Personal Obsidian notes management — project lifecycle, sessions, meetings, invoices, RAG export; email triage; solo TTRPG domain tooling (pc, rpg, solo-mc) on autonomous local game domains; the Documents/ organiser tree (cache-based: index, check, fix, sort); and brief/lore/data assembly for writing: brief (builds the portable _brief/ working dir), forge (concept), research (data), lore-extract, rules-keeper, extract-pdf.
GM voice for solo RPG — creates scenes, routes description to cinerio and dialogue to conversation-cards, enforces HRP/RP conventions, drives the micro-scene interactive loop, and proposes logging pauses. Uses response-templates.md for consistent output. Use proactively when the player uses `/scene`, continues a scene, or needs GM narration during a solo RPG session.
Invisible decision engine for solo RPG — breaks linear cause/effect by routing randomness and world decisions to the appropriate game subsystem. Routes hasard (dice, random word/concept) to muses-et-oracles, and decision (what does the world decide?) to parallaxe. Reads system dice from R/_systeme/canon/. Maintains Facteur Chaos. Use proactively when the LLM needs to determine an unpredictable outcome, inject entropy, or answer a fate question — never surfaces as a visible prompt unless a die result is shown.
Builds the portable, self-contained _brief/ working directory consumed by the writing plugin — summary.md (autonomous brief), personas/, output-styles/. Use when starting a new writing unit (technical doc, cheat sheet, RPG scenario, novel…) and you need to assemble its brief before producing with writing. Do NOT use to write chapters — use `writing:write`; do NOT use to develop the concept — use `forge` first.
Multi-session pipeline for extracting content from large PDF files and distributing it into reference source documents under sources/. Use when importing an existing PDF (rulebook, novel, source document) into a by-game domain (R) across multiple sessions. Do NOT use for web research — use `writing:research` instead; do NOT use for writing new content — use `writing:write` instead. Do NOT use to produce final canon — run `lore-extract` (lore) and `rules-keeper` (rules) on the resulting sources/ files to ventilate into canon/.
Iterates on a narrative writing project's overview — challenges concepts, proposes alternatives, and validates structure until the project is ready for TOC generation. Use when developing a novel, RPG scenario, or guide concept; when the overview is empty or needs challenging; when stuck on narrative structure. Do NOT use for software or code brainstorming — use aidd-refine:brainstorm instead; do NOT use once the overview is complete and validated — use `writing:toc` instead.
Extracts and organizes universe lore from raw source files into structured thematic files under canon/ and mj/ (terminologie, factions, histoire, géographie, personnages, and optional themes), separating canonical lore (canon/) from homemade/user-created content (mj/). Works from the current directory; resolves the game domain R locally (walks up to the _campagnes/, _univers/ or _pjs/ marker) to place outputs. Use when processing PDF extracts, notes, or raw text into universe documentation ready for other writing skills (and by obs:rpg for JDR universes). Do NOT use for web research — use `writing:research` instead; do NOT use for PDF extraction — use `extract-pdf` first, then pipe output here.
Sorts, summarizes, merges, and files emails exported as Markdown in C:/Users/fxgui/Public/Notes/Thunderbird/. Scans a scope (all of Thunderbird/ or a sub-branch), applies the rules in mail-config.yaml, proposes validatable action batches, then executes classify / delete / merge / summarize / flag-phishing. Detects duplicates, applies prune rules, identifies phishing, and logs each session. Use when the user invokes /obs:mail. Do NOT use for project management — use obs:project instead.
Uses power tools
Uses Bash, Write, or Edit tools
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.
Marketplace personnelle de plugins Claude Code — overlay du framework AIDD pour tous mes développements.
Le détail des skills de chaque plugin vit dans son propre README — ce tableau est l'index.
| Plugin | Doc | recommended | Description |
|---|---|---|---|
overcode | README · CHANGELOG | ✅ | Socle commun — workflows projet-agnostiques (alias, harvest, audits perf, readme, changelog…) |
design | README · CHANGELOG | — | Design system en entonnoir : define → destructure → adjust → enforce → diffuse |
writing | README · CHANGELOG | — | Rédaction pro et narrative : documentation (guides, technique, cahier des charges) et craft narratif |
game-writer | README · CHANGELOG | — | Écriture narrative de jeu vidéo (8-MINE) : timelines Dialogic, bank d'assets |
sc-godot | README · CHANGELOG | — | Stack Godot / GDScript : sniff, audit, improve, legacy, teach |
sc-js | README · CHANGELOG | — | Stack JavaScript : Nuxt / Vue SPA / Vite / Alpine / Astro |
sc-php | README · CHANGELOG | — | Stack PHP : Laravel / Symfony / WordPress / HTMX |
sc-python | README · CHANGELOG | — | Stack Python : Django / FastAPI / Flask / Celery |
sc-rust | README · CHANGELOG | — | Stack Rust : Axum / Actix-web |
sc-tiers | README · CHANGELOG | — | SaaS tiers : Firebase, Klaviyo, GTM, Clarity, PSI |
obs | README · CHANGELOG | — | Notes Obsidian — projets Pro, JDR solo, tri d'emails, assemblage d'intrants pour writing |
Depuis GitHub — ajouter dans ~/.claude/settings.json :
{
"extraKnownMarketplaces": {
"my-marketplace": {
"source": {
"source": "github",
"repo": "RebelliousSmile/my-claude-marketplace"
}
}
}
}
En local (développement) — utiliser "source": "directory" avec le chemin absolu ; les modifications sont prises en compte sans push.
Global (tous les projets) — ~/.claude/settings.json :
{
"enabledPlugins": {
"overcode@my-marketplace": true
}
}
Par projet — .claude/settings.json du projet, ou via commande :
/plugin install sc-js@my-marketplace
| Type de projet | Plugin |
|---|---|
| Socle (tous projets) | overcode |
| Design system / UI mobile-first | design |
| Documentation ou rédaction narrative | writing |
| Web JavaScript / Nuxt / Vue | sc-js |
| Web PHP | sc-php |
| Web Python | sc-python |
| Web Rust | sc-rust |
| SaaS tiers (Firebase, Klaviyo, GTM…) | sc-tiers |
| Jeu vidéo (contenu narratif) | game-writer |
| Jeu vidéo (code Godot) | sc-godot |
| Notes Obsidian / JDR solo | obs |
MIT — voir LICENSE.
npx claudepluginhub rebellioussmile/my-claude-marketplace --plugin obsSource des skills natives Hermes Agent (Nous Research, agentskills.io). solo-mc (MJ JDR solo en direct, agent unique, modules oracle/narrateur) est déployée vers ~/.hermes/skills/ — pas exécutée par Claude Code (variante Claude Code : obsidian:solo-mc).
Rust-specific skills and workflows: two-tier sniff (pivot model), audit (aidd-dev:reviewer), improve, legacy, log-analysis, teach (Axum/Actix + SQLx/Diesel).
Extends the AIDD framework with project-agnostic workflows: interactive codebase quiz (dig), memory maintenance (harvest, reconcile-normative), obsolescence detection (taste), prospective analysis (foresee), behavioural-test harness (behave), performance audits (data-optimize, web-optimize, ap-optimize), SEO/GEO audits (seo-optimize), project health reporting (status), and planning utilities (decompose, journey, changelog, end-plan). Alias chains: rechallenge, endtask, bump-plugin, previously, smarten, skillconf, weeklyemail, gitit, mirror.
PHP ecosystem skills: sniff, audit, improve, legacy, teach. design-bridge: réceptacle du pivot design (enforce → linter PHP/WP natif + pre-commit ; diffuse → block pattern WP + theme.json).
Design system funnel — 5-verb pipeline: define (extract tokens + component inventory from references or brief), destructure (challenge direction, propose alternatives), adjust (arbitrate + freeze 3-layer contract: tokens · components.json · charter), enforce (portable linter derived from contract + pivot to sc-php/sc-js + 3 gates), diffuse (repeatable elements under lint gate, baseline HTML/CSS + pivot to sc-*). Adds the copycat agent (per-page mockup→contract reconciliation, fanned out by define over many pages), a cross-OS Python fidelity oracle (getComputedStyle per breakpoint), and a 2nd enforce gate (fidelity vs the resolved mockup, alongside the vocabulary lint). Replaces: setup, from-reference, from-brief, wireframe, component, audit, diagnose, refactor, export-wordpress.
Intelligent draw.io diagramming plugin with AI-powered diagram generation, multi-platform embedding (GitHub, Confluence, Azure DevOps, Notion, Teams, Harness), conditional formatting, live data binding, and MCP server integration for programmatic diagram creation and management.
Complete creative writing suite with 10 specialized agents covering the full writing process: research gathering, character development, story architecture, world-building, dialogue coaching, editing/review, outlining, content strategy, believability auditing, and prose style/voice analysis. Includes genre-specific guides, templates, and quality checklists.
TypeScript/JavaScript full-stack development with NestJS, React, and React Native
Complete AI coding workflow system. Self-correcting memory + persistent FTS5-indexed research wikis + auto-research loop + multi-LLM council on a single SQLite store. 33 skills, 8 agents, 22 commands, 37 hook scripts across 24 events. Cross-agent via SkillKit.
Open-source, local-first Claude Code plugin for token reduction, context compression, and cost optimization using hybrid RAG retrieval (BM25 + vector search), reranking, AST-aware chunking, and compact context packets.