agentic-development
Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)
33
30%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/agentic-development/SKILL.mdQuality
Discovery
32%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 too terse—it names the domain and two frameworks but lacks concrete actions, explicit trigger guidance, and natural keyword variations. It would benefit significantly from listing specific capabilities and adding a 'Use when...' clause to help Claude distinguish this skill from other coding or AI-related skills.
Suggestions
Add a 'Use when...' clause with trigger terms like 'Use when the user wants to build an AI agent, create agentic workflows, use Pydantic AI, or integrate the Anthropic Claude SDK in Node.js'.
List specific concrete actions such as 'define agent tools, configure agent loops, handle structured outputs, manage conversation state, set up streaming responses'.
Include natural keyword variations users might say: 'pydantic-ai', 'anthropic SDK', 'agentic workflow', 'tool use', 'function calling', 'agent framework'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain (AI agents) and specifies two frameworks (Pydantic AI, Claude SDK) with their languages, but doesn't list concrete actions like 'create tool definitions', 'configure agent loops', 'handle streaming responses', etc. | 2 / 3 |
Completeness | Provides a brief 'what' (build AI agents with specific frameworks) but completely lacks a 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill. Per rubric guidelines, missing 'Use when' caps completeness at 2, and the 'what' is also thin, so this scores 1. | 1 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'AI agents', 'Pydantic AI', 'Claude SDK', 'Python', 'Node.js', but misses common user terms like 'agentic', 'tool use', 'function calling', 'agent framework', 'pydantic-ai', or 'anthropic SDK'. | 2 / 3 |
Distinctiveness Conflict Risk | Mentioning specific frameworks (Pydantic AI, Claude SDK) provides some distinctiveness, but 'Build AI agents' is broad enough to overlap with other agent-building or SDK-related skills. The dual-framework scope also increases potential conflict with Python-only or Node.js-only skills. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
27%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill attempts to be a comprehensive guide to agentic development but suffers from extreme verbosity and scope creep — covering OpenAI, Gemini, and general agent architecture patterns despite being described as focused on Pydantic AI and Claude SDK. The content would benefit enormously from being split into focused sub-files, removing generic concepts Claude already knows, and replacing pseudocode patterns with fully executable examples.
Suggestions
Reduce scope to match the description: focus on Pydantic AI (Python) and Claude SDK (Node.js) only, removing OpenAI, Gemini, and generic agent architecture content that Claude already understands.
Split into multiple files: create separate reference files for Python/Pydantic AI patterns, Node.js/Claude SDK patterns, testing strategies, and guardrails, with SKILL.md serving as a concise overview with navigation links.
Replace pseudocode patterns (explore/plan/execute/verify with undefined types like `Task`, `Plan`, `llmCall`) with either fully executable examples or remove them in favor of framework-specific implementations that actually work.
Cut the document to under 200 lines by removing explanations of concepts Claude already knows (what agents are, three-component architecture, basic project structures) and focusing only on framework-specific, actionable guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose at ~600+ lines. Explains concepts Claude already knows (what agents are, what tools are, basic architecture diagrams). Includes extensive coverage of OpenAI, Gemini, and general agent patterns that go far beyond the stated scope of 'Pydantic AI (Python) and Claude SDK (Node.js)'. Much content is generic software engineering advice (project structures, testing patterns, memory interfaces) that doesn't earn its token cost. | 1 / 3 |
Actionability | Contains many code examples that appear executable for Pydantic AI and Claude SDK sections, but large portions are pseudocode-like patterns (explore/plan/execute/verify functions reference undefined types like `Task`, `Plan`, `Step`, `ToolResult`, `llmCall`). The guardrails, memory, and multi-agent sections show interfaces and patterns rather than copy-paste-ready implementations. | 2 / 3 |
Workflow Clarity | The explore-plan-execute-verify workflow is clearly sequenced with verification steps, which is good. However, the verification steps are conceptual pseudocode rather than concrete implementations. The overall document lacks a clear workflow for how to actually start building an agent — it presents many patterns without guiding the reader through which to use when, and the checklist at the end is a flat list rather than a sequenced workflow. | 2 / 3 |
Progressive Disclosure | Monolithic wall of text with no bundle files to reference. All content — framework selection, architecture, tool design, multi-agent patterns, memory, guardrails, model selection, testing, Pydantic AI patterns, skills pattern, anti-patterns, and quick reference — is crammed into a single file. This should be split across multiple files (e.g., separate files for Python/Pydantic AI patterns, Node.js/Claude SDK patterns, testing, guardrails) with the SKILL.md serving as an overview with navigation. | 1 / 3 |
Total | 6 / 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 — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (856 lines); consider splitting into references/ and linking | Warning |
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 9 / 11 Passed | |
- Repository
- alinaqi/claude-bootstrap
- Commit
7e5f7a2
- 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.