bendrucker

Query Claude Code session history via a DuckDB index over `~/.claude/projects/`. Use when asked about Claude Code activity ("how many tokens today?", "what did I work on this week?") or instead of reading, grepping, or jq-ing session transcripts. Not for codebase search, git log queries, or arbitrary databases.

Triage and batch-implement Claude-tagged Things todos as PRs for the claude config repo, discover improvement candidates from session history, or watch open PRs to implement review feedback and close shipped todos. Use when the user wants to work on their Claude Code improvement backlog, process Things todos tagged claude-code, batch-implement configuration changes, mine session history for grounded config-change candidates (Discover mode), or watch this skill's open PRs for review feedback and merges (Watch mode).

Creating and optimizing Claude Code Skills including activation patterns, content structure, and development workflows. Use when creating new skills, converting memory files to skills, debugging skill activation, or understanding skill architecture and best practices.

Targeted interview for execution-time clarification. Use when you hit an ambiguity or decision point during implementation that needs user input before proceeding.

Comprehensive interview for planning new features or changes. Use when the user wants thorough upfront planning before implementation, or when starting work on a complex feature.

Rewrite a draft message, explanation, or note to strip AI voice, slop, and filler while preserving meaning. Use to polish functional prose before sending.

Curate the writing plugin's trope ruleset by auditing wordlist entries against session history and surfacing candidate phrases. Use when refreshing trope detection, reviewing wordlist health, or mining sessions for new AI-writing patterns to add or stale rules to remove.

Finish a branch: infer which review passes the change warrants, run them, open the PR, babysit CI to green, triage bot comments, and refresh the body from a clean context.

QA the honeycomb CLI against a live account to find bugs and feature gaps. Target one command or resource family for manual testing, or sweep everything before a release. Use when dogfooding the CLI, reproducing a bug, or producing a findings report mapped to issues.

Manage Honeycomb boards: create, update panels, configure visualizations, and review in Chrome. Activated by explicit mention of Honeycomb boards or /board invocation.

Design and build Honeycomb queries: calculations, filters, breakdowns, visualization selection, granularity tuning, and anti-patterns. Activated by explicit mention of Honeycomb queries or /query invocation.

Honeycomb CLI and MCP server usage — auth, queries, datasets, SLOs, boards, triggers, markers, columns, and raw API requests for observability workflows

Working with Honeycomb SLOs, burn alerts, and SLO history

Add a new cobra subcommand to the CLI

Analyze shell history and installed tools to suggest dotfiles improvements. Use when looking for missing aliases, functions, completions, or topics based on actual usage patterns. Trigger on "what aliases should I add", "what's missing from my dotfiles", "audit my shell setup", "suggest improvements", "what should I add to my dotfiles", or any request to review dotfiles for gaps.

DuckDB data layer over shell command history (atuin) for usage analysis. Use when analyzing how commands are actually used — frequency, alias/function candidates, argument patterns, sequences. Not for editing config, querying Claude Code sessions, or non-shell data sources.

Capture screenshots of the user's tmux/terminal setup so the model can see what it actually looks like. Use when the user asks for a visual review of their terminal, tmux status bar, prompt, fonts, or pane chrome, or any case where text introspection (capture-pane, list-panes) loses styling, color, glyph, or layout fidelity.

Add interactive prompts, spinners, styled logging, and pickers to shell scripts using gum. Use when editing a shell script and adding a prompt, asking for confirmation, wrapping a long-running command in a spinner, picking from a list, logging styled status output, or otherwise making a script interactive. Trigger on "add a prompt", "show progress", "spinner", "make this script interactive", "confirm before", "ask the user", "pick from a list", "menu", "styled logs", "gum log", "gum spin", "gum confirm", "gum choose", "gum input".

ZSH completion system patterns and conventions. Use when implementing custom completion handling, writing completion files, or working with zsh autocomplete. Do not use when installing packages from homebrew, since that typically installs completions automatically.

Manage route-agent project: check status, find next tasks, spawn parallel work. Use when starting work, checking progress, or asking "what's next?"

Promptfoo evaluation framework for testing and comparing LLM outputs. Use when writing eval configs, creating test cases, debugging eval runs, or working with assertions.