CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

create-stories

Breaks one epic into implementable stories with acceptance criteria. Use when the user wants stories for an epic or the next batch of work to build. Not for turning the whole design into epics.

Quality

82%

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

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 actionable, well-sequenced multi-phase workflow: every branch has concrete commands, exact strings and explicit validation gates, with genuine error-recovery loops. Its main costs are length — the minimal-tier rules and '## Your systems' ordering are each specified twice — and heavy inlining of detail (field tables, output templates, error messages) that could live in reference files like the existing qa-lead-gate.md.

DimensionReasoningScore

Conciseness

The body is dense, telegraphic and almost entirely project-specific operational detail Claude could not infer, with no padding about known concepts — but at ~378 lines it repeats itself in places, e.g. the '## Your systems' three-step ordering is specified in full in Phase 2 and again in Phase 6's minimal summary, fitting anchor 4 rather than the every-token-earns-its-place bar of 5.

4 / 5

Actionability

Guidance is fully executable throughout: exact commands (md-section.sh extract, adr-status.sh with ADR-NNNN args), exact file paths, exact message strings to utter on each failure branch, and a field-value table for the minimal tier — matching anchor 5's copy-paste-ready bar for an instruction-only skill.

5 / 5

Workflow Clarity

Eight explicitly numbered phases with a copy-and-tick checklist, validation checkpoints (report before drafting, QA gate before the ask, "Write nothing before the yes"), feedback loops for error recovery (missing ADR/EPIC/brief branches, dismissed question → ask again in plain text, declined write → BLOCKED verdict), and a terminal verdict block — a clear anchor 5 match with the destructive/batch cap not applying since write validation is present.

5 / 5

Progressive Disclosure

The one bundle reference (references/qa-lead-gate.md) is real, clearly signaled and one level deep, but the main body inlines substantial content that belongs in separate reference files — the entire minimal-tier spec with its field table, the Phase 6 output templates, and the exact error messages — fitting anchor 3's 'content that should be separate is inline' rather than anchor 4's 'most content is appropriately placed'.

3 / 5

Total

17

/

20

Passed

Description

75%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 strong description with an explicit what, an explicit 'Use when' clause, and an explicit exclusion boundary against the sibling epic-creation skill. Its weaknesses are narrow vocabulary and single-action framing: it omits the concrete byproducts (story files, EPIC.md and index updates) and natural synonyms like "break down" or "split".

Suggestions

Mention the concrete artifacts the skill produces (e.g., "...and writes them to production/epics/ with the epic's Stories table and index updated") to lift specificity from one action to several.

Add natural trigger variations such as "break down", "decompose", or "split an epic" to the 'Use when' clause so users phrasing the need differently still match.

DimensionReasoningScore

Specificity

"Breaks one epic into implementable stories with acceptance criteria" names the domain and a concrete core action, but lists only that one action — it never mentions writing the story files, updating EPIC.md or the epics index, so coverage is not comprehensive as anchor 4 requires.

3 / 5

Completeness

It explicitly answers both parts: the first sentence states what it does ("Breaks one epic into implementable stories with acceptance criteria") and "Use when the user wants stories for an epic or the next batch of work to build" gives a concrete when-clause — matching anchor 5, not 4, since the 'when' is fully explicit rather than vague.

5 / 5

Trigger Term Quality

"stories for an epic" and "the next batch of work to build" are natural trigger phrases, but common variations users would say — "break down", "decompose", "split into stories", "user stories" — are missing, matching anchor 3 rather than the fuller synonym coverage of anchor 4.

3 / 5

Distinctiveness Conflict Risk

"Not for turning the whole design into epics" explicitly draws the boundary against the sibling /create-epics skill, and "epic"/"stories" form a clear niche with minimal overlap risk, matching anchor 5.

5 / 5

Total

16

/

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/create-stories/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.