create-stories

Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

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-stories/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 body is exceptionally actionable and workflow-clear, with lean operational prose, concrete templates, and explicit validation gates. Its main weakness is monolithic structure with no progressive disclosure — substantial inline reference material could be split into separate files.

Suggestions

Split the Step 6 story-file template and the Step 3 classification table into a reference file (e.g. references/story-template.md) and link to it one level deep, keeping SKILL.md as an overview.

Extract the shared test-case spec / manual-check formats (Step 4b) into references/test-spec-format.md and reference it from both Step 4b and the story template.

Dedupe the review-mode handling (described in Step 1 and repeated in Step 4b) into a single canonical block to tighten the already-lean body.

Dimension	Reasoning	Score
Conciseness	Dense operational prose that assumes competence — no concept padding (a single framing sentence defines 'story'), with the bulk being directives, tables, and templates rather than explanations of things Claude already knows.	3 / 3
Actionability	Provides copy-paste-ready guidance: exact file paths, a complete story-file template (Step 6), named gates (QL-STORY-READY), and exact AskUserQuestion prompts/options — concrete and executable rather than abstract.	3 / 3
Workflow Clarity	Steps 1–7 are clearly sequenced with explicit validation checkpoints ('stop immediately' on missing ADRs, 'Do not proceed to Step 3 until... confirmed'), review-mode gating before each gate, and an ADEQUATE feedback loop that revises criteria before proceeding.	3 / 3
Progressive Disclosure	A single ~330-line monolithic file with no bundle files and no external references; well-organized into labeled sections, but large inline blocks (the story template, classification table, test-case formats) are content that could be split into one-level-deep reference files.	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 well-differentiated, naming concrete inputs and embedded outputs, but its trigger guidance is a sequencing cue rather than natural user-need language and lacks a 'Use when...' clause. Adding explicit trigger phrasing would lift the completeness and trigger-term dimensions.

Suggestions

Add a 'Use when...' clause with natural user phrasing, e.g. 'Use when breaking an epic into implementable stories or when the user asks to decompose an epic / create story files.'

Surface a few natural trigger variations beyond the jargon ('epic', 'GDD', 'ADR') — e.g. 'story breakdown', 'split epic into tickets', 'write story files'.

Keep the concrete input/output enumeration; it is the description's strongest feature and should anchor any revised wording.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Break a single epic into implementable story files', 'Reads the epic, its GDD, governing ADRs, and control manifest', and enumerates the structured fields each story embeds (TR-ID, ADR guidance, acceptance criteria, story type, test evidence path).	3 / 3
Completeness	Clearly states what the skill does, but the only 'when' guidance is the sequencing line 'Run after /create-epics for each epic' — a pipeline-order cue rather than an explicit user-need trigger, which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Includes relevant domain keywords ('epic', 'story', 'story files', '/create-epics') but they are process jargon with limited common variations, and there is no 'Use when...' clause enumerating natural user-need triggers.	2 / 3
Distinctiveness Conflict Risk	Occupies a clear, highly specialized niche (epic-to-story decomposition with GDD/ADR/TR-ID traceability) anchored to the /create-epics successor step, making conflict with other skills unlikely.	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-stories/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.