spm1001

MANDATORY gate BEFORE running jq on any .jsonl under ~/.claude/ or reading past CC sessions. Invoke FIRST when introspecting conversations, searching session history, parsing transcripts, or building tools that read ~/.claude/projects/ data. Provides the CC JSONL schema reference and `deglacer` CLI tool — prevents the 54-attempt fumble pattern where Claudes guess at field names. Triggers on 'what happened last session', 'find when we discussed', 'parse session', 'read conversation', 'session history', 'token usage', 'deglacer'. Do NOT use for git history (use git log) or your own current-session context. (user)

Inspects which ad, martech, analytics, and affiliate tags fire on any website and identifies each by vendor — tag names collide, so it confirms identity, not just labels. Drives a clean headless Chrome that bypasses ControlD DNS filtering and uBlock via DoH, captures the full network with cookies accepted, then groups every host by vendor and flags the unknowns for hand identification. Use when asked 'what tags fire on this site', 'is there a Meta, GA4, or Lantern tag here', 'audit this site for tracking', 'reverse engineer the martech', 'accept all cookies and show what loads', 'which vendors does this site use'. Triggers on 'tag explorer', 'tag scan', 'tamis'. For page reading or browser automation use passe; tamis is the tag-identification layer on top. (user)

Orchestrates cross-machine repo hygiene + GitHub account cleanup via an audit→approve→execute process that prevents accidental deletion. FIRST sweeps every git repo across machines (local + ssh) for uncommitted/unpushed work and true ahead/behind drift, THEN audits GitHub-side — Dependabot alerts traced to unused-direct vs transitive deps, stale forks, orphaned secrets, failing workflows, plugin version-bump gaps. Triggers on 'clean up GitHub', 'audit my repos', 'uncommitted or unpushed changes', 'are my repos in sync', 'push discipline', 'Dependabot trouble', 'unused deps', 'stale forks', 'dependency audit'. Requires gh CLI (+ ssh for remote hosts). (user)

Deep clean and structural health check for Claude-maintained codebases. INVOKE BEFORE adding significant complexity, WHEN inheriting an unfamiliar repo, or when something feels off and you can't name it. Three agents — Cracks (architecture), Dustballs (convention drift), Goofs (correctness) — examine in parallel, then synthesise into an honest assessment. Triggers on 'toise', 'deep clean', 'health check', 'should I be worried', 'check this codebase', 'is the architecture sound'. (user)

Spawns an isolated Claude with no CLAUDE.md, no skills, no hooks, no plugin context — only training weights and built-in skills. INVOKE BEFORE running evals, design research, cold critique, baseline comparisons, or testing plugin installs as a fresh user would experience them. Triggers on 'blank slate claude', 'fresh claude', 'isolated claude', 'naive claude', 'test plugin install', 'out of box claude', 'ardoise'. (user)

Searches Google developer documentation via REST API — returns fresh Markdown from sites like cloud.google.com, firebase.google.com, developer.android.com, ai.google.dev. BEFORE scraping or guessing at Google API docs, invoke FIRST. Triggers on 'check the Google docs', 'look up Firebase docs', 'what do the Cloud docs say', 'Google API documentation', 'search Google developer docs'. (user)

Transforms SPSS files, CSVs, and spreadsheet dumps into self-documenting BigQuery tables. Load BEFORE ingesting raw data — invoke first when you see opaque column names (S1, Q1r3), numeric codes, or empty BQ descriptions. Triggers on 'make this data analysis-ready', 'build a clean BQ table', 'load this SPSS file', 'enrich this table', 'process this codebook'. (user)

Spawn a peer Claude on the Anthropic conductor mesh to review code. The reviewer reads the target files, sends observations via mesh message, and you receive them as <channel> tags — peer-to-peer, not authority channel. Requires conductor-channel MCP server (aboyeur). Triggers on /peer-review, 'get a peer review', 'fresh eyes on this', 'spawn a reviewer'. (user)

Activate at session start when .bon/ exists AND before any bon CLI command. Handles session orientation (process contributions, present hierarchy, pick direction) and structures draw-down workflow (bon show → bon work → bon step). Triggers on: session start with .bon/, /open, /bon, 'bon init', 'bon new', 'bon list', 'bon done', 'what can I work on', 'next action', 'desired outcome', 'file this for later', 'track this work', or when .bon/ directory exists.

Plan multi-session work as a bon hierarchy. Outcomes narrate the journey, actions carry execution detail, understanding.md provides the frame. Replaces plan mode for work that spans sessions. Triggers on 'plan this', 'how should we approach', or when about to enter plan mode for non-trivial work. (user)

Run before /exit, to reflect on this session and end it properly by figuring out what's best to (1) do now, with current context wisdom (2) file as a handoff for the next Claude as well as (3) capture for future Claudes in collective memory. Ends with a set of quick fixes and a commit. Invoke on 'wrap up', 'let's finish', 'close out', '/close'.

Orchestrates periodic cross-repo backlog review using 5-phase survey-verify-summarize-act-snapshot workflow that prevents closing items without codebase verification. Scans open bon items across all repos, dispatches parallel subagents to verify briefs against actual code, classifies as done/stale/active/blocked, and presents triage summary for user approval before closing. Load before backlog review sessions. Invoke on '/review', 'review my bons', 'backlog review', 'what needs closing', 'clean up bons', 'triage my backlog'. Requires bon skill loaded first.

Ship a Batterie shard or CLI change end-to-end in one verb — bump plugin.json, commit, push, trigger the assemble CI, watch it green, then pull this machine current. Use when you've edited a batterie source repo (instructions.md, a skill, a hook, CLI code) and want it live. Triggers on 'publish this', 'ship this shard', 'release this', 'cut a version', '/batterie:publish'.

Update all installed batterie plugins in one go

Show the Batterie suite version and every installed plugin/CLI version

Orchestrates diagram creation with iterative render-and-check workflow. Invoke FIRST when asked to 'create a diagram', 'Venn diagram', 'flow chart', 'architecture diagram', 'visualize this' — ensures CRAP-principled self-critique before showing user, preventing amateur layouts and low-contrast text. Composes with brand skills for styling. (user)

Generate images using Google Imagen. Use when user needs 'hero image', 'presentation visual', 'conceptual illustration', or 'generate an image'. Composes with itv-styling for brand-constrained outputs. (user)

Code review alias. Invokes titans (three-lens review).

Orchestrates browser automation — read pages, take screenshots, fill forms, capture network traffic, and verify deployments via Chrome CDP. MANDATORY BEFORE any `passe` command — 12-recipe cookbook covering scout-then-act pattern, verb conventions, and common pitfalls that prevent malformed scripts. Triggers on 'passe run', 'automate the browser', 'screenshot a page', 'scrape this page', 'fetch this page', 'open this URL in Chrome', 'what does this page look like on mobile', 'fill out this form', 'capture network requests', 'reverse-engineer API', 'check if this page has', 'verify deployment', 'dismiss cookie banner', 'monitor network traffic'. (user)

Lightweight session open/close ritual — top-and-tail a work session without a full work-tracker. Use when the user says open/start a session ("/open", "let's start") or close/wrap one ("/close", "wrap up"). Orients at the start; reflects, captures a short note, and commits at the end.

MANDATORY gate BEFORE any Todoist operation — orchestrates GTD semantics the CLI alone can't provide (outcomes are sections not tasks, workspace vs personal filtering, horizon alignment). Invoke FIRST for weekly review, outcome coaching, and pattern detection. Triggers on 'clean up outcomes', 'team priorities', 'is this a good outcome', 'weekly review', 'am I overcommitting', 'check my patterns', 'should I take this on', 'scope creep', 'freedom score'. (user)

Orchestrates content fetching via mcp__mise__ tools. Load before using search/fetch/do — invoke first when you see 'search Drive', 'search Gmail', 'find docs about', 'fetch this document', 'research in Workspace', 'move this file', 'create a doc', 'triage my inbox', 'archive these', 'draft an email'. Covers research loops, Gmail triage with batch ops, email drafting, and result filtering the tools alone don't know. (user)

Orchestrates collaborative document editing. Load before any mcp__tafelmusik__ tool call. Invoke first when user says 'edit the doc', 'check the document', 'add a comment', 'write together', or 'collaborate on this' — teaches load-first workflow, edit mode selection, and comment conventions that prevent data loss.

Search and retrieve context from past Claude sessions. Triggers on 'search memory', 'find past sessions', 'what did we learn about', 'have we done this before', 'what did we decide about', 'what did I work on yesterday', 'remind me what we did', or when disoriented about past work ("I'm lost", "where were we?"). (user)

BigQuery data analysis — BEFORE writing any BQ query, load this for methodology and dialect reference. Provides 5-stage workflow (discover → understand → analyse → validate → present) mapped to MCP tools (execute_sql, forecast, analyze_contribution, catalog search). Triggers on 'analyse this data', 'explore the dataset', 'what tables do we have', 'build a dashboard', 'query BigQuery', 'why did this metric change'. (user)

Mobile web UI for Claude Code — setup, status, and management. Invoke FIRST when setting up gueridon on a new machine, checking bridge status, or troubleshooting mobile access. Triggers on 'set up gueridon', 'mobile Claude', 'access from phone', 'check bridge status', 'gueridon status'. (user)