AI & ML

matrixfounder Bundle

Guidelines for managing the Product-to-Technical handoff, including Quality Gates and BRD Compilation.

matrixfounder Skill

Detailed checklist for verifying Technical Specifications (TASK).

matrixfounder Skill

Decision tree for breaking down tasks and prioritizing work.

matrixfounder Bundle

Guidelines for creating and refining Product Vision and Strategy.

matrixfounder Bundle

Guidelines for implementing effective and maintainable tests.

matrixfounder Bundle

Standards for code documentation, comments, and artifact updates.

matrixfounder Skill

Core structure for Architecture documents. For full templates with examples, load architecture-format-extended.

matrixfounder Bundle

Regenerate architecture documentation from codebase analysis.

matrixfounder Skill

Stage Cycle pattern and dispatch table for Orchestrator compression. Defines common Init→Review→Revision flow.

matrixfounder Bundle

Use when decomposing tasks into parallel sub-tasks or spawning sub-agents. Vendor-agnostic core; load a per-vendor reference for concrete tool names, directory conventions, and invocation syntax.

matrixfounder Skill

Detailed checklist for verifying System Architecture and Data Models.

hiroro-work Skill

Methodology for iteratively improving agent-facing instructions (skills / slash commands / CLAUDE.md / code-gen prompts) by having a bias-free executor run them and evaluating two-sidedly (executor self-report + instruction-side metrics) until improvements plateau. Use after creating or revising a prompt or skill.

matrixfounder Bundle

Guidelines for creating Solution Blueprints (UX Flows, ROI, Risk Registers) for BRD preparation.

matrixfounder Bundle

Guidelines for conducting Market Research (TAM/SAM/SOM) and Competitive Analysis.

matrixfounder Bundle

Meta-skill for verifying Framework Upgrades (Gemini Self-Improvement).

markusstrasser Bundle

Use when: /eval, new benchmark/grader/judge, model bakeoff, auditing eval design. Pre-reg decision rule + power preflight. Modes: design, review. NOT spot-checks (/verify-before) or code diffs (/code-review).

markusstrasser Skill

Use when: parallel adversarial bug-hunt fan-out or pre-commit audit; scouts write files, orchestrator model triages. NOT a code-review scout (/code-review) or plan critique (/critique).

markusstrasser Bundle

Architecture/strategy decision arc — ground → diverge → cross-model critique → capture. For hard-to-reverse decisions (schema, breaking refactor, tech choice). NOT trivial (/critique) or ideation (/brainstorm).

modu-ai-cc-plugins Bundle

MoAI super agent - unified orchestrator for autonomous development. Routes natural language or explicit subcommands (plan, run, sync, fix, loop, project, feedback) to specialized agents. Use for any development task from planning to deployment.

mintuz Bundle

WHEN the immediately previous LLM response was unclear, too dense, or hard to follow; NOT for doing the work that response describes, and NOT for writing a new document from it; returns a plain UK English re-explanation that keeps every detail that changes how the response should be understood.

miroapp Skill

Use when authoring or revising plugin SKILL.md files in this repo. Captures the principles for keeping skills as compact shortcuts to MCP tool groups.

markusstrasser Bundle

Use when: /critique, 'review plan', 'what's wrong', fact-check plans/findings/closeout. Modes: model, verify, close. NOT code diffs (/code-review) — critique owns design/plan layer.

mintuz Skill

WHEN monitoring open PRs and issues as an agent inbox, or sending messages to other agents through GitHub, Forgejo, or Gitea comments; NOT for shipping code, reviewing diffs, or watching one PR's checks until it is green and merged (babysit); polls with gh or tea from one scripted cycle, routes messages addressed to this agent, and replies using a structured comment protocol.

mintuz Bundle

WHEN building ChatGPT apps using the OpenAI Apps SDK and MCP; NOT for OpenAI API chat completions, agent frameworks, or MCP servers with no ChatGPT widget; create conversational, composable experiences with proper UX, UI, state management, and server patterns.

markusstrasser Bundle

Use when: /brainstorm, divergent design space, denial/domain/constraint perturbation. Optional multi-model volume. NOT convergent review (/critique) or decisions (/decide).

markusstrasser Bundle

Use when: /llmx-guide, writing llmx calls, debugging llmx failures, or choosing model/provider. Python/Bash gotchas — flags, transports, subscription vs API.

markusstrasser Skill

Use when: ACS/CPS/IPUMS/QWI extracts, county/state aggregates, immigrant/earnings panels. Census API patterns. NOT generic dataset staging (/data-acquisition alone).

markusstrasser Skill

Use when: improving a gpt-image-2 prompt before generation. NOT scene injection (/person-into-scene).

markusstrasser Bundle

Use when: choosing frontier model/effort for a task class (Claude Opus 5, GPT-5.6 Sol/Terra/Luna, Kimi K3 open-weight coding opt-in, Grok 4.5 Cursor repo-review opt-in). Fable 5 METERED since 2026-07-07 (off subscription, 2× Opus) — fable lanes are paid opt-ins, and the Agent tool currently can't reach Fable at all (routing bug, see Verified Transport). NOT transport flags (/llmx-guide).

markusstrasser Skill

Use when: headless `agent` CLI from shell/CI/scripts, Composer install/auth/dispatch, or exact Cursor Grok 4.5 read-only repo review. NOT in-editor Cursor agent or llmx/claude-cli.

markusstrasser Bundle

Headless/scripted browser automation from Bash (Vercel Labs CLI, Rust/CDP). Use for navigating pages, filling forms, clicking, screenshots, scraping JS-rendered pages, testing web apps, Electron apps, or any programmatic web interaction — especially in subagents, scouts, launchd jobs, and autonomous runs where claude-in-chrome MCP is unavailable. NOT for the operator's logged-in Chrome session (use claude-in-chrome) or static fetches (WebFetch/Firecrawl).

markusstrasser Bundle

Use when: vendor/agent landscape scan, 'what's new', trending repos, weekly update check. Filtered vs known memos — NOT deep topic research (/research).

markusstrasser Skill

Use when: downloading/staging external data (Census, IPUMS, NCES, intel download scripts). Probe→stage→register. Then /dataset-register. NOT papers (/research).

markusstrasser Skill

Use when: after /data-acquisition, formalize staged dataset in topic catalog (provenance, variables, quirks). NOT downloading (/data-acquisition).

agentscope-ai Skill

Use this skill whenever the user needs ANY mailbox/email operation — checking, reading, searching, sending, replying, forwarding, organizing or deleting email, managing threads, connecting a personal mailbox, or registering a new mailbox. This skill is the single entry point for email tasks and orchestrates qwenpawmail-mcp for nine supported personal-mail domains.

markusstrasser Bundle

Architectural decision-making workflow using tournament-based proposal generation and ranking. Generates proposals from multiple LLM providers (google, openai, xai) via llmx unified CLI, ranks them via tournament evaluation, optionally refines with feedback loops, and records decisions as ADRs. Use when exploring architectural alternatives, comparing implementation approaches, or making significant design decisions. Requires API keys, Python 3.10+.