MatrixFounder
UserA robust agentic workflow for LLM-based development. Features role-based orchestration (Analyst, Architect, Developer), strict Stub-First methodology, and automated TDD/VDD cycles.
Categories
Indexed Skills (68)
architecture-format-extended
Extended architecture templates with full examples. Imports architecture-format-core for base structure.
light-mode
Guidelines for fast-tracking trivial tasks (typos, UI tweaks, simple bugfixes).
brainstorming
Use when brainstorming ideas, exploring solutions, generating options, clarifying requirements, designing architecture, or answering open-ended "how should we" and "what are the options" questions — even without the word "brainstorm".
architecture-design
Guidelines for designing scalable and modular system architecture.
architecture-format-core
Core structure for Architecture documents. For full templates with examples, load architecture-format-extended.
core-principles
Fundamental principles of agentic development: atomicity, traceability, stub-first, minimizing hallucinations.
developer-guidelines
Guidelines for the Developer role: strict adherence, no unsolicited refactoring, documentation, security.
documentation-standards
Standards for code documentation, comments, and artifact updates.
known-issues-format
Use when creating, formatting, or adding an entry to a project's thin-index ledger — `docs/KNOWN_ISSUES.md` + `docs/issues/` for defects, or `docs/BACKLOG.md` + `docs/backlog/` for work-items — or seeding either in a new project: shared index-over-records mechanics, per-registry frontmatter schema, prefix→category table, status/severity/effort vocab, index-line format, record-file recipe.
run-feedback
Use when a run of a workflow, skill, command, or test produced errors or friction worth keeping, or when executing the end-of-run Retro Global Protocol — collect findings into the feedback inbox, triage them (defect / work-item / noise), and file defects into the known-issues ledger or work-items into the backlog. NOT for fixing already-filed issues (/heal-issues). Triggers: "собери фидбек по прогону", "file run errors", "retro this run", "/run-feedback".
security-audit
Use when performing security vulnerability assessment (OWASP, secrets, dependencies, IaC, LLM, API, MCP/agentic) or when "thinking like a hacker" to find exploits.
skill-adversarial-performance
Performance critic in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
skill-adversarial-security
Use when performing OWASP security critique in adversarial style (optional sarcastic skin). Part of VDD Multi-Adversarial pipeline.
skill-archive-task
Complete protocol for archiving TASK.md and PLAN.md (lockstep) with ID generation. Single source of truth for archiving.
skill-orchestrator-patterns
Stage Cycle pattern and dispatch table for Orchestrator compression. Defines common Init→Review→Revision flow.
skill-parallel-orchestration
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.
skill-phase-context
Skill loading tiers: TIER 0 (always), TIER 1 (phase-triggered), TIER 2 (extended). Defines when to load which skills.
skill-product-analysis
Guidelines for creating and refining Product Vision and Strategy.
skill-product-handoff
Guidelines for managing the Product-to-Technical handoff, including Quality Gates and BRD Compilation.
skill-product-solution-blueprint
Guidelines for creating Solution Blueprints (UX Flows, ROI, Risk Registers) for BRD preparation.
skill-product-strategic-analysis
Guidelines for conducting Market Research (TAM/SAM/SOM) and Competitive Analysis.
skill-reverse-engineering
Regenerate architecture documentation from codebase analysis.
skill-safe-commands
Centralized list of commands safe for auto-execution without user approval. Single source of truth.
skill-self-improvement-verificator
Meta-skill for verifying Framework Upgrades (Gemini Self-Improvement).
skill-session-state
Persist and restore agent session context (Mode, Task, Summary) to survive resets.
skill-update-memory
Auto-update .AGENTS.md files based on code changes.
tdd-strict
Use when high-assurance reliability is required (Bug fixes, Critical Features, Quality Hardening).
architecture-format
Standard structure and templates for Architecture documents (docs/ARCHITECTURE.md).
architecture-review-checklist
Detailed checklist for verifying System Architecture and Data Models.
code-review-checklist
Structured checklist for code review: bugs, style, performance, security, docs.
plan-review-checklist
Detailed checklist for verifying Development Plans.
skill-spec-validator
Validates conformance between TASK.md (RTM) and PLAN.md (Atomic Checklists).
task-review-checklist
Detailed checklist for verifying Technical Specifications (TASK).
artifact-formalizer
Use BEFORE authoring a specification (TASK, ARCHITECTURE, PLAN, task files, issue records), a CHANGELOG entry or release notes, and AFTER to audit one that reads as an essay: long sentences, evaluative words, maxims, personification, metaphors, reasoning inside requirements, emoji as severity. Self-probing scanner; never changes the document's language. Triggers: «формализуй задачу», «проверь регистр», «напиши CHANGELOG», "formalize this spec", "reads like an essay", "write the spec", "release notes".
skill-creator
Use when creating new Agent Skills, upgrading existing skills, running evals to test a skill, benchmarking skill performance, or optimizing a skill's description for better triggering accuracy. Guidelines for Gold Standard skill structures.
skill-enhancer
Use when you need to audit, fix, or improve an existing agent skill to meet Gold Standard compliance.
vdd-adversarial
Use when performing Verification-Driven Development with adversarial approach. Actively challenge assumptions and find weak spots.
hooks-creator
Use when the user wants to customize Gemini CLI behavior using hooks (events, blockers, loggers).
vdd-sarcastic
Use when performing VDD adversarial review with an opt-in sarcastic, provocative delivery style — a stylistic skin over vdd-adversarial mechanics (exhaustive reporting + objective bar).
docx
Use when the user asks to create, edit, convert, validate, preview, or password-protect Microsoft Word .docx documents. Triggers include "markdown to docx", "docx to markdown", "fill Word template", "accept tracked changes", "validate docx", "preview docx as image", "encrypt/decrypt docx", and related .docx round-trip or template-fill tasks.
html
Use when fetching a web page/URL or converting a saved .html/.htm/.mhtml/.webarchive to clean Markdown — an Obsidian web-clipper and a universal HTML acquisition + HTML→Markdown step that also feeds the pdf and docx skills. Triggers include "html to markdown", "url to markdown", "download this page", "save the html", "web page to obsidian", "webarchive/mhtml to markdown", "clip this article".
Use when the user asks to create, combine, split, preview, or extract content from PDF files. Triggers include "markdown to pdf", "html to pdf", "webarchive/MHTML to pdf", "export this deck to pdf", "mermaid in pdf", "math/LaTeX in pdf", "merge PDFs", "split a PDF", "extract text from pdf", "fill AcroForm", "preview pdf as image", and similar PDF generation, conversion, or manipulation tasks.
pptx
Use when the user asks to create, edit, convert, preview, clean, or password-protect Microsoft PowerPoint .pptx presentations. Triggers include "markdown to pptx", "pptx to markdown", "slides from outline", "mermaid in slides", "pptx to pdf", "slide thumbnails", "drop orphan slides", "OCR slide images", "encrypt/decrypt pptx", and related presentation or OOXML round-trip tasks.
summarizing-meetings
Use when summarizing meeting transcripts OR articles, papers, and threads into structured Markdown or wiki note-JSON. Model-agnostic meta-skill: auto-detects content type, selects a template, and produces a two-level pyramid (or opt-in structured note-JSON) optimized for people, AI agents, RAG, and Obsidian.
transcript-fetcher
Use FIRST for ANY request to transcribe a video/audio URL or get its subtitles, captions, or text — before yt-dlp, ffmpeg, or a manual whisper run. Returns clean plain text plus a JSON stat sidecar; uses embedded captions when present, else falls back to local ASR automatically. Sources: YouTube, Vimeo, X/Twitter (incl. Broadcasts/Spaces), Skool lessons, Yandex VH/Strm webinars. Also triggers on расшифровка, транскрипт, субтитры.
xlsx
Use when the user asks to create, transform, validate, chart, preview, or password-protect Microsoft Excel .xlsx workbooks. Triggers include "csv to xlsx", "recalculate this workbook", "scan formula errors", "add a chart to xlsx", "bar / line / pie chart over a range", "financial model in xlsx", "fix
brainstorming
Use when brainstorming ideas, exploring solutions, generating options, clarifying requirements, designing architecture, or answering open-ended "how should we" and "what are the options" questions — even without the word "brainstorm".
planning-decision-tree
Decision tree for breaking down tasks and prioritizing work.
requirements-analysis
Use when gathering and refining requirements into a structured TASK.
skill-planning-format
Standards for Development Plans (PLAN.md) and Detailed Task Descriptions (TASK.md).
skill-product-backlog-prioritization
Guidelines for managing and prioritizing the Product Backlog using WSJF.
skill-task-model
Standards for Technical Specifications (TASK) and Use Cases.
testing-best-practices
Guidelines for implementing effective and maintainable tests.
design-md
Use when authoring, auditing, or exporting a DESIGN.md design system — design tokens, tailwind config, deslopify a generic look, дизайн-система, фирменные цвета, единый стиль, извлеки палитру по скриншоту, derive one from a brief, or extract one from a codebase or its CSS.
marp-slide
Use when users request slide creation, presentations, or Marp documents. Creates professional Marp slides with 7 themes (default, minimal, colorful, dark, gradient, tech, business). Supports custom themes, image layouts, and "make it look good" requests.
mcp-builder
Guidelines for creating high-quality MCP (Model Context Protocol) servers. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
obsidian-cli
Use to DRIVE the running Obsidian desktop app from the shell via its official CLI: link-safe rename/move, typed properties, task toggles, daily-note capture, template insertion, Base queries, file-history restore, open notes/panes. Triggers: "rename/move the note", "open in Obsidian", "daily note", "set a property", "query the base", "restore a version", "obsidian cli". NOT for knowledge lookup — for anything ABOUT vault content use wiki-ingest query mode first.
post-writing
Use when the user asks to write, draft, or rewrite a post for social media (LinkedIn, Telegram, Blog) or wants content to be more engaging.
skill-auto-improve
Use when you want to automatically improve an artifact (a skill, prompt, command/workflow, or eval dataset) against a measurable metric — the orchestrator proposes one change at a time, scores it, and keeps it only if the metric improves, reverting otherwise. Vendor-agnostic (Anthropic / OpenAI / Gemini / local gateways).
skill-validator
Use when auditing a new or existing skill for security vulnerabilities, malware (bash scripts), and structural compliance.
text-humanizer
Use when a text needs to stop reading as machine-written, or when you need a reusable system prompt that writes that way. Humanize a draft, de-slop it, clean up the wording, or audit it for AI phrasing. Covers requests like "make this sound like a person wrote it" or "убери признаки, что писал AI". Non-fiction only, never a short story, a novel chapter or a screenplay.
wiki-ingest
Use when ingesting a source (transcript, article, summary, meeting note) into an Obsidian-style llm-wiki, or maintaining one. Four modes: ingest (delegate to `summarizing-meetings`, upsert concept/entity pages additively, flag contradictions, update index.md and log.md), lint (orphans, dangling links, missing pages, contradictions), reindex (rebuild index.md from disk, preserve custom sections), query (keyword-find + cite). Triggers: ingest into wiki, register summary, lint, reindex, search notes, compound notes, llm-wiki.
hooks-creator
Use when the user wants to customize Gemini CLI behavior using hooks (events, blockers, loggers).
skill-enhancer
Use when you need to audit, fix, or improve an existing agent skill to meet Gold Standard compliance.
vdd-adversarial
Use when performing Verification-Driven Development with adversarial approach. Actively challenge assumptions and find weak spots.
vdd-sarcastic
Use when performing VDD adversarial review with an opt-in sarcastic, provocative delivery style — a stylistic skin over vdd-adversarial mechanics (exhaustive reporting + objective bar).
tdd-stub-first
Test-Driven Development with Stub-First approach.
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.