data-formats
01Skill Claude CodeCodex
Working with diverse data formats: binary, text, structured, and custom.
not rated 1.1k
+3 12d ago A 18 tokens
original MIT
Skill Claude CodeCodex
Best practices for creating research diagrams with Excalidraw MCP tools.
not rated 1.1k
+3 12d ago A 16 tokens
original MIT
Skill Claude CodeCodex
Comprehensive data analysis skill for CSV files using Python and pandas.
not rated 1.1k
+3 12d ago A 15 tokens
original MIT
debug-evals
04Skill Claude CodeCodex
Debug haiku.rag evaluation runs in Logfire. Use when asked to look at Logfire for an eval run, find failing or low-scoring eval cases, compare runs, check citation quality (citedmap) or judge pass rate (answerequivalent), or explain why an eval case failed. Drives the Logfire MCP against the evals service, or the…
not rated 585 6d ago A 103 tokens
original MIT
Skill Claude CodeCodex
Debug haiku.rag ingestion in Logfire. Use when asked to look at Logfire for ingestion, find failed or dead ingestion jobs, investigate retries or circuit-breaker events, trace a document through convert/chunk/embed/store, find which docling-serve instance served a request, spot slow conversions, or tell concurrent…
not rated 585 6d ago A 87 tokens
original MIT
DougTrajano/pydantic-ai-skills
Skill Claude CodeCodex
Profile and aggregate a bundled sales dataset - group revenue by region, category, channel or month, apply filters, and compute sums, means, medians and ranges. Use for questions about sales figures, trends, or which segments perform best.
not rated 363 6d ago A 51 tokens
original MIT
DougTrajano/pydantic-ai-skills
Skill Claude CodeCodex
Use this skill whenever the user is working with the Pydantic AI framework — including building AI agents, defining structured outputs with Pydantic models, wiring up tools/function calling, configuring model providers (OpenAI, Anthropic, Gemini, etc.), managing dependencies via agent context, handling streaming…
not rated 363 6d ago A 133 tokens
original MIT
web-research
08DougTrajano/pydantic-ai-skills
Skill Claude CodeCodex
Use this skill for requests related to web research; it provides a structured approach to conducting comprehensive web research.
not rated 363 6d ago A 25 tokens
original MIT
Skill Claude CodeCodex
Use when adding pause/resume, human approval, provider routing, tool scoping, or knowledge search to an existing agent — covers all optional Agent2 framework capabilities with implementation patterns.
not rated 36 3mo ago A 39 tokens
original MIT
brain-clone
10Skill Claude CodeCodex
Use when a domain expert wants to clone their professional brain into an Agent2 agent — interactive multi-phase interview that extracts identity, Chain-of-Thought, tools, knowledge, examples, and output format, then generates a complete production agent with a Sachbearbeiter-style Chain-of-Thought prompt, Pydantic…
not rated 36 3mo ago A 96 tokens
original MIT
Skill Claude CodeCodex
Use when building an agent that needs deep domain expertise — reads documents, checks them against professional knowledge, asks clarifying questions, and produces structured domain-specific output. Covers knowledge-backed agents, document processing, multi-turn workflows with human approval, and per-context knowledge…
not rated 36 3mo ago A 59 tokens
original MIT
Skill Claude CodeCodex
Build and debug Pydantic AI v2 agents using best practices for dependencies, instructions, tools, capabilities, hooks, and structured output validation. Use when the user wants to: (1) Create a new Pydantic AI agent, (2) Debug or fix an existing agent, (3) Add features like tools, validators, capabilities, hooks, or…
not rated 10 1mo ago A 135 tokens
original MIT
Skill Claude CodeCodex
Test and evaluate AI agents and LLM outputs using code-first evaluation framework with strong typing. Use when the user wants to: (1) Create evaluation datasets with test cases for AI agents, (2) Define evaluators (deterministic, LLM-as-Judge, custom, or span-based), (3) Run evaluations and generate reports, (4)…
not rated 10 1mo ago A 130 tokens
original MIT
Skill Claude CodeCodex
Writes and runs Python code in a sandbox. Describe the task in plain English — the skill will write and execute the program.
not rated 9 1mo ago A 29 tokens
original MIT
gmail
15Skill Claude CodeCodex
Search, read, send, and manage Gmail emails.
not rated 9 1mo ago A 13 tokens
original MIT
sandbox
16Skill Claude CodeCodex
Writes and executes Python code in a Docker sandbox with filesystem access and pre-installed data science packages.
not rated 9 1mo ago A 21 tokens
original MIT
Skill Claude CodeCodex
Skill "aether-aesthetics" from takzen/aether-agent, covering skill: aether aesthetics, główne zasady (design tokens), 1. paleta kolorystyczna (modern hsl), 2. glassmorphism (efekt szklany) and 3. animacje (framer motion).
not rated 8 5mo ago A 0 tokens
original Apache-2.0
pydantic-ai
18alirezaebrahimi5/ai-senior-engineer-template
Skill Claude CodeCodex
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
not rated 5 2mo ago A 32 tokens
Skill Claude CodeCodex
Consult a person's thinqee persona mid-task — ask how they would run a retro, handle a conflict, or what they think about a practice. Use when you want a specific person's grounded, cited stance (via their public thinqee API) rather than a generic best-practice answer. Treats "not in my notes" as a valid answer, never…
not rated 0 1mo ago A 82 tokens
original Apache-2.0
Skill Claude CodeCodex
Interview yourself into a thinqee persona knowledge base. Use when the user wants to build or extend their own persona (voice, values, methods, positions) for the thinqee engine, get "grilled" about how they work, or turn a declined question into a signed note. Runs the installed thinqee CLI's interview; it never…
not rated 0 1mo ago A 81 tokens
original Apache-2.0
pydantic-ai
21Skill Claude CodeCodex
Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.
not rated 31k today A 32 tokens
MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: