dotfiles

Address Greptile PR review comments — read inline comments and summary, fix issues locally, push, reply to each thread, then tag Greptile to re-score and resolve threads.

End-to-end feature development loop. You describe a feature, iterate on the plan, then the team implements, reviews, ships a PR, and handles the configured PR-review bot autonomously. Notifies you at milestones. Use ONLY when the user wants the full autonomous implement→review→PR→verify loop for a multi-file feature. Do NOT use for: quick bug fixes, single-file edits, exploratory/discussion tasks, or anything the user wants to drive step-by-step.

Fetches and debugs a Langfuse trace OR session by ID or URL. A `.../sessions/<id>` URL renders a turn-by-turn conversation transcript (USER → TOOLS → ANNIE) across all the session's traces. A trace renders a span-tree overview with auto-suggested drill targets, then drills into a chosen section to surface system prompts, tool calls, and tool results. Renders both Anthropic block-style and langchain `tool_calls`-key messages, and strips noise (tool-call ids — incl. the giant gemini `__thought__` ids — plus `additional_kwargs`/`response_metadata`/message ids). Supports comparing two spans side-by-side. Use when the user provides a Langfuse trace/session ID or URL, mentions a langfuse.* link, or asks to debug, inspect, diagnose, or compare an LLM trace or conversation. Defaults to anyformat credentials (LANGFUSE_TRACING_*) and host (langfuse.anyformat.ai); other hosts work if LANGFUSE_HOST and LANGFUSE_PUBLIC_KEY/LANGFUSE_SECRET_KEY are set.

Query and debug anyformat's Datadog observability (logs, metrics, traces, monitors, incidents) via the plugin:datadog:mcp server, accounting for our non-standard loguru log structure. Use when searching or debugging anyformat logs/metrics/traces/monitors/incidents in Datadog, or when a Datadog log search for anyformat-core/backend returns 0 results.

Commit changes grouped by logical chunks, push to a feature branch, link a Linear ticket, and create a labelled PR. Targets 'dev' if it exists on origin (anyformat convention), otherwise the repo's default branch. Triggers on: commit, push, create PR, ship it, send PR.

Address failing CI checks on the current PR — group failures by root cause, fix locally, push, then watch the re-run. Pairs with react-to-greptile (comments) for full PR clean-up.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Find deepening opportunities in a codebase and propose refactors that turn shallow modules into deep ones. Aim is testability and AI-navigability. Use when the user wants to improve architecture, find refactoring opportunities, consolidate tightly-coupled modules, or make a codebase more testable.

Autonomous Sentry triage and fix loop. Pulls unresolved Sentry issues, investigates each in parallel, auto-dispatches up to 3 high-confidence fixes as spec loops, and resolves issues on merge. Triggers on: sentry fix, fix sentry errors, autofix sentry, sentry autofix.

Test-driven development with red-green-refactor loop, vertical slicing, and integration-first testing. Use when building features or fixing bugs test-first, when user mentions "TDD", "red-green-refactor", "test-first", or when /spec or /chunked-review delegates the test-writing step here.

Create new agent skills with proper structure, progressive disclosure, and bundled resources. Merges Anthropic's authoring best practices with a pragmatic process for our repo. Use when the user wants to create, write, or build a new skill.

Hygiene pass for Python: run Astral's ty (type check) + ruff (lint + autofix + format). Autofix what's fixable, report what's not. Use after editing Python or before committing.

Router for LangChain, LangGraph, and Deep Agents skills. Load this ONCE — it tells you which sub-skill file to read for the specific task.

Companion to a plan. Runs AFTER a plan exists (from plan mode, /spec Phase 1, or a plan.md file) and appends: viability + scoring + concerns + agent-team execution strategy. Use when you want a second-opinion pass before execution. Do NOT use to generate a plan from scratch — assumes a plan already exists.

Run tests for the anyformat monorepo (uv + docker compose). Use ONLY inside the anyformat-monorepo repo. Do NOT use for other repos — use their native test runner directly.

Implement a plan in logical, ordered sequential chunks. Each chunk is proposed with current/after blocks for approval before applying.

Run the test suite for anyformat-backend services using Docker Compose. Use when you need to validate code changes, debug failing tests, or verify that implementations work correctly before committing.