ts-agent-sdk
Generate typed TypeScript SDKs for AI agents to interact with MCP servers. Converts JSON-RPC curl commands to clean function calls. Auto-generates types, client methods, and example scripts from MCP tool definitions. Use when building MCP-enabled applications, need typed programmatic access to MCP tools, or creating reusable agent automation scripts.
77
Does it follow best practices?
If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:
npx tessl skill review --optimize ./path/to/skillValidation for skill structure
Discovery
85%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 strong skill description that clearly articulates specific capabilities and includes an explicit 'Use when' clause. The description effectively communicates the technical domain (MCP SDK generation) with concrete actions. The main weakness is that trigger terms are somewhat technical and may miss natural language variations users might employ.
Suggestions
Add more natural trigger term variations like 'SDK generator', 'generate client', 'type-safe MCP', or 'MCP wrapper' to improve discoverability
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Generate typed TypeScript SDKs', 'Converts JSON-RPC curl commands to clean function calls', 'Auto-generates types, client methods, and example scripts from MCP tool definitions'. | 3 / 3 |
Completeness | Clearly answers both what (generate typed SDKs, convert curl commands, auto-generate types/methods/scripts) AND when ('Use when building MCP-enabled applications, need typed programmatic access to MCP tools, or creating reusable agent automation scripts'). | 3 / 3 |
Trigger Term Quality | Includes relevant technical terms like 'TypeScript SDKs', 'MCP servers', 'JSON-RPC', 'MCP tools', but these are fairly technical. Missing more natural variations users might say like 'SDK generator', 'type generation', or 'MCP client'. | 2 / 3 |
Distinctiveness Conflict Risk | Very specific niche targeting MCP SDK generation with TypeScript typing. The combination of 'MCP servers', 'TypeScript SDKs', and 'JSON-RPC curl commands' creates a distinct trigger profile unlikely to conflict with other 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 skill provides solid, actionable guidance for generating TypeScript SDKs with clear code examples and a well-defined workflow. However, it lacks validation checkpoints in the generation process and could be more concise by moving reference material (error types, env vars) to separate files. The workflow would benefit from explicit verification steps after code generation.
Suggestions
Add validation checkpoints after Step 3 (verify generated types compile) and Step 4 (verify client methods are syntactically correct) to catch generation errors early
Move the error handling types and environment variables table to a separate REFERENCE.md file, keeping SKILL.md focused on the generation workflow
Add a feedback loop for handling Zod schema conversion failures - what to do when a schema can't be cleanly converted to TypeScript
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Content is mostly efficient but includes some unnecessary explanation like the detailed environment variables table and error handling section that Claude could infer. The workflow steps are clear but could be tighter. | 2 / 3 |
Actionability | Provides fully executable code examples throughout - from copying templates, to generated TypeScript interfaces, client classes, and runnable example scripts. Commands are copy-paste ready with clear patterns. | 3 / 3 |
Workflow Clarity | Steps are clearly numbered and sequenced (Steps 1-6), but lacks validation checkpoints. No verification that generated code compiles, no feedback loop for handling extraction failures or schema conversion errors. | 2 / 3 |
Progressive Disclosure | References template location and output structure well, but the skill is somewhat monolithic. The detailed type generation examples and error handling could be split into separate reference files for cleaner organization. | 2 / 3 |
Total | 9 / 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.