scitex-ai

Master index of all available skills for development workflows. Use when needing guidance on which skill to apply or when starting work on any project.

Master index of all available skills for development workflows. Use when needing guidance on which skill to apply or when starting work on any project.

Autonomous work mode — never ask user to run commands, never stand by, always take next action. Use when working independently on tasks.

Claude Code setup and configuration reference. Skills, commands, hooks, MCP servers, CLI, and permissions.

Code audit, cleanup, refactoring, API minimization, test review, examples, and project evaluation. Use when reviewing code quality or preparing for release.

Core development philosophy including development cycles, naming conventions, architectural decisions, and multi-agent workflows. Use when establishing project foundations or making architectural decisions.

Inspect DOM elements via playwright-cli eval for autonomous CSS/layout debugging.

Emacs Lisp development best practices including file templates, project structure, testing, and coding style. Use when writing Emacs Lisp packages or configuration.

[WHAT] Persistent, auto-reconnecting SSH reverse tunnels for NAT traversal — installs an `autossh` systemd unit on the local host so a bastion/relay server can SSH back in even through firewalls and dynamic IPs. [WHEN] Use whenever the user asks to "set up a reverse SSH tunnel", "keep SSH alive through NAT", "access a lab machine from outside", "tunnel through a bastion", "autossh systemd service", "check tunnel status", "remove a tunnel", "expose this machine via a jump host", or mentions bastion server, NAT traversal, autossh, reverse SSH, HPC login node. [HOW] `pip install scitex-ssh` then `import scitex_ssh`; see leaf skills for details.

Master index of all available skills for development workflows. Use when needing guidance on which skill to apply or when starting work on any project.

Core development philosophy including development cycles, naming conventions, architectural decisions, and multi-agent workflows. Use when establishing project foundations or making architectural decisions.

Emacs Lisp development best practices including file templates, project structure, testing, and coding style. Use when writing Emacs Lisp packages or configuration.

General programming best practices applicable to all languages. Covers clean code, testing, refactoring, version control, and development workflows. Use when writing or reviewing code in any language.

Project organization, multi-agent coordination, bug reporting, feature requests, and documentation practices. Use when managing projects, coordinating work, or organizing development workflows.

Python development for scientific computing and SciTeX projects. Includes testing, debugging, ML practices, and environment management.

Apply rigorous scientific writing standards for academic manuscripts. Use when writing abstracts, introductions, methods, results, or discussions for papers, grants, theses, or mermaid figure.

[WHAT] Scitexification — the verb: translate existing code (a script, a notebook, a small repo, a published-paper supplement) into SciTeX form so it gains the ecosystem's session-managed I/O, scitex-clew evidence binding, publication-quality figures, and project structure. Single source of truth for the migration act itself, package-agnostic; per-package patterns delegate to the per-pkg SKILL.md, and Clew-specific specialization layers on top of this skill via `scientific/04_clew_*`. [WHEN] You have existing code that works and want to bring it into the SciTeX ecosystem with minimal rewrite, OR an agent is asked to translate a research capsule, paper supplement, or one-off notebook into a SciTeX project. Load this skill BEFORE picking the per-chapter topic. [HOW] Read this SKILL.md first to orient on the 5-stage translation arc; then drill into the topic chapter you need next (`01_io-patterns`, `02_session-config`, `03_plt-patterns`, `04_repro-clew`, `05_naming-and-numbering`). Per-package details (full stx.i

[WHAT] Scientific-methodology skills for the SciTeX ecosystem — publication-quality figures, statistics, experiment reproducibility. Distinct from `general/` (which covers package engineering) and per-package skills (which cover package-specific APIs). Load when authoring analysis scripts, preparing figures for manuscripts, or checking scientific rigour of ecosystem output. [WHEN] Authoring analysis scripts, preparing figures or PDF reports for manuscripts, or auditing scientific outputs of any ecosystem package. [HOW] Read SKILL.md as the index, then drill into the numbered sub-skill leaves (`01_figures_*`, `02_research-project_*`, `03_reporting_*`) for the relevant topic.

[WHAT] Developer utilities for maintaining the whole SciTeX ecosystem across ~15 packages — version audit and mismatch fixing, editable-install sync, per-host git pull/commit/diff via SSH, bulk rename across files + contents + directories + symlinks (with git-safety guards), aggregated docs search across all packages, a Result/ErrorCode envelope shared by CLI + MCP, DevConfig/HostConfig, a local +… [WHEN] Use whenever the user asks to "list scitex versions", "check for version mismatches", "fix version drift", "rename old_name → new_name across all files", "sync my changes to the HPC / laptop / servers", "run tests on the HPC via Slurm", "poll my sbatch job", "fetch HPC test output", "search the docs for save_fig", "commit remote changes on gpu01", "pull all repos", "audit the ecosystem before a… [HOW] See sub-skills index for entry points.

[WHAT] Canonical engineering standards every `scitex-*` package and research project must follow — 3-layer architecture cascade, dependency/version pinning, local-state directory layout (`~/.scitex/<pkg-short>/` and `<project>/.scitex/<pkg-short>/`), repo layout (src/tests/scripts/examples), the five interfaces (Python API → CLI → MCP → Skills → optional HTTP) with their delegation rules and the noun-verb CLI convention, README/Sphinx docs, version-control workflow plus `scitex-dev ecosystem …` release automation, skill-authoring rules (layout, editable-vs-wheel install, public-vs-private), and the periodic quality checklist. Use as the single entry point for creating, auditing, reviewing, or releasing any SciTeX package. [WHEN] Creating, auditing, reviewing, or releasing any SciTeX package, or onboarding a research repo to ecosystem standards. [HOW] Read SKILL.md as the index, then drill into the per-category sub-dirs (`01_ecosystem/`, `02_package/`, `03_interface/`, `04_docs/`, `05_development/`, `09_qualit

[WHAT] AST-based linter for reproducible-research Python — 47 built-in rules across 7 categories: STX-I (imports), STX-IO (forbid raw pd.read_csv / np.load / pickle / fig.savefig — use scitex.io.save / scitex.io.load instead), STX-P (path handling — resolve via scitex.path, no hardcoded `/home/...`), STX-PA (plot/axes), and more. [WHEN] User asks to lint scitex code, check scitex conventions, list linter rules, show STX-IO001 meaning, or enforce reproducible-research style; mentions STX-*, scitex-dev linter, scitex conventions, reproducibility lint. [HOW] `scitex-dev linter check <path>` (CLI) or `scitex_dev.linter.check(path)` (Python). Hook integration auto-runs on PreToolUse for Edit/Write.

ALWAYS invoke this skill when the user wants to navigate websites, fill forms, take screenshots, test web UIs, extract page data, or debug frontend behavior. Do not spawn browser automation without loading this skill first.

ALWAYS invoke this skill when the user creates, edits, optimizes, benchmarks, or evaluates a Claude Code skill, or asks to improve a skill's activation rate. Do not write or modify SKILL.md files without loading this skill first.

ALWAYS invoke this skill at the start of any task to pick the right specialized skill. Do not begin development work without consulting this master index first.

[WHAT] Project scaffolding cloner + code snippet library for the SciTeX ecosystem — 6 templates (pip-project, minimal, cloud-module, research, singularity, paper) vendored in a single monorepo and populated into user targets via a `~/.scitex/template/cache/` shallow-clone. [WHEN] Starting a new SciTeX-flavored project (pip package, research repo, paper, container, or cloud module) and you want the canonical layout. [HOW] `scitex-template clone <id> <target>`, or `from scitex_template import clone_template_from_cache`. MCP: `template_clone`, `template_list`.

Template for new Python packages — clone and customize for a FastMCP-ready pip package with agentic (planning + TDD) workflows. Use when bootstrapping a new Python library from this template.

Template for research projects using the SciTeX framework — clone and customize for reproducible experiments, manuscript writing, and publication-ready figures. Use when starting a new SciTeX-based research project.

Standard template for scientific research projects using the SciTeX framework. Provides reproducible experiment tracking, automated data management, manuscript writing, and publication-ready visualization.

Master index of all available skills for development workflows. Use when needing guidance on which skill to apply or when starting work on any project.

[WHAT] SciTeX Hub operational surface — 55 MCP tools across 6 categories — project_* (cloud project CRUD), repo_* (self-hosted Gitea clone/push/pull/PRs/issues), cloud_sdk_data/files/jobs_* (DataStore/FileVault/JobQueue SDK — submit compute jobs, upload/download files, CRUD records), api_* (Scholar paper search, CrossRef lookup, BibTeX enrichment, LaTeX compile via cloud), app_* (install/switch app plugins), onsite_* (in-browser Playwright on the live Django site). [WHEN] Use whenever the user asks to create a cloud project, push/clone via Gitea, submit a cloud job, upload to FileVault, compile LaTeX on cloud, search papers via Scholar, enrich BibTeX, switch app plugin, deploy to staging/production, or mentions SciTeX Hub, Gitea, DataStore, FileVault, JobQueue, CloudClient. [HOW] `pip install scitex-hub` then `import scitex_hub`; see leaf skills for details.

SciTeX Hub web service integration — health monitoring, web app context, JavaScript evaluation, and browser UI control. Module-level helpers wrap CloudClient.

Mark functions as SciTeX workspace modules with the @module decorator and collect structured outputs. Canonical home — the umbrella scitex.module re-exports from here.

SciTeX Hub project management — CRUD plus secure MCP handlers for list, read, write, search, and execute within project sandboxes.

[WHAT] Umbrella package that lazy-re-exports every standalone SciTeX sister package (io, plt, stats, scholar, writer, cloud, container, ...) under one `import scitex` namespace. [WHEN] Use when the user wants the all-in-one entry point, or asks for `import scitex`, `scitex.io`, `scitex.plt`, `@scitex.session`, or any `scitex.<sub>` access; defer to the relevant sister-package skill for sub-module specifics. [HOW] `pip install scitex` then `import scitex`; sub-modules load lazily on first attribute access (see `src/scitex/__init__.py`).

Command-line interface for SciTeX platform operations — 30+ subcommands with lazy loading. Specialization of scitex-cli-convention.

[WHAT] Declarative YAML AI-agent lifecycle — define an agent in one `spec.yaml`; `sac agents start` runs it as a long-lived Claude SDK session inside Apptainer, with A2A inbound (`POST /v1/turn`), SSH remote deploy, JSON status. [WHEN] Launching/managing a Claude Code agent or fleet, running one on a remote host, wiring MCP, talking over A2A, or any mention of `sac agents start`, `scitex-agent-container`, `spec.yaml`, fleet head/worker. [HOW] `pip install scitex-agent-container`, then `sac agents start <name>` or `import scitex_agent_container`.

[WHAT] Project-specific context and reusable knowledge for this agent — coding conventions, tool usage patterns, domain vocabulary. [WHEN] Always loaded at agent startup; provides background the agent needs to work effectively in this codebase. [HOW] Place one `.md` file per topic in this directory; each file is loaded into the agent's context via the skills system.

[WHAT] Publication-ready matplotlib figures with mm-precision layouts, YAML recipes, declarative specs, multi-panel composition, whitespace cropping, style presets (SCITEX, MATPLOTLIB), and box-and-arrow diagrams. [WHEN] Use when the user asks to "make a figure", "plot this data", "save a figure", "lay out panels at exact mm sizes", "compose panels A/B/C", "crop whitespace", "reproduce a figure", "plot mean ± CI", "confusion matrix", "raster plot", "apply SCITEX style". [HOW] `import figrecipe` for the Python API; see leaf skills for entry points.

Master index of all available skills for development workflows. Use when needing guidance on which skill to apply or when starting work on any project.

[WHAT] Media handling for SciTeX — detect file paths in text (render.detect), classify a file by media type (render.classify), and render a file to terminal/chat/markdown (render.show). [WHEN] Scanning tool output for produced figures/data files, deciding how to display a file inline (terminal OSC overlay, AI chat pane, or markdown embed), or mapping a filename extension to a media category. [HOW] `from scitex_etc.media import render` — call `render.detect(text, root_path=...)`, `render.classify(path)`, or `render.show(path, target=...)`.

[WHAT] Miscellaneous SciTeX utilities — wait_key(p) blocks until 'q' pressed (terminates a process), count() prints an incrementing counter forever. [WHEN] Pausing a script until 'q' is typed to cleanly terminate a background process, implementing a simple counter loop with injectable test seams, or needing unbuffered keypress reading. [HOW] `from scitex_etc import wait_key, count` — call `wait_key(p)` to block on a process until 'q', `count(...)` to start an infinite counter.

[WHAT] Offline, zero-API-key DOI lookup + full-text search over the CrossRef corpus. [WHEN] Use when the user asks to "look up a DOI", "resolve DOI to BibTeX", "find a paper by DOI", "enrich BibTeX with missing fields". [HOW] `import crossref_local` then call `habanero.Crossref()`.

[WHAT] End-to-end LaTeX manuscript toolchain — 44 MCP tools — project (clone/info/get_pdf), compile (manuscript / supplementary / revision with tracked changes), BibTeX (add/list/get/remove/merge, dedup by DOI), figures + tables (add/list/remove/archive, csv_to_latex, pdf_to_images), claims (`\vclaim{}` linked to scitex-clew session hashes for verifiable assertions), checks (float order, references), export + Overleaf migration, per-journal guidelines, AI2 Asta prompts. [WHEN] Use whenever the user asks to compile manuscript / build PDF / supplementary / revision with tracked changes, add figure/table/bibentry, merge or dedup . [HOW] `pip install scitex-writer` then `import scitex_writer`; see leaf skills for details.

[WHAT] Offline, zero-API-key search over the full OpenAlex academic corpus. [WHEN] Use when the user asks to "search papers", "find literature on X", "look up a DOI", "get metadata for this paper", "enrich these OpenAlex IDs", "batch-resolve DOIs to BibTeX", "search by title/abstract/author". [HOW] `import openalex_local` then call `openalex_local.search(...)`.