openai-assistants
Build stateful chatbots with OpenAI Assistants API v2 - Code Interpreter, File Search (10k files), Function Calling. Prevents 10 documented errors including vector store upload bugs, temperature parameter conflicts, memory leaks. Deprecated (sunset August 2026); use openai-responses for new projects. Use when: maintaining legacy chatbots, implementing RAG with vector stores, or troubleshooting thread errors, vector store delays, uploadAndPoll issues.
Install with Tessl CLI
npx tessl i github:jezweb/claude-skills --skill openai-assistants98
Does it follow best practices?
Validation for skill structure
Discovery
100%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 an excellent skill description that hits all the marks. It provides specific capabilities (stateful chatbots, Code Interpreter, File Search, Function Calling), includes concrete value propositions (prevents 10 documented errors), has explicit trigger guidance, and clearly distinguishes itself by noting deprecation status and recommending alternatives for new projects.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Build stateful chatbots', 'Code Interpreter, File Search (10k files), Function Calling', 'Prevents 10 documented errors including vector store upload bugs, temperature parameter conflicts, memory leaks'. Very detailed capabilities. | 3 / 3 |
Completeness | Clearly answers both what (build chatbots with specific features, prevent documented errors) AND when with explicit 'Use when:' clause covering maintenance, RAG implementation, and troubleshooting scenarios. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'OpenAI Assistants API', 'chatbots', 'RAG', 'vector stores', 'thread errors', 'uploadAndPoll', 'legacy chatbots', 'File Search', 'Function Calling'. These are terms developers would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche: specifically targets OpenAI Assistants API v2, explicitly notes deprecation and recommends alternative for new projects, mentions specific error types. Unlikely to conflict with general OpenAI or chatbot skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an exceptionally well-crafted skill document that maximizes information density while maintaining clarity. It excels at providing actionable, executable code for every major use case, includes critical validation checkpoints (especially for vector stores and run states), and properly handles the deprecation context without being verbose. The Known Issues section is particularly valuable, documenting real bugs with GitHub sources and working workarounds.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is highly efficient, avoiding explanations of concepts Claude already knows. Every section provides actionable information without padding - code examples are direct, limits are stated as facts, and the deprecation notice is appropriately brief. | 3 / 3 |
Actionability | Excellent executable code throughout - the Quick Start is copy-paste ready, all API patterns include complete TypeScript examples, and the Known Issues section provides both error messages and working fix code. Function calling, streaming, and file handling all have concrete implementations. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. The Quick Start has numbered steps, vector store usage explicitly warns to wait for 'status: completed', and the race condition handling includes proper polling loops with status checks. | 3 / 3 |
Progressive Disclosure | Excellent structure with clear overview sections and well-signaled one-level-deep references. Templates and references are listed at the end with clear paths. The main content stays focused while pointing to detailed materials (migration guides, error catalogs, related skills). | 3 / 3 |
Total | 12 / 12 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
| Criteria | Description | Result |
|---|---|---|
metadata_version | 'metadata' field is not a dictionary | Warning |
license_field | 'license' field is missing | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 13 / 16 Passed | |
- 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.