CtrlK
BlogDocsLog inGet started
Tessl Logo

build-with-tinybase

Scaffold, extend, and verify reactive local-first JavaScript or TypeScript applications with TinyBase. Use when choosing TinyBase for in-memory tabular or key-value state, generating an app with create-tinybase, adding schemas or UI bindings, configuring browser or database persistence, configuring MergeableStore synchronization, or diagnosing an existing TinyBase application.

76

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

96%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 a strong, lean operational guide: executable commands, clear lifecycle boundaries, and explicit verification with feedback loops. Progressive disclosure is good with one real reference file, though the bundle is light enough that further file-splitting opportunities are limited.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — no tutorial padding about what TinyBase or reactive state is; every line gives actionable guidance (scaffold commands, lifecycle boundaries, verification steps).

5 / 5

Actionability

Provides fully executable, copy-paste-ready commands (`npm create tinybase@latest -- --list-options` and a complete unattended generation invocation) plus concrete inspection targets and named documentation entry points (https://tinybase.org/llms.txt, Context7).

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced (inspect generator → generate unattended → post-generation checklist → extend → verify) with validation checkpoints including build/type-check, real reload for persistence, two-client sync confirmation, and an explicit feedback note that compilation alone is not proof.

5 / 5

Progressive Disclosure

A clear one-level-deep reference (`references/architecture.md`) is well-signaled for architecture decisions, and the body is appropriately split into scaffold/extend/verify sections; only a single bundled reference exists, leaving minor room for additional navigational pointers (e.g. API reference) rather than a full multi-file structure.

4 / 5

Total

19

/

20

Passed

Description

92%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.

The description is exemplary: concrete, action-oriented, with explicit 'Use when...' triggers tightly scoped to TinyBase. It cleanly satisfies the what/when requirements and is highly distinguishable from generic state-management skills.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Scaffold, extend, and verify', 'generating an app with create-tinybase', 'adding schemas or UI bindings', 'configuring browser or database persistence', 'configuring MergeableStore synchronization' — with comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers both 'what' (scaffold/extend/verify TinyBase apps) and 'when' via a detailed 'Use when choosing TinyBase... generating an app... adding schemas... configuring persistence... diagnosing' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'choosing TinyBase', 'generating an app', 'adding schemas or UI bindings', and 'diagnosing an existing TinyBase application' are present, but a few common variations (e.g. 'sync', 'local-first store') are missing.

4 / 5

Distinctiveness Conflict Risk

Tightly scoped to the TinyBase niche with distinct triggers (create-tinybase, MergeableStore, schema/UI bindings) and minimal overlap risk with other skills.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
tinyplex/tinybase
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.