pydantic

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add…

Extend Pydantic AI agents with capabilities from pydantic-ai-harness -- the Coder coding agent, file and shell tools in local or sandboxed workspaces (Modal, E2B, Sprites, Daytona, boxd, smolvm, BoxLite), Code Mode, sub-agents and planning, memory and skills,…

Migrate Python LangChain, LangGraph, or Deep Agents applications to Pydantic AI and, when the source uses harness features, Pydantic AI Harness. Use for LangChain agents, chains, LCEL, direct LangGraph graphs, persistence, interrupts, streaming, and…

Migrate Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness. Use when the source uses the upstream `deepagents` package or demonstrably reproduces its middleware, backends, skills, memory, subagents, or sandbox contracts. Use…

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical…

Study a problem or GitHub issue in a fresh worktree, plan a fix, optionally implement it, and open the initial PR. Use when starting work on a new problem — not for advancing existing PRs.

Review candidate content locally under the scope, exemptions, and three-review budget defined by pushing-commits-to-the-repo

Capture a real, net-positive bug or improvement you discovered that is OUT OF SCOPE for the current PR — the PR already closes its issue and is stable, and the new work is non-trivial (adds its own decisions, carries uncertainty, or widens blast radius beyond…

Connect Claude Code or Codex itself to Logfire telemetry, or route a coding agent's model requests through Pydantic AI Gateway. Use for coding-session recording, capture policies, Gateway agent configuration, temporary proxy launches, status, or removal. Not…

Set up and troubleshoot Pydantic Logfire frontend observability and session replays in JavaScript/TypeScript browser applications. Use for browser errors, RUM, Web Vitals, replay recording, privacy controls, or reducing browser telemetry volume. Supports…

Build AI agents with Pydantic AI — tools, capabilities (including on-demand loading), workspaces, structured output, streaming, testing, and multi-agent patterns. Use when the user mentions Pydantic AI, imports pydantic_ai, or asks to build an AI agent, add…

Extend Pydantic AI agents with capabilities from pydantic-ai-harness -- the Coder coding agent, file and shell tools in local or sandboxed workspaces (Modal, E2B, Sprites, smolvm), Code Mode, sub-agents and planning, memory and skills, context compaction,…

Connect Codex itself to Logfire, check connection status, or stop session recording. Use for this plugin's MCP access and optional native Codex telemetry, not application instrumentation or AI Gateway routing.

Migrate Python LangChain, LangGraph, or Deep Agents applications to Pydantic AI and, when the source uses harness features, Pydantic AI Harness. Use for LangChain agents, chains, LCEL, direct LangGraph graphs, persistence, interrupts, streaming, and…

Migrate Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness. Use when the source uses the upstream `deepagents` package or demonstrably reproduces its middleware, backends, skills, memory, subagents, or sandbox contracts. Use…

Query and analyze Logfire telemetry data — traces, logs, spans, metrics, summaries, and SQL results. Use this skill when the user asks to "query logfire", "search traces", "find logs", "query data", "search spans", "look up errors in logfire", "get metrics…

How to write prose that reads like human technical documentation rather than LLM output. Use whenever writing or editing docstrings, comments, limitations/ docs, READMEs, commit messages or PR descriptions, and when prose reads as smooth, salesy or generic.

Read the review comments left by the known agent reviewers and repo maintainers on the current PR, resolve and reply. Use when asked to deal with PR comments, review feedback, or bot review findings.

Security review of the current branch against its merge base — sandbox escapes, memory errors, panics and resource-limit bypasses. Use when reviewing changes for security risk, or before merging anything touching the heap/ module, path_security.rs, the wire…

Fetch coverage diff from Codecov for the current branch or a specific PR. Shows uncovered lines, patch coverage, and overall coverage change.

Run and test Python code in a dedicated playground directory. Use when you need to execute Python scripts, test code snippets, investigate CPython behavior, or experiment with Python without affecting the main codebase.

Review the current branch against its merge base for bugs, CPython divergence, sandbox escapes, resource-limit escapes, performance regressions, verbose comments and missing ./limitations/ or docs/ updates. Use for a general pre-merge review of a branch or PR.

Check whether the common Python code an LLM would plausibly write still works on this branch, testing real cases in ./playground against CPython. Use to find behaviour that diverges from CPython or trips up ordinary idiomatic code.

Rewrite excessively verbose comments and docstrings added by this branch, and delete tautologous ones. Use after writing a feature to tighten up its comments; this skill edits code rather than only reporting.

Add Pydantic Logfire observability to application code — traces, logs, metrics, and AI/agent spans. Use when the user asks to add or configure Logfire, observability, tracing, logging, or monitoring; maximize useful telemetry; or understand what an app is…

Route broad requests to set up Pydantic Logfire across application instrumentation, infrastructure, evals, frontend observability, Gateway, or coding agents. Use for "set up Logfire", "add Logfire to my project", "get me set up properly with Logfire", "send…

Configure an application's model calls to use the Pydantic AI Gateway. Use when the user asks to route application inference through Gateway, connect a Gateway key, or add a Gateway provider snippet. This does not configure or instrument coding agents.

Run offline Python (`pydantic_evals`) or Node.js (`logfire/evals`) evaluations and review them in Logfire. Also redirect existing Braintrust `Eval()` suites. Use for eval setup, test datasets, AI scoring, agent checks, LLM judges, Braintrust migration, or…

Monitor hosts, Docker containers, Kubernetes clusters, database/queue/cache servers, and cloud-provider metrics with Pydantic Logfire — no application code required. Use this skill whenever the user asks to "monitor my host/server/VM", "monitor my Docker…

Create a PR in which all dependencies are updated to their latest versions and CI is passing. Only user initiated.

Extend Pydantic AI agents with batteries-included capabilities from pydantic-ai-harness -- Code Mode (collapse many tool calls into one sandboxed Python execution), a filesystem and shell, sub-agents, planning, context compaction, and more. Use when the user…

Migrate Python LangChain Deep Agents applications to Pydantic AI and Pydantic AI Harness. Use when the source uses the upstream `deepagents` package or demonstrably reproduces its middleware, backends, skills, memory, subagents, or sandbox contracts. Use…

Branch-local durable PR state -- issue brief, decisions log, and session handoffs. Read the brief, decisions, and latest handoff at session start; append decisions as you work; write a handoff only on user request or explicit session turnover.

What to do when you open a PR and every time you push -- label the PR, watch CI to green, triage every review comment to a reply and a reaction, and escalate genuine design trade-offs to maintainers. Use whenever you open a PR or push a commit to one.

Bootstrap branch-context on an existing PR. Writes issue-brief.md from the linked issue(s) + current PR state, and backfills pr-decisions.md with decision-bearing entries from already-resolved review threads. Use when picking up a PR mid-flight (yours or…

Use when adding, changing or removing a remote setting (a Logfire SDK policy control or one of its fields) that the SDK integrations carry out, or when changing which integrations carry one out live or at the next start. Covers the policy contract, the host…

Use when moving the clients to a new core release (a core/vX.Y.Z release appeared, a lock-bump PR is red with HTTP 404, or an SDK change needs behavior a newer core has). Covers editing opamp-core.lock.json with scripts/fetch_core.py lock/fetch/check, what…

Use when releasing anything from this repository: the Go modules (go/vX.Y.Z and the nested modules' tags), a Supervisor release (go/opampsupervisor/vX.Y.Z: GitHub Release archives with checksums and provenance), the collector extension, or the SDK packages…

Read first in any session that works on an opamp-clients pull request, and before acting on a CI failure, review comment, merge conflict or base-moved event for one. Covers the public-repo rule and the checks before every push, what may and may not be done on…

Add a new LLM model (or provider) to genai-prices pricing data, or change the price of one that is already there. Use when asked to add/update pricing for a model — e.g. "add grok 4.5", "add the new Claude", "update openai o5 prices", "provider X cut its…

Add a new inference provider to genai-prices, including provider data, matching, usage extractors, update automation, cassettes, agentic checks, generated artifacts, and Python/JavaScript/Go parity tests. Use for a new provider, not a new model on an existing…

Pydantic is a Python data validation and serialization library, based on type hints. Use this skill whenever you need to do relatively complex data modeling using Pydantic, e.g. when adding constraints, defining a model hierarchy with subclasses, etc.

Create a deck with deckx. Use when the user mentions "deckx", "deck" or "slides", asks to build a slide deck from MDX, asks to convert a brand palette into a deck stylesheet, or asks how to convert a deckx HTML deck into a PDF. Covers project layout,…

Verify Logfire Helm chart installs, stable upgrades, public APIs, and browser flows against the pinned platform images in an isolated local Kind cluster. Use for chart configuration, image, migration, routing, CSP, or topology changes.

Verify terraform-provider-logfire changes against platform's public API schema and existing Terraform resource lifecycle tests. Use before claiming provider behavior works.