lox

lox/notion-cli

Skill Claude CodeCodex

Manage Notion pages, databases, and comments from the command line. Search, view, create, and edit content in your Notion workspace.

lox/agent-skills

Skill Claude CodeCodex

Performs skeptical, high-signal code reviews that try to break confidence in a change by surfacing grounded, material failure modes. Use when asked for an adversarial review, ship/no-ship assessment, or a review focused on subtle production risks instead of balanced feedback.

lox/agent-skills

Skill Claude CodeCodex

Iteratively reviews and improves the current PR or branch by running general-code-reviewing, fixing grounded issues, validating, and re-reviewing until the change is merge-ready or blocked. Use when asked to auto-review, self-review and fix, harden, polish, or get a PR ready.

lox/agent-skills

Skill Claude CodeCodex

Opens, updates, and carries GitHub pull requests through review feedback, rebases, CI or Buildkite failures, existing Codex review, and optional merge. Use when asked to publish a branch, address PR feedback, babysit or prepare a PR, make it mergeable, land it, or merge it.

lox/agent-skills

Skill Claude CodeCodex

Checks whether repository docs, plans, examples, runbooks, changelogs, generated docs, or other durable written artifacts match a code or configuration change. Use when asked to verify or update docs, prevent documentation drift, or check whether a PR needs documentation changes.

lox/agent-skills

Skill Claude CodeCodex

Emulates repository-librarian research in hosts without a native Librarian. Use in non-Amp agents when tracing dependency internals, comparing remote repositories, reading commit history, or explaining external architecture.

lox/agent-skills

Skill Claude CodeCodex

Drafts and revises concise, durable engineering plans. Use for docs/plans, architecture, rollout or design docs, first-slice selection, open-question resolution, plan review, or plan maintenance during implementation.

lox/agent-skills

Skill Claude CodeCodex

Runs a broad code review with separate ship-risk and simplicity lenses, then synthesizes grounded findings. Use for general PR, diff, or code reviews when the user did not request only one narrower review lens.

lox/agent-skills

Skill Claude CodeCodex

Writes, reviews, and refactors Go code with idiomatic package design, error handling, concurrency, performance, tests, linting, and toolchain awareness. Use when implementing or reviewing .go changes, tests, benchmarks, package APIs, or version-gated Go modernization.

lox/agent-skills

Skill Claude CodeCodex

Handles Codex GitHub PR review loops by waiting for reviews, fixing actionable feedback, resolving threads, and requiring Codex's main-thread thumbs-up. Use when Codex is already reviewing a PR, the PR has @codex review activity, or Codex has added an eyes reaction.

lox/agent-skills

Skill Claude CodeCodex

Writes, reviews, and optimizes high-performance Zig code with a measurement-first workflow, cache-aware layout, allocator discipline, comptime specialization, SIMD/scalar paths, and regression checks. Use for .zig changes where latency, throughput, memory, startup, binary size, or layout-sensitive code matters.

lox/agent-skills

Skill Claude CodeCodex

Rewrites robotic or AI-sounding text to feel natural while preserving meaning and voice. Use when humanizing or reviewing generated, over-polished, repetitive, or impersonal prose. Covers 24 wording patterns and 14 construction patterns.

lox/agent-skills

Skill Claude CodeCodex

Finds evidence-backed deepening opportunities that improve module leverage, locality, and testability. Use when asked to improve architecture, consolidate tightly coupled modules, reduce shallow abstractions, or explore a selected interface design.

lox/agent-skills

Skill Claude CodeCodex

Searches and manages Linear issues with the external linear CLI. Use when asked to find, view, create, update, assign, or change the status of Linear issues.

lox/agent-skills

Skill Claude CodeCodex

Manages Notion pages, databases, and comments with the external notion-cli. Use when asked to search, view, create, upload, edit, or comment on Notion content.

lox/agent-skills

Skill Claude CodeCodex

Reads x.com/twitter.com posts, quote posts, replies, and user-provided status IDs through the authenticated xurl CLI, with Birdclaw as an optional local fallback. Use when asked to read, summarize, inspect, quote, fetch, or explain an X/Twitter post or use authenticated X context.

lox/agent-skills

Skill Claude CodeCodex

Reviews changes for unnecessary code and structural complexity, judging whether new code, abstractions, dependencies, or configuration need to exist. Use for YAGNI, simplicity, minimalism, maintainability, over-engineering, deep code-quality, or explicitly harsh and thermo-nuclear reviews.

lox/agent-skills

Skill Claude CodeCodex

Reads Slack messages, threads, channels, and users with the external slack-cli. Use in hosts without native Slack tools when asked to view a Slack URL, search Slack, or look up Slack users.

lox/agent-skills

Skill Claude CodeCodex

Writes, rewrites, drafts, or reviews text in Lachlan's written and spoken voice. Use when the user asks to "talk like me" or "sound like me", or needs Slack replies, emails, leadership notes, technical feedback, customer or strategy messages, meeting comments, or talking points that match Lachlan's directness, dry…

lox/agent-skills

Skill Claude CodeCodex

Produces a concrete end-of-work walkthrough grounded in observed behavior and validation. Use when explicitly asked for a demo, walkthrough, substantial handoff, implementation showcase, UX or CLI examples, impact, limitations, or next steps.

lox/agent-skills

Skill Claude CodeCodex

Drafts, checks, and updates concise pull request titles and bodies grounded in the final diff, repository conventions, and author-supplied intent. Use when creating a PR, reviewing PR metadata, or refreshing stale PR text after a branch changes.