mdeuerlein
Usercurated collection of reusable building blocks for AI agents
Categories
Indexed Skills (11)
adapt-agent-system
Adapts a project set up for one AI agent system to work with another supported system
ai-usage-report
Generates a self-contained HTML report on token usage and cost of the AI CLI tools (Claude Code · Codex · Hermes) for any time period — KPIs, cost/token donuts, agent cards, a breakdown table, and daily trend charts (line + stacked bar). Data comes live from ccusage (local transcripts). Trigger on requests like "ai usage report for June", "token report last 7 days", "how much did I spend on AI this month", "cost overview Claude/Codex/Hermes for [period]", or German equivalents like "ai usage report für Juni" / "token-bericht letzte 7 tage".
codebase-suite
Structured, phase-based workflow for analyzing, documenting, and preparing unfamiliar codebases. Read-only first, human checkpoints after each phase. Produces durable technical documentation (incl. architecture.md and important-files.md) in _docs/ as well as analysis artifacts in _docs/intake/, and optionally provides the documentation to AI agents via CLAUDE.md/AGENTS.md. Includes a refresh mode that re-verifies existing documentation claim by claim against the current code.
codeigniter-knowledge
CodeIgniter 4 framework knowledge base. Provides CI4 MVC architecture, DDD integration, persistence, services, security (Shield auth, Filters authorization, CSRF), event system, queue (codeigniter4/queue jobs, workers, retry), infrastructure components (cache, HTTP client, email, throttler), testing, and antipatterns for CodeIgniter PHP projects.
easypanel-nixpacks-deploy
Configures and repairs existing PHP web projects for deployments on Easypanel using the Nixpacks builder
git-release
Publish the current local dev branch changes as a new semantic version on GitHub. Use when Codex is asked to release local changes by inspecting git status, updating CHANGELOG and README, running available tests/checks, committing to dev, pushing dev, merging dev into prod, creating and pushing a semantic version tag, creating a GitHub Release, and returning the local checkout to dev after success. Includes careful stop conditions for merge conflicts, missing remotes, missing permissions, unclear version numbers, and destructive operations.
grill-me
Relentlessly interview the user to turn a vague idea or goal into clear, buildable requirements. First clarifies ambiguities, then challenges assumptions and probes for holes — one question at a time, each with a recommended answer. Use when the user says "grill me", wants to stress-test or sharpen a half-formed idea, or needs a vague concept turned into actionable requirements before building.
hermes-agent-setup
Installs, configures, updates, or troubleshoots Hermes Agent strictly grounded in the official documentation at hermes-agent.nousresearch.com — never from model memory. Use for any task involving Hermes Agent setup, config.yaml, providers, messaging platforms, MCP, skills, or CLI usage.
loomkit-build-persona
Combines a character and a role from the Loomkit into a finished, standalone system persona under a freely chosen name. Then either saves it to a folder of the user's choice (default agent-personas/my-personas/) or applies it to the current agent, adapted to the target system via agent-personas/systems/. Use this skill when the user wants to create or apply a new persona.
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
slidev-template-creator
Creates a reusable Slidev project template from an existing Slidev presentation via URL
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.