agentic-development

Build AI agents with Pydantic AI (Python) and Claude SDK (Node.js)

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Advisory

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./skills/agentic-development/SKILL.md

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is highly actionable with executable examples and a clearly sequenced, validated workflow, but it is verbose and delivered as one large monolithic file with no bundle references to split the detail. Splitting framework-specific guides into reference files would improve both conciseness and progressive disclosure.

Suggestions

Move per-framework detail (OpenAI/Gemini/Claude-specific and Pydantic patterns) into separate reference files linked from a concise overview in SKILL.md to improve progressive disclosure.

Trim redundant or already-known explanations (e.g., what each model tier is for) to tighten the body and reduce token cost.

Consolidate overlapping multi-agent sections so each pattern appears once instead of across framework-specific blocks.

Dimension	Reasoning	Score
Conciseness	The body is roughly 850 lines with overlapping coverage of multiple frameworks (OpenAI, Gemini, Claude, Pydantic) and some explanations Claude already knows; it is mostly efficient and code-driven but could be tightened and trimmed of redundant sections.	2 / 3
Actionability	It provides extensive copy-paste-ready executable code for Pydantic AI and the Claude Agent SDK plus concrete tool, memory, guardrail, and test patterns — specific and immediately usable.	3 / 3
Workflow Clarity	The Explore-Plan-Execute-Verify workflow is numbered with per-phase code, an explicit verification phase, and a self-correct/escalate feedback loop, giving clear sequencing with validation checkpoints.	3 / 3
Progressive Disclosure	No bundle files exist and the entire body is a single monolithic SKILL.md; sections are well-organized but content that could live in separate references (per-framework guides, checklists) is inline with no signaled one-level-deep references.	2 / 3
	Total	10 / 12 Passed

Description

72%

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 specific and distinct, naming concrete frameworks and natural trigger terms, but it omits an explicit "Use when..." clause inside the description field, which caps its completeness. Folding the when-to-use guidance into the description would push it to the top level.

Suggestions

Add an explicit 'Use when...' trigger clause directly inside the description field (e.g., '... Use when building AI agents, tool-using LLM systems, or agentic workflows.') so completeness is not capped.

List multiple concrete actions rather than the single verb 'Build' (e.g., 'Build, orchestrate, and test AI agents...') to reach the top specificity anchor.

Dimension	Reasoning	Score
Specificity	The description uses a single concrete verb ("Build AI agents") and names two specific frameworks ("Pydantic AI (Python)" and "Claude Agent SDK (Node.js)") rather than vague language, but it does not enumerate multiple distinct actions, so it stops short of the top anchor.	2 / 3
Completeness	It states what the skill does but the description field itself lacks an explicit "Use when..." trigger clause; per the rubric a missing trigger clause caps completeness at 2 even though a separate when-to-use field exists.	2 / 3
Trigger Term Quality	It surfaces natural terms a user would actually say — "AI agents", "tool-using LLM systems", "agentic workflows", plus the framework names — giving good coverage of common phrasings.	3 / 3
Distinctiveness Conflict Risk	The narrow focus on building agents with two named SDKs gives it a clear niche with distinct triggers, making unintended activation by other skills unlikely.	3 / 3
	Total	10 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 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	14 / 16 Passed

Repository: alinaqi/claude-bootstrap
Path: skills/agentic-development/SKILL.md
Commit: bb6195f

Reviewed: 6 days ago

Table of Contents

Discovery Implementation Validation

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.