Keep a change small and in the existing idiom - size the plan and weigh smaller alternatives before writing it, reuse the mechanism that already owns the behavior instead of adding a parallel one, and simplify the diff before handoff. Use when planning any change beyond a few lines, before readying a PR, or when reviewing agent-written code for bloat.
Personal productivity system for task and capacity management. Create and organize tasks with rich attributes (priority, effort, complexity, tags), track time and streaks, manage capacity across projects and contexts, view Eisenhower Matrix prioritization, sync calendar subscriptions, handle delegation and follow-ups, and get AI-powered insights. Supports batch operations, multi-project workflows, and real-time capacity planning to prevent overcommitment.
Manage Telegram channel access — approve pairings, edit allowlists, set DM/group policy. Use when the user asks to pair, approve someone, check who's allowed, or change policy for the Telegram channel.
Build multiple genuinely different versions of a UI piece you describe, rendered behind a visual picker so you can flip through them live and promote the one that feels right. Only runs when explicitly invoked; it does not trigger on its own.
Analyze geospatial data using geopandas with proper coordinate projections. Use when calculating distances between geographic features, performing spatial filtering, or working with plate boundaries and earthquake data.
Page transitions library for creating fluid, smooth transitions between website pages. Use this skill when implementing page transitions, creating SPA-like experiences, adding animated route changes, or building websites with smooth navigation. Triggers on tasks involving Barba.js, page transitions, routing, view management, transition hooks, GSAP integration, or smooth page navigation. Works with gsap-scrolltrigger for transition animations.
How to query OpenTelemetry metrics datasets in Honeycomb correctly. Metrics datasets follow different rules from trace/event datasets — many operations (bare COUNT, RATE_SUM, RATE_AVG, RATE_MAX, CONCURRENCY) are forbidden, temporal aggregation is automatic, and each metric has its own attributes. Use this skill when querying a metrics dataset (gauges, counters, histograms, sums), asking about temporal aggregation (RATE, INCREASE, SUMMARIZE, LAST), finding the metrics dataset or discovering metric names and attributes, debugging unexpected metrics query results, or querying infrastructure metrics like CPU, memory, disk I/O, or network stats. Do NOT use for instrumenting metrics (use otel-instrumentation), querying event datasets with "metrics" in their name, or conceptual questions (use observability-fundamentals).
Audits an existing repository against BazelStarterTemplate and brings it in line, one concern at a time - hermetic Bazel build, devenv and git hooks, format/lint tests, unit tests and coverage, conventional commits and release-please, CI, OCI image, documentation, CLAUDE.md - or upgrades a project created from the template to a newer template release. Use when the user asks to review, audit, standardize, clean up, modernize or "make consistent" a repository's infrastructure, to add CI, linting, formatting, releases, Docker/OCI images or docs to an existing project, to migrate a project to Bazel, or to update a project to the latest template.
Safety hooks for Claude Code — 916 pre-built hooks that prevent file deletion, credential leaks, git disasters, and token waste during autonomous AI coding sessions. 296 test files. Install with npx github:yurukusa/cc-safe-setup.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Expert in secure frontend coding practices specializing in XSS prevention, output sanitization, and client-side security patterns. Use PROACTIVELY for frontend security implementations or client-side security code reviews.
Use when asked to review a code change (diff, branch, or PR) for merge readiness and collaborate asynchronously with another agent (often invoked with tony:does-work) that is or will be pushing fixes to the same change. Leaves P0-P* findings in a Changelog section, then sleeps in 5-minute checks (up to 4) waiting for the other agent to respond, re-reviewing whenever it does. Triggers: 'review this PR and wait for the other agent', 'reviews:code', 'is this ready to merge, check back as they fix it'.