Tessl • The management layer for AI agent skills

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

85%

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

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 actionable, well-sequenced workflow document: every phase has concrete commands, exact output templates, and explicit stop conditions, and the one bundle reference is properly gated. Its weaknesses are minor — some inlined per-tier detail that could be externalized, and a few passages compressed to the point of needing a re-read.

Dimension	Reasoning	Score
Conciseness	The body is dense, imperative, and project-specific throughout with no explanation of concepts Claude already knows (tiers, ADRs, TR registries, granularity settings are all project constructs); only minor instances could be tightened, such as the cryptic config-resolution preamble, matching the efficient anchor 4 rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	It provides copy-paste-ready commands ("bash .claude/scripts/md-section.sh extract design/gdd/[file].md \"Acceptance Criteria\"", "bash .claude/scripts/adr-status.sh ADR-0001 ADR-0003"), exact message templates for every stop/ask case, a full Phase 6 output example covering Ready, Blocked, and Visual/Feel stories, and a closing verdict block, with specific examples covering the common cases.	5 / 5
Workflow Clarity	Eight explicitly numbered phases with a copy-and-tick checklist, explicit validation gates (missing epic, missing ADR by tier, missing brief, missing VERSION.md), an ask-before-write feedback loop ("Write nothing before the yes"; an adjustment can change any estimate), and a declined-write recovery path ("Verdict: BLOCKED — user declined") with retry guidance for dismissed questions.	5 / 5
Progressive Disclosure	The single bundle reference (references/qa-lead-gate.md, verified to exist) is clearly signaled, one level deep, and conditionally loaded ("On a skip, do not load it"), but the ~310-line body inlines per-tier detail (the entire minimal branch and field-value tables) that could be split into reference files, leaving minor organization gaps consistent with anchor 4.	4 / 5
	Total	18 / 20 Passed

Description

78%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 trigger, and a valuable negative boundary clause. Its main gap is that it names only one concrete capability, keeping specificity at the anchor-3 level, and trigger coverage misses a few natural synonyms.

Suggestions

Add one or two more concrete actions to the what clause (e.g., "sizes and types each story, links it to its governing ADR and requirement") to lift specificity above anchor 3.

Include natural trigger variations such as "user stories" or "break down the epic into stories" in the use-when clause.

Tighten "the next batch of work to build" to something epic-scoped (e.g., "the next epic's batch of stories") to reduce overlap with sprint-planning skills.

Dimension	Reasoning	Score
Specificity	"Breaks one epic into implementable stories with acceptance criteria" names the domain and one concrete action with its deliverable, but does not list several specific actions as the 4-5 anchors require; it is far more concrete than the generic anchor-2 examples.	3 / 5
Completeness	It explicitly answers both what ("Breaks one epic into implementable stories with acceptance criteria") and when ("Use when the user wants stories for an epic or the next batch of work to build") with concrete trigger phrases, mirroring the rubric's good example structure.	5 / 5
Trigger Term Quality	"Use when the user wants stories for an epic or the next batch of work to build" covers natural phrases (stories, epic, batch of work) a user would say, but misses common variations like "user stories" or "break down/decompose the epic" that would merit a 5.	4 / 5
Distinctiveness Conflict Risk	The explicit exclusion "Not for turning the whole design into epics" cleanly separates it from a create-epics skill, but "next batch of work to build" leaves minor overlap risk with sprint-planning skills, matching the mostly-distinct anchor 4 rather than a clear niche 5.	4 / 5
	Total	16 / 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-stories/SKILL.md
Revision: 05ad7c8

Reviewed: 9 days ago

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.

create-stories

Table of Contents

Is this your skill?