Recursively Self-Improving Module — persistent memory + structured improvement loop for Claude Code
This repository also configures its own agents. See what RSIm tells them →
Skill Claude CodeCodex
Breaks down complex projects into actionable tasks with timelines, dependencies, and milestones. Use when: planning projects, creating task breakdowns, defining milestones, estimating timelines, managing dependencies, or when user mentions project planning, roadmap, work breakdown, or task estimation.
Skill Claude CodeCodex
Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust, efficient, and maintainable Python applications.
Skill Claude CodeCodex
Purpose: Analyze completed session/project — creates /.claude/reflection.md as input for Improve. When: At end of each significant session. Required at project end. Output: /.claude/reflection.md (global, not in project folder) + entries in /.claude/memory/episodic/hard-problems.md for hard cases.
Skill Claude CodeCodex
Purpose: Collect local RSIm skill improvements (skills/ + commands/) and publish to GitHub as a PR. When: After improve cycles with accumulated skill changes. Auto-suggested after /improve. Reminded at session start if > 7 days since last export. Requirements: gh CLI installed and authorized (gh auth login), git…
Skill Claude CodeCodex
Purpose: Pull RSIm skill updates from GitHub releases and apply locally — with security scan and per-change approval. Preserves local memory/. When: Periodically to receive improvements. Reminded at session start if > 14 days since last sync. Requirements: gh CLI installed and authorized, git installed.
Skill Claude CodeCodex
Purpose: Onboarding and creation of product / portfolio guides from documents (docx, PDF, website). Fixed question checklist at start, vendor/product card template, final output as HTML/PDF. When: User wants to create a Sales Guide, Product Guide, Partner Catalog, or similar structured document from source materials.…
Skill Claude CodeCodex
Search the internet and news using a local SearXNG instance. Use when the user wants to search the web, find current information, search for news, or research a topic without depending on third-party APIs.
Skill Claude CodeCodex
Purpose: Add SECURITY section to project CLAUDE.md. Canary token, stop-ops, prompt injection signals — one command. When.
Skill Claude CodeCodex
Purpose: Create a new skill using the standard system template. When: Improve Skill proposes a new skill, or user wants to automate a recurring action. Output: Ready /.claude/skills/[name]/SKILL.md + row in /.claude/skills/index.md.
Skill Claude CodeCodex
Create new Claude Code skills with proper structure and best practices. Use when the user wants to create a new skill, extend Claude's capabilities, or needs help structuring a SKILL.md file.
Skill Claude CodeCodex
Manages context in long sessions by suggesting /compact at logical task boundaries — after research phases, debugging, or phase transitions. Prevents losing critical context mid-implementation.
Skill Claude CodeCodex
Purpose: Analyze a service or project at phase transitions — identify what's working, what's broken, and what to build next. Produces a prioritized feature roadmap grounded in real metrics. When: At phase transitions in plan.md, when metrics degrade, or when the backlog needs re-prioritization. Output: Structured…
Skill Claude CodeCodex
Purpose: Catalog of ready-to-use HTML/CSS/JS components for dashboard projects. Insert components directly — no reinventing each time. When: Building a dashboard, admin panel, or monitoring UI in plain HTML/CSS/Jinja2. Output: Ready CSS + HTML markup + formulas for each component.
Skill Claude CodeCodex
UI/UX design intelligence. 67 styles, 96 palettes, 57 font pairings, 25 charts, 13 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing…
Skill Claude CodeCodex
Purpose: Automatically check project CLAUDE.md for compliance with current intake standard. When: At session start when reading CLAUDE.md; after updating intake standard; before running reflect. Output: Report of issues found + offer to run migrate-claude-md if needed.
Skill Claude CodeCodex
Post-deploy verification of a deployed web application. Reads credentials from update.py, fetches key pages, checks HTTP status and expected HTML elements, outputs a pass/fail table.
Skill Claude CodeCodex
Scrape web pages, search the internet, and extract structured content using Python. Includes anti-bot/Cloudflare bypass via Scrapling. Use when the user wants to fetch a webpage, search for information online, extract links, crawl JS-rendered pages, or bypass bot protection.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: