Skills covering Upstash Search quick starts, core concepts, and TypeScript/JavaScript SDK usage. Use when a user asks how to get started, how indexing works, or how to use the TS client.
58
66%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/upstash-search-js/SKILL.mdQuality
Discovery
67%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 adequately identifies the domain and includes an explicit 'Use when' clause, which is a strength. However, it lacks specific concrete actions (e.g., indexing documents, running queries, configuring namespaces) and could include more natural trigger terms users would use. The distinctiveness could be improved by clarifying what differentiates this from other Upstash product skills.
Suggestions
Add specific concrete actions like 'index documents, run search queries, configure namespaces, manage API keys' to improve specificity.
Expand trigger terms to include natural variations users might say, such as 'search API', 'full-text search', 'vector search', 'query documents', '@upstash/search package'.
Clarify boundaries with other potential Upstash skills by specifying this is specifically for the Upstash Search product (not Redis, Kafka, QStash, etc.).
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (Upstash Search) and mentions some actions like 'quick starts', 'core concepts', and 'SDK usage', but doesn't list specific concrete actions like indexing documents, querying, creating namespaces, etc. | 2 / 3 |
Completeness | Clearly answers both 'what' (covers quick starts, core concepts, and TS/JS SDK usage) and 'when' (explicit 'Use when' clause with triggers: getting started, how indexing works, how to use the TS client). | 3 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'Upstash Search', 'indexing', 'TS client', 'TypeScript/JavaScript SDK', but misses common variations users might say such as 'search API', 'vector search', 'full-text search', 'query', '@upstash/search', or 'npm install'. | 2 / 3 |
Distinctiveness Conflict Risk | The mention of 'Upstash Search' provides some distinctiveness, but 'core concepts' and 'quick starts' are generic enough to potentially overlap with other Upstash-related skills (e.g., Upstash Redis, Upstash Kafka). The description doesn't clearly delineate boundaries from other Upstash product skills. | 2 / 3 |
Total | 9 / 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 skill provides a solid, actionable quick start with executable TypeScript code that gets users up and running quickly. Its main weaknesses are the lack of linked file paths for referenced skill files, some redundancy between the code example and the bullet-point summary, and missing validation/error handling guidance. The progressive disclosure structure is reasonable but would benefit from actual links and tighter descriptions.
Suggestions
Add actual file paths or links to the referenced skill files (e.g., '[SDK Overview](./sdk-overview.md)') instead of just naming them
Remove the redundant 'Basic steps' bullet list since the code example already demonstrates those steps
Add a brief verification step after the search (e.g., 'console.log(results) to confirm documents were indexed') to improve workflow clarity
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient with a clean quick start example, but the 'Basic steps' bullet list is redundant given the code example already demonstrates those steps. The 'Other Skill Files' section descriptions are somewhat verbose with bullet lists that could be more concise. | 2 / 3 |
Actionability | The quick start provides fully executable, copy-paste ready TypeScript code with environment variable usage, SDK import, and a complete upsert + search workflow. The concrete code example is immediately actionable. | 3 / 3 |
Workflow Clarity | The quick start shows a clear sequence (install → create client → upsert → search), but there's no validation or error handling guidance. For a non-destructive simple skill this is acceptable, but the workflow lacks any verification step (e.g., checking results or handling missing env vars). | 2 / 3 |
Progressive Disclosure | The skill references two other skill files (sdk-overview and quick-start) with descriptions of their contents, providing reasonable navigation. However, the references lack actual file paths or links, and the descriptions are somewhat verbose lists rather than concise signposts. No bundle files were provided to verify the references. | 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.
1fc95df
Table of Contents
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.