CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

playground-demos

Choose and write live playground demos for the dataclient.io docs site and homepage (HooksPlayground examples, the homepage demo, their fixtures). Use when adding, redesigning or reviewing a docs demo, or coming up with a new demo idea for a feature.

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

76%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 body is an exemplary lean, opinionated conventions list with genuinely concrete rules (components, layouts, fixture interception, effort-based escalation). Its main weaknesses are that the demo-building workflow is never sequenced — verification steps are implied rather than ordered — and the single external reference escapes the skill bundle, leaving the skill dependent on repo layout.

Suggestions

Add a brief ordered workflow (e.g., 1. Read the Playground README's Layouts and Design system sections, 2. Pick a use case where the preview shows the advantage, 3. Write the demo with one uncollapsed file in the `row` layout, 4. Verify phone width and both themes) so the existing checks become explicit checkpoints.

Include or point to one minimal example of an existing demo (file path in the repo) so the abstract criteria ("very beautiful", "as simple as possible while still showing maximum value") have a concrete model to imitate.

Copy the essential Layouts and Design system guidance into a bundled reference file (e.g., `references/playground.md`) instead of a `../../../` path that escapes the skill directory, so the reference resolves wherever the skill is installed.

DimensionReasoningScore

Conciseness

Lean and dense — every bullet carries a project-specific rule ("Loading states are skeletons (`<Loading />`, `skeleton`), not 'Loading…' text"; "never a new Playground prop"), and the few rationale lines ("People copy what they see and agents copy the code") are project-specific rather than concepts Claude already knows. Every token earns its place.

5 / 5

Actionability

Mostly concrete for an instruction-only skill: specific component names, layout choices ("Use the `row` layout, with one uncollapsed file"), a fixture path (`website/src/fixtures/`), and an explicit escalation rule for ideation. Not 5 because there is no example demo or pointer to an existing demo to model from, and some directives remain abstract ("very beautiful", "as simple as possible while still showing maximum value").

4 / 5

Workflow Clarity

The work order (consult the Playground README, pick a use case, implement, verify) is only implicit — the content is a criteria list, not a sequence — and the verification checkpoint ("Check phone width and both themes") is buried as the last bullet rather than framed as a step. Validation exists so it is above 2, but checkpoints are implicit, matching 3.

3 / 5

Progressive Disclosure

A short, well-sectioned overview (Goal, Conventions) with a single clearly-signaled one-level reference that even names the relevant sections ("mainly its Layouts and Design system sections"). Not 5 because that reference points outside the skill directory (`../../../website/src/components/Playground/README.md`) and the core mechanics the skill depends on are not bundled with it — a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

87%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: it states concrete capabilities with named artifact types, uses an explicit "Use when..." clause covering add/redesign/review/ideate triggers, and is tightly scoped to a niche with minimal overlap risk. Only minor gaps in synonym coverage keep trigger term quality and specificity from full marks.

DimensionReasoningScore

Specificity

Names several concrete actions and targets — "Choose and write live playground demos" with "HooksPlayground examples, the homepage demo, their fixtures" — in third person. Not 5 because coverage is limited to choosing/writing and reviewing contexts; not 3 because it goes well beyond 1-2 generic actions by enumerating specific artifact types.

4 / 5

Completeness

Explicitly answers both: what ("Choose and write live playground demos for the dataclient.io docs site and homepage...") and when with concrete trigger phrases ("Use when adding, redesigning or reviewing a docs demo, or coming up with a new demo idea for a feature"). Matches the 5 anchor exactly.

5 / 5

Trigger Term Quality

Good natural keywords users would say: "docs demo", "demo idea", "playground demos", "homepage demo", "adding, redesigning or reviewing". Not 5 because common synonyms like "example", "sample", "showcase", or "live example" are missing.

4 / 5

Distinctiveness Conflict Risk

"dataclient.io docs site", "HooksPlayground", and "their fixtures" carve a clear niche with distinct triggers; it could only fire for this project's demo work, so conflict risk is minimal. Clear fit for the 5 anchor.

5 / 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_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

relative_links

Relative link issues: 1 suspicious

Warning

Total

13

/

16

Passed

Repository

reactive/data-client

Path

.agents/skills/playground-demos/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.