Martin-Hausleitner

Use when discovering, verifying, or sharing SKILL.md based skills across local Hermes, Codex, OpenClaw, Gemini, OpenCode, Claude-adjacent, and generic agent skill roots without overwriting existing skills or leaking private paths.

Use when external services should trigger agent runs through webhook events

Use when GitHub authentication is missing, broken, or needed before repository, issue, pull request, or CI work

Use when triaging, creating, labeling, searching, or closing GitHub issues

Use when creating, updating, reviewing, testing, or merging a GitHub pull request

Use when reading, creating, updating, or organizing Notion pages and databases through the Notion API

Create interactive feature-comparison heatmaps that score, rank, and crown winners across multiple tools, repos, or products. Use this skill whenever the user asks to compare tools, software, GitHub repos, frameworks, extensions, or any set of alternatives across multiple features or criteria — especially when they want a visual matrix, heatmap, scorecard, ranking, or 'who wins' analysis. Also trigger when the user says things like 'compare features', 'which is the best', 'feature matrix', 'score them 1-100', 'rank these tools', 'Vergleich', 'Heatmap', 'wer gewinnt', or 'Gewinner küren'. The output is always an interactive React (.jsx) artifact with clickable GitHub/repo links, last-update dates, color-coded scores, sorting, and an automatic winner badge.

Review code changes by analyzing git diffs, leaving inline comments on PRs, and performing thorough pre-push review. Works with gh CLI or falls back to git + GitHub REST API via curl.

Use when turning finished AI research results into clear chat messages, copy-ready summaries, duration metrics, PSPin/deep-research links, and optional Notion pages without exposing private data.

Use when the user asks to compare products, tools, GitHub repos, packages, frameworks, guides, platforms, plugins, or alternatives with Deep Research. Produces a strict research prompt and output format with at least 10 candidates, ideally 50, clickable GitHub and website links, five use-case-specific scoring categories, a 100-point total score, ranking, diagrams, and recommendation tables. Trigger on "vergleichen", "compare products", "best packages", "best tools", "GitHub links", "score 100", "rank platforms", "beste Programme", "Plugins vergleichen", or any broad comparison request that should become a reusable Deep Research scorecard.

Use when running, debugging, or explaining the ai-research-browser CLI for real Browser/CDP AI-provider automation, including Brave/Comet live sessions, restart recovery, workflow-live-run, workflow-suite, Deep Research/Agent/image runs, rate-limit cooldowns, screenshots, clipboard output, and safe E2E evidence.

Discover local Brave, Comet/Komet, Chrome, or Edge profiles and run ChatGPT/Gemini research or agent workflows with hidden/headless launch arguments and screenshot-backed E2E records.

Use when validating Oracle 0.13 with ai-research-browser, workflow-run, GitHub public-safe proof, local Hermes skill installation, guarded ChatGPT/Gemini browser E2E, or reattach/status/session evidence.

Use when a script or agent needs to ask a human exactly one question and continue with a structured JSON answer. It is the human-in-the-loop bridge used by interactive/integrative deep research. Triggers: "ask the user and continue", "human-in-the-loop pause", "question bridge", "clarifying question step", "interactive prompt from a script".

Use during deep research and tool comparisons to turn researched candidates into a weighted Σ/100 ranking, crown one winner, and explain why the winner beats the runner-up. Triggers: "score the candidates", "punkte vergeben", "Sieger küren", "weighted comparison", "100-point scorecard", "rank tools and pick a winner with justification".

Use when the user wants a deterministic NotebookLM-backed deep research run with one human clarification step and a self-contained HTML report. The driver runs agy scoping, NotebookLM fast research, one askq/chat question, NotebookLM deep research on the same notebook, fixed topic-anchored query angles, and local report rendering. Triggers: "integrative deep research", "interactive deep research", "NotebookLM deep research with one question", "deep research HTML report".

Umbrella guide for the interactive deep-research system. Use when someone asks how the full system works, how to install it, how to run an end-to-end research with one human question, or how the idr, askq, and scorecard skills fit together.

Manager-only orchestration of a fleet of coding agents (Claude Code, Antigravity, Codex) running in watchable terminal sub-sessions. Use when acting as the orchestrator/babysitter: spawn and brief lanes, never do project work yourself, research-first (interactive deep research) before planning, and report to the operator in a fixed colour-coded line-based format. Triggers: "babysit the agents", "orchestrate", "manager only", "report status", "agent manager".

Reliably drive the operator's LOCAL cmux (Mac) from the manager session: show a markdown file / open a website / open a new terminal in a dedicated right-side "📄 preview" workspace, on command. Use when the operator says "show me <file>", "open <url>", "give me a terminal", or wants something displayed on the right.

Diagnose Sonar pairing failures between two iPhones — QR-scan path silent, Tailscale shown connected but inactive, peer never goes online, distance ring flickering. Use when the user reports "they don't see each other", "QR-scan does nothing", "Tailscale is green but no audio", or any pairing-related bug. Walks through the four connection paths (AWDL → BLE → Tailscale → Internet) and isolates the failing one against real symptoms in the current code.

Cut a new Sonar SideStore release. Use when the user says "publish", "ship", "release", "bump version", or wants the in-app SideStore Update button to surface a new build. Runs the validated `make publish` flow — bumps Info.plist, runs the iPhone 16 Pro test suite, builds an unsigned IPA, archives it under releases/, regenerates apps.json, commits, pushes, and creates a GitHub release.

Screenshot every Grafana dashboard in this repo's local stack and embed them as a gallery in the README. Use when the user asks to "screenshot the dashboards", "put the dashboards in the README", "update the dashboard gallery", "Dashboards in die Readme", "Screenshots von den Grafana-Dashboards", or to refresh the dashboard images after rebuilding. Handles starting the local stack, optional rebuild, robust capture, README injection, and an end-to-end test.

Use when the user says "EU Activate", asks to enable Codex Computer Use in the EU, asks to install or validate the bundled computer-use plugin, or needs a repeatable self-test proving SkyComputerUseClient MCP can control Finder or Notes.

Hard-critical Tribunal workflow for knowledge, critique, UI/UX, and comparison reviews using three isolated judges, Nx rounds, explicit provenance, and strict anti-fake gates.

Find, compare, and install agent skills across ClawHub and Skills.sh when the user needs new capabilities, better workflows, stronger tools, or safer alternatives. Use when (1) they ask how to do something, how to improve or automate it, or what to install; (2) a skill could extend the agent, replace a weak manual approach, or close a capability gap; (3) you need the best-fit option, not just a direct answer.

Operate and maintain the aw-importer-apple-screentime repository, an Apple iPhone Screen Time CSV/JSON to ActivityWatch importer. Use when an agent needs to parse Screen Time exports, dry-run or import app usage into ActivityWatch, verify Screen Time buckets, debug parser behavior, or change repository code/docs/tests.

Operate and maintain the aw-importer-whoop repository, a WHOOP to ActivityWatch importer. Use when an agent needs to set up WHOOP OAuth, create or validate WHOOP Developer Dashboard credentials, log in through the local OAuth callback, request or import WHOOP export ZIPs, run API syncs, repair ActivityWatch WHOOP buckets, debug importer behavior, or change repository code/docs/tests.

Use when installing, configuring, testing, backfilling, or troubleshooting aw-importer-youtube, the ActivityWatch importer for local YouTube watch sessions.