable: exact Grep patterns with output_mode and -A/-n flags, bounded Read(offset, limit) ranges through the next heading, a copy-paste-ready bash hook call, complete EPIC.md and index.md templates, and scripted AskUserQuestion prompts with enumerated options. This matches the anchor for copy-paste ready commands covering common cases.	5 / 5
Workflow Clarity	Steps 1-6 plus 4b are explicitly sequenced with validation checkpoints throughout: the three-outcome M/N Summary-scan table, the untraced-requirements warning gate, the PR-EPIC producer gate with revise-and-re-run feedback loops ("Do not write epic files until the producer gate resolves"), the never-overwrite EPIC.md check with update/skip options, and final Verdict lines. Batch file-writing is well guarded, matching the top anchor.	5 / 5
Progressive Disclosure	There are no bundle files; gate definitions, automation modes, and config resolution are delegated one level deep to clearly signaled .claude/docs/* paths, and the body is well-sectioned with headers and templates. However, the ~350-line body inlines the full EPIC.md template and the multi-tier matrix content that could live in reference files, leaving minor organization gaps — good structure but not the ideal split.	4 / 5
	Total	17 / 20 Passed

Description

53%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 compact and domain-specific with a clear 'what' and distinct niche vocabulary, but it lacks any 'when to use' trigger guidance and misses natural synonyms (e.g., 'game design document', 'break down into epics') and several concrete capabilities (writing EPIC.md files, layer scoping). It is serviceable but below the good-example standard, which pairs a full action list with an explicit 'Use when...' clause.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to break GDDs into epics, plan work per architectural module, or prepare epics before /create-stories at standard/full tiers."

Spell out the key acronym and add synonyms once — "GDDs (game design documents)" — so the description matches both abbreviated and full-form phrasings.

Name the concrete outputs ("writes production/epics/[slug]/EPIC.md and the epics index") so the action list is comprehensive rather than 1-2 actions.

Dimension	Reasoning	Score
Specificity	"Turn GDDs plus architecture into epics — one per architectural module, with untraced requirements" names the domain and two concrete actions (decompose per architectural module, surface untraced requirements), but omits key capabilities like writing EPIC.md/index files, layer scoping, and gate checks. It matches the anchor for naming the domain with 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	The 'what' is clear (turn GDDs plus architecture into epics, one per module, flagging untraced requirements), but there is no 'when' — no "Use when..." clause or equivalent trigger guidance anywhere in the description. Per the rubric guideline, a missing explicit trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Terms "GDDs", "architecture", "epics", and "/create-stories" are relevant domain keywords a user would plausibly say, but common variations and synonyms are missing — no "game design document" spelled out, no "break down"/"decompose"/"epic creation" phrasing. This fits the anchor for some relevant keywords while missing common variations.	3 / 5
Distinctiveness Conflict Risk	"GDDs", "epics", and architectural decomposition form a clear niche unlikely to trigger generically, but the trailing "Then /create-stories [epic-slug]" overlaps with the closely related sibling story-generation skill, creating minor conflict risk. Mostly distinct with minor overlap risk matches anchor 4; not 5 because of that sibling-skill pointer.	4 / 5
	Total	13 / 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/create-epics/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.