By spm1001
Session lifecycle, code review, data analysis, and behavioral skills for Claude Code. Best with: bon, garde-manger
Build a Chart.js HTML dashboard from BigQuery data
Explore a BigQuery project or dataset — list tables, catalog search
Turn a Google Sheet into a queryable BigQuery table — paste a URL, get a table
Profile a BigQuery table — schema, shape detection, quality assessment
Analyse a Google Sheet directly — no BigQuery needed. Paste a URL, get insights.
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)
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)
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 live session context (use garde-manger) or git history (use git log). (user)
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)
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)
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Robustness: Stable — used daily Works with: Claude Code (plugin or manual install) Requires: Claude Code CLI 2.0+
A skill drawer for Claude Code — slash commands that teach Claude specialized workflows.
Trousse provides 17 skills as SKILL.md files. Each one is a structured instruction set Claude reads and follows when you invoke the slash command.
Session lifecycle (startup briefings, handoffs, tactical tracking) is handled by bon, not trousse. Trousse is purely skills.
/plugin
# → batterie-de-savoir → trousse
git clone https://github.com/spm1001/trousse ~/Repos/trousse
The plugin system discovers skills from skills/*/SKILL.md automatically.
| Skill | What it does |
|---|---|
/titans (or /review) | Three-lens code review: hindsight, craft, foresight |
/diagram | Create diagrams with iterative render-and-check |
/screenshot | Capture screen to verify changes |
/picture | Generate images with Google Imagen |
/server-checkup | Linux server audit and management |
/github-cleanup | Audit repos, find stale forks and deps |
/sprite | Manage Sprites.dev remote VMs |
/skill-forge | Build and validate new skills |
/ia-presenter | Write iA Presenter slide decks |
/google-devdocs | Look up Google developer documentation |
/mandoline | Transform raw data into clean BigQuery tables |
/consomme | BigQuery data analysis — discover, profile, analyse, validate, present |
/toise | Architecture review (8 checks, letter grades) |
/claude-survey | Survey naive Claude instances for design research |
/ardoise | Context-isolated Claude (blank-slate testing) |
/amp-close | End-of-session ritual for Amp (CC uses bon's /close) |
trousse/
├── skills/ # 17 skill definitions (SKILL.md files)
│ ├── titans/ # → three-lens code review
│ ├── diagram/ # → diagramming workflow
│ ├── skill-forge/ # → skill development + validation
│ └── ...
├── scripts/ # Utility scripts used by skills
│ ├── ardoise.sh # → context isolation for spawned Claudes
│ └── bon-survey.py # → survey automation for claude-survey skill
├── hooks/
│ └── hooks.json # → empty (trousse registers no hooks)
├── references/ # Architecture docs (not loaded automatically)
│ └── ERROR_PATTERNS.md # → troubleshooting guide
├── tests/ # pytest suite
└── CLAUDE.md # Instructions Claude reads when working in this repo
cd ~/Repos/trousse && git pull
# Plugin cache refreshes on next session start
Use /plugin uninstall trousse to remove the plugin.
Trousse is part of Batterie de Savoir — a suite of tools for AI-assisted knowledge work.
Suite-level utilities for the Batterie de Savoir suite — cross-plugin updates and maintenance
Fast browser automation via Chrome DevTools Protocol. Requires: passe CLI (uv tool install passe), Chrome with CDP
Session lifecycle skill (couvert) + ping diagnostic MCP.
Todoist CLI with GTD coaching — outcomes, weekly review, pattern detection
GTD-native work tracker for AI coding agents — outcomes, actions, tactical steps
npx claudepluginhub spm1001/batterie-de-savoir --plugin trousseCore skills: ecosystem guide, skill creator, research patterns, session reflection, and plugin development. Includes UserPromptSubmit hook for forced skill evaluation.
Custom commands, skills, agents, rules, hooks, and output styles for Claude Code - session continuity and modern CLI tooling for real-world development workflows
Create, test, measure, and iteratively improve Claude Code skills with category-aware design, gotchas-driven development, progressive disclosure coaching, and automated description optimization.
Non-technical progress summaries for Claude Code work (hides diffs/log noise).
Skill and agent authoring tools: generate, audit, and improve Claude Code skills, commands, and agents
Analyze Claude Code agent session transcripts to identify inefficiencies, anti-patterns, repeated mistakes, missing tooling opportunities, and user frustration signals for continuous improvement