agentify

Use when deciding how to manage, audit, sync, enable, disable, or troubleshoot skills and agents with the skillshare CLI across Claude Code, Codex, Gemini, OpenCode, Kiro, Goose, Pi, Antigravity, or project-local .skillshare setups. Especially use for questions about global vs project mode, disabled-by-default policies, .skillignore/.agentignore, target drift, broken symlinks, duplicate skills, sync dry-runs, or whether to use skillshare versus a runtime-native tool such as Codex skill-manager.

Use when creating git commits or reviewing commit messages. Ensures messages follow the Conventional Commits specification v1.0.0, which enables automated changelogs and semantic versioning. Invoked when the user wants to commit changes, craft a commit message, or validate an existing one.

Use when user references previous work phases, tasks, or discussions from prior sessions not present in current conversation context.

Use when designing or reviewing Python classes, deciding where logic belongs, or recognizing antipatterns like helper classes, utility bags, and god objects.

Use when crafting prompts that require factual accuracy, working with long documents, generating claims that need verification, or when outputs must be auditable and grounded in source material

Use when transitioning between work sessions and wanting to pick up where the previous session left off.

Use when: tracking work, adding todos, filing bugs, managing tasks/issues, checking what to work on, planning epics, deferring work, pre-PR checks, or any mention of bd/beads. Covers the full bd CLI.

Use when the user wants fast, high-quality command-line advice, shell one-liners, terminal troubleshooting, or the best CLI-native way to do something. Grounds answers in proven Unix command-line practices and the bundled art-of-command-line reference.

Use when reasoning about EP-133 KO-II device organization: slot/bank layout, where samples live, how pads map to filesystem nodes, node ID system, or project structure. Does NOT cover SysEx wire format — see ep133-protocol for that.

Use when implementing EP-133 KO-II upload/download/delete/metadata operations, debugging SysEx messages, or working with 7-bit packed encoding. Does NOT cover device organization (slots/banks/pads) — see ep133-device for that.

Use when configuring Ghostty, creating or looking up keybindings, setting up profiles, applying themes, working with splits, looking up available actions, or troubleshooting terminal config.

Use when parsing or generating Rekordbox MIDI Learn CSV mapping files, implementing MIDI-to-function lookup, working with deck channel offsets, hi-res 14-bit CC controls, or understanding DDJ/XDJ/DJM controller MIDI conventions.

Use when reviewing PCQ answers for The Club's Burning Man 2026 placement application, or when asked how a placement reviewer would assess an interactivity statement or other placement-facing document.

Periodic self-audit of Claude Code configuration quality, effectiveness, and documentation currency

Proactively suggests and writes session notes at end of work sessions for multi-day task continuity

Use when auditing skills for spec compliance, reviewing skill descriptions, checking frontmatter structure, or fixing common skill authoring violations. Provides the exact rules and a checklist to verify any skill file.

Use when the user wants to install, configure, migrate, or wire shortcuts/plugins for terminal apps such as yazi, zellij, tmux, fzf, starship, bat, fd, eza, or ripgrep. Handles environment probing, package-manager-aware setup, XDG config placement, plugin-manager bootstrap, and verification.

Use when estimating context window overhead in Claude Code configurations, auditing token consumption, identifying configuration bloat, or answering questions like "how many tokens left?", "check my context window", "what's eating my tokens?", or "audit Claude Code configuration".