bun-tanstack-start
TanStack Start full-stack React framework with Bun runtime. Use for TanStack Router, server functions, vinxi, or encountering SSR, build, preset errors.
82
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/bun/skills/bun-tanstack-start/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description that clearly identifies a specific technology niche (TanStack Start with Bun) and provides explicit trigger conditions. Its main weakness is that it describes the domain rather than concrete actions the skill performs (e.g., 'diagnoses build errors', 'configures server functions', 'sets up routing'). The trigger terms are excellent and highly distinctive.
Suggestions
Add concrete actions the skill performs, e.g., 'Diagnoses and resolves TanStack Start build errors, configures server functions, sets up TanStack Router routes' instead of just naming the domain.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (TanStack Start, full-stack React framework, Bun runtime) and mentions some specific concepts (TanStack Router, server functions, vinxi, SSR, build, preset errors), but doesn't list concrete actions the skill performs—it's more about what it covers than what it does. | 2 / 3 |
Completeness | Explicitly answers both what ('TanStack Start full-stack React framework with Bun runtime') and when ('Use for TanStack Router, server functions, vinxi, or encountering SSR, build, preset errors'). The 'Use for...' clause serves as a clear trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms users would actually say: 'TanStack Start', 'TanStack Router', 'server functions', 'vinxi', 'SSR', 'build errors', 'preset errors', and 'Bun runtime'. These cover the key terms a developer working with this stack would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive—TanStack Start, vinxi, and the combination of TanStack Router with Bun runtime create a very specific niche that is unlikely to conflict with generic React or other framework skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with excellent executable code examples covering the full TanStack Start + Bun stack. Its main weaknesses are verbosity (repeated patterns across sections that could be consolidated or split into reference files) and lack of validation checkpoints in workflows. The progressive disclosure at the end is good but the body itself is too long for an overview file.
Suggestions
Move detailed sections (Server Functions, API Routes, Search Params, Error Handling) into separate reference files and link to them from SKILL.md to reduce the main file size and improve progressive disclosure.
Add validation checkpoints to the Quick Start and Deployment workflows, e.g., 'Verify dev server is running at http://localhost:3000' after `bun run dev`, or 'Check .output directory exists' after build.
Consolidate the repeated users/database pattern—show it once fully, then reference it in subsequent sections rather than repeating similar fetch/sqlite code.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is fairly comprehensive but includes some redundancy—for example, the users route pattern is repeated across multiple sections (loader, server functions, API routes) with similar fetch/database code. Some sections like the basic route example are straightforward enough that Claude wouldn't need them, but the Bun-specific configuration and deployment details earn their place. | 2 / 3 |
Actionability | All code examples are fully executable and copy-paste ready with correct imports, proper TypeScript types, and realistic patterns. The quick start commands, project setup, route components, server functions, API routes, Docker deployment, and error handling all provide concrete, specific guidance. | 3 / 3 |
Workflow Clarity | The quick start section provides a clear sequence for project creation, and the deployment section has clear build steps. However, there are no validation checkpoints—for example, no verification step after build, no guidance on what to do if `bun run dev` fails, and the common errors table is reactive rather than integrated into the workflow as checkpoints. | 2 / 3 |
Progressive Disclosure | The 'When to Load References' section at the end is a good progressive disclosure pattern pointing to external files. However, the main body is quite long (~250 lines of content) with several sections that could be split into reference files (e.g., server functions, API routes, search params). The inline content is heavy for a SKILL.md overview. | 2 / 3 |
Total | 9 / 12 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- secondsky/claude-skills
- Commit
88da5ff
- 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.