CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

storybook

Scaffolds, audits, and tests Storybook stories for React and React Native — a visual-regression `Default` story, an interactive `Playground`, and an interaction test, with an opt-in adversarial `--validate` pass. Triggers on "scaffold stories", "add storybook", "story for this component", "/storybook".

Quality

83%

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

73%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 well-structured workflow document — gated phases, decision tables, feedback loops, and a definition of done — that mostly avoids padding and gives concrete commands. Its defining weakness is that it is an index whose referenced detail files (all rules/ and templates/) are absent from the bundle, leaving the progressive-disclosure promise unfulfilled and the literal scaffolds unreachable.

Suggestions

Ship the referenced rules/*.md and templates/* files in the bundle (or inline the critical patterns, e.g. the variant-grouping scaffold and one full .test.stories.tsx example) so the 12 dangling pointers resolve.

Consolidate repeated per-phase "Load rules/…" pointers into the central Rules section to trim the token budget.

Drop or merge the "Decision flow at a glance" table with the When-to-use and phase tables to remove duplicated content.

DimensionReasoningScore

Conciseness

Dense, competent-facing content — exact jq/ls preflight commands, a prop-to-argTypes mapping table, hard rules stated as one-liners — with no explanation of concepts Claude already knows. Not 5: the "Decision flow at a glance" table restates the When-to-use and phase tables, and pointers like "Load rules/adversarial-validation.md" (×5), "Load rules/auth.md" (×4), and "Load rules/react-native.md" (×4) repeat across sections and could be consolidated.

4 / 5

Actionability

Phase 0 gives copy-paste bash ("jq '.devDependencies | keys[]' package.json | grep -E '@storybook/'"), the argument table gives exact flags and defaults, and Phase 4's locator ladder ("getByRole → getByLabelText → …") is concrete. Not 5: the actual generated-file contents live only in templates/*.md ("Use the literal scaffolding in templates/component.stories.tsx"), which are absent from the bundle, so the core scaffold is a shape diagram rather than executable code.

4 / 5

Workflow Clarity

"Each phase has a single gate. Do not proceed until it passes" plus a phase/gate table, a Phase 0 decision table with explicit halt conditions, an ordered Phase 5 verification list, a Phase 6 fix→pin→re-validate feedback loop with a confidence gate ("apply only at ≥ 90"), and a Definition of done checklist — explicit validation steps, feedback loops, and checklists throughout.

5 / 5

Progressive Disclosure

The body is a well-signaled thin index ("Concern-specific rules live in rules/*.md and load on demand", one-level-deep references, per-file descriptions in Rules/References/Templates sections), but scored against the actual bundle: all 7 rules/*.md and 5 templates/* paths are dangling — only references/ with 2 files exists — so navigation to the bulk of the skill's content fails. Not 3: the problem is not organization but that the referenced detail files are missing, which breaks the disclosure structure at its core; not 1 because the in-body structure and the two real reference files are clear.

2 / 5

Total

15

/

20

Passed

Description

88%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: concrete artefact-level actions, explicit trigger phrases in third person, and a well-scoped Storybook niche. The only gaps are a few missing natural trigger variations and the slight ambiguity of "add storybook" against installation requests.

Suggestions

Add natural trigger variations such as "write/create stories", "visual regression", or "interaction test" to the Triggers list.

Disambiguate "add storybook" (e.g. "add storybook stories") so it does not capture Storybook-installation requests the skill explicitly refuses.

DimensionReasoningScore

Specificity

"Scaffolds, audits, and tests Storybook stories" with named artefacts — "a visual-regression `Default` story, an interactive `Playground`, and an interaction test" plus "an opt-in adversarial `--validate` pass" — lists multiple concrete actions with comprehensive coverage of the skill's niche. Not 4: the enumeration of artefacts leaves no meaningful coverage gap.

5 / 5

Completeness

Explicitly answers both: what — "Scaffolds, audits, and tests Storybook stories … a visual-regression `Default` story, an interactive `Playground`, and an interaction test"; when — "Triggers on 'scaffold stories', 'add storybook', 'story for this component', '/storybook'" with concrete trigger phrases. Matches the anchor-5 example pattern exactly.

5 / 5

Trigger Term Quality

Triggers "scaffold stories", "add storybook", "story for this component", "/storybook" are natural phrases a user would say. Not 5: common variations like "create/write stories", "visual regression", "interaction test", or "chromatic" are missing; not 3 because the given terms are varied and natural rather than merely relevant.

4 / 5

Distinctiveness Conflict Risk

"Storybook stories for React and React Native" is a clear, distinct niche with tool-specific triggers. Not 5: the trigger "add storybook" can fire for installation requests, which the skill itself says it does not handle ("this skill does not bootstrap Storybook") — a minor overlap risk with install/setup intents.

4 / 5

Total

18

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

relative_links

Relative link issues: 35 missing, 13 suspicious

Warning

Total

13

/

16

Passed

Repository

mthines/agent-skills

Path

skills/design/storybook/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.