MasihMoafi/skills

logo

Generate logos, icons, ornaments, illustrations, badges and diagrams with the image tool, then keep the chosen artwork as real SVG paths through SVG Studio. Use for an image-first visual-to-SVG request or /logo.

artifact

Handling rules for visual and document artifacts: PDFs, HTML reports, dashboards, slides and formula rendering. Load when creating, editing, verifying, or opening any of these artifact types.

latex-authoring

Write, structure and compile LaTeX papers and reports (NeurIPS, ICML, ICLR, IEEE, ACM), including Persian and English XeLaTeX. Use for TeX manuscripts, LaTeX/XeLaTeX build errors, BibTeX checks or TikZ diagrams.

app-control

Drive a desktop Electron app (Elpis desktop, ChatGPT, Claude) as its user does, through its Chromium DevTools port: see, read, click, type. Use to try, test or compare app features first-hand. The Elpis TUI uses tmux instead.

first-principles

Use only when the user explicitly asks for a first-principles review of a product, requirement, workflow, or implementation: question the requirements, delete what should not exist, then simplify.

debugging

Use for any bug, failing test, crash or unexpected behaviour, before proposing a fix. Root cause first, one hypothesis at a time, and a stop after three failed fixes.

spec

Use for nontrivial implementation, requirements, a PRD or vision document, or acceptance criteria. Defines done before code. Not for trivial edits, exploration, spikes or prototypes.

tdd

Test-driven development: the agent writes the failing test, then the code, one behavior at a time. Use when building a feature or fixing a bug test-first, or when the user says tdd, red-green, or test-first.

experiment-workflow

Use when designing, running, or comparing a repeatable experiment where a decision question, controlled variables, baselines, measurements, and raw evidence matter. Not for ordinary unit tests or one-off checks.

multi-agent

Split work across agents without losing control, with one worktree and prompt file per task and a coordinator who integrates. Use when dispatching more than one agent or writing a brief for another agent.

project-docs

Use when entering an unfamiliar project, when creating or repairing a project's agent docs (AGENTS.md, feature map, lat.md folder map, VISION.md, ES.md), or when the workspace check reports doc problems.

reference-driven-product

Use when improving or rebuilding a product from a reference app, screenshots, user feedback, or open-source alternatives, when speed and a restart guide matter. Not for isolated bug fixes or purely visual imitation.

product-design

Use when shaping a new product, materially redesigning a user flow, choosing a web or app stack, or turning a product concept into an implementation-ready design.

test-audit

Invoke whenever writing, changing, reviewing, or sweeping tests: an authoring gate for new tests, an audit for low-value, implementation-coupled or duplicate tests, and layered verification for AI-generated code.

doc-style

Use when writing, reviewing or auditing a README, skill, specification, project page or launch material that must stay concise and evidence-backed, including "audit docs" and "prune AI self-talk".

clean-system

Reclaim disk space or clear the clutter Claude Code, Codex and Elpis leave (old chat logs, file history, logs, backups), or name or remove single sessions. Agent clutter goes without asking; caches and Docker need a yes.

contribution-checklist

Use when preparing or reviewing a contributor issue, call for participation, newsletter submission or related outreach, or answering a reviewer's feedback on one.

word-farsi-docx

Build a clean, editable Persian (Farsi) Word .docx in B Nazanin from a report, PDF or TeX source with python-docx. Use for Persian Word output, RTL or font problems in .docx, or converting a Persian report to Word.