opum-output-styles
claudecodexOriginal Claude Code output styles from Opum AI. Ships "Show Your Checks": a reporting style that marks every claim as verified, inferred, or unchecked, instead of presenting all three with the same confidence.
Claude Code and Codex plugins their authors filed under "productivity". All categories.
Original Claude Code output styles from Opum AI. Ships "Show Your Checks": a reporting style that marks every claim as verified, inferred, or unchecked, instead of presenting all three with the same confidence.
Internal toolkit for image generation, landing page factory, and development workflow commands.
Metacognition layer for prompt capture, pattern extraction, and system design methodology.
Interactive day and week planning with Eisenhower matrix prioritization, time-blocking, and Jira/GitHub integration.
Voice announcements, AI-powered session logging, and auto-commit with Conventional Commits
Generic personal toolkit. v0.1.0 ships the secrets category — dotenvx-based secret management with hierarchical .env resolution (home → project), single-master-key model, JSON export/import for vault round-tripping, and a one-shot keychain → dotenvx migrator.
Wraps the ai-pkm CLI as a Claude Code plugin — query, ingest, lint, and inspect a personal knowledge wiki via slash commands and an auto-triggering skill.
Attach Claude Code to a live audio meeting transcript — tools, curated /mcp__steno__* prompts, subscribable transcript resource, and the experimental claude/channel capability for ambient push reactions to committed utterances. Pairs with the steno macOS daemon.
Standard artifact set for backend engineers: code review plus the deployment workflow. Install this when you join a backend team.
The baseline set of AI artifacts every engineer at the company gets by default. Install this first; team-specific packs build on top of it.
A website factory: drives a site idea from an empty directory to a published GitHub Pages site through gated stages — brief with a page inventory as definition of done, a human-gated design.html mock, a verified scaffold (lean-Jekyll or Astro+React-islands) with a Playwright shots harness, then a build → shoot → judge → refine loop where independent visual and editorial agents critique the rendered pages and the prose, capped rounds, human feel check, publish stage. A retro skill closes the outer loop in both directions: it mines the run journals of generated sites for fixes that recur and proposes concrete edits to the factory itself, then replays today's hardened floor against sites generated before it existed. Carries craft knowledge (typography, palette, Jekyll conventions, content pipelines, Astro islands) extracted from ~25 hand-built sites. Sibling of first-factory and demo-factory.
Generate RenPy visual novels for desktop and browser: a brief with a branch outline and required paths, a native RenPy scaffold with save/load, menus and ending galleries, and a write, test, review and refine loop with independent editorial review. Optional scene art uses the Polyptych narrative pipeline through three human gates. Build desktop applications and a browser/PWA release from the same story, with optional GitHub Pages publishing.
Progressive linting system with directory-chunked baselines, drift detection, and auto-healing for monorepo projects (Python + JS/TS)
Eliminate context rot in Claude Code with intelligent memory, auto-learning hooks, and specialized subagents
Autonomous task execution with loop engine, orchestrated subagents, context persistence, and intelligent failure recovery. Includes bundled aeon-flux bash-loop mode.
Plan feature work with an appropriate verification strategy; use when a feature plan is requested.
Core posture and writing/policy craft: execute-first, MCP-first, host URLs, STE/writing skills. Pair with business-analyst for planning and code for coding work (incl. Conventional Commits).
Coding standards and workflow: language rules (incl. YAML/Kubernetes); React/Next.js/Flask/FastAPI; Conventional Commits; refactor/debug/verify skills; worktrees, merge conflicts; coding agents.
Business analysis and planning: BA brief skill, planner for ambiguous multi-step work, and external researcher. Pair with global (posture) and code (implementation).
No description.
AI skill for generating Business Model Canvas (Osterwalder/Strategyzer) visualizations. Works with Claude Code, Cursor, Codex, and 38+ AI tools via npx skills add.
Run a multi-model AI council on any question. Get responses from ChatGPT, Claude, Gemini and more — then receive a synthesized verdict, plus a full workspace (Kanban, Gantt, presentations, specs).
No description.
Add Spanish dashboard version (ecc_dashboard_es.py)
No description.
No description.
Policy-bound IconPark selection for humans and AI agents.
No description.
No description.
QuotaKeeper protects long-running Codex Goals from exhausting your Codex quota