skills

native microsoft excel automation for windows .xlsx/.xlsm/.xls/.csv/.tsv workflows. use when chatgpt, codex, or claude code is running on windows with microsoft 365 excel installed and needs to refresh, recalculate, validate, or route a workbook through excel com automation. trigger for workbook connections, cached values, pivottables, calculation correctness, refreshing an existing power query connection, data model-aware routing, chart-ready data, no-template spreadsheet deliverables, or excel environment self-test. does not support authoring or editing power query m code, or macro execution -- see "known gaps" below. do not use for cloud execution, non-windows environments, google sheets api workflows, or machines without excel desktop installed.

Archived. Do not install or invoke for Claude Code or Codex GPT-5.6 Sol. Use the repository's scaffolds/agent-project-scaffold for the maintained scaffold or native Codex planning and execution controls.

Create a comprehensive project archive and handoff package — curated workfolder copy, evidence and state, agent context, and dark-mode HTML memo — from Claude Code or Codex projects. Use for milestone archives, cold-start continuation packages, or comprehensive handoffs; use a lightweight session-handoff skill for a short continuation note.

use only in Claude Code as an explicit provider router when Graphify, code-mapper, or selective CodeQL availability must be assessed. do not install or auto-trigger for Codex GPT-5.6 Sol; native direct inspection, Plan Mode, explorer work, and subagents cover this routing without an added analyzer.

Generate deterministic Python import, reference, artifact, contract, catalog, OpenLineage, and explicitly authorized local CodeQL maps. Use for explicit Python blast-radius, callers, inputs/outputs, APIs/schemas, Backstage relationships, lineage, or local value/taint evidence; do not use for ordinary code search, broad repository exploration, or simple edits.

Deprecated for GPT-5.6 Sol. Use native Codex Plan Mode, with focused verification or adversarial review skills when needed.

Use when Codex is building, revising, or reviewing a frontend UI, web app screen, responsive layout, component surface, dashboard view, form flow, visual system, or no-template product interface that needs visual polish, accessibility, screenshots, or browser QA.

windows powerpoint automation and no-template deck design support for .pptx files in codex app or other local windows environments with microsoft 365 installed. use when chatgpt needs to open, inspect, edit, create, render, export, or qa powerpoint presentations on windows, especially new decks without a template, existing deck edits, speaker notes, slide images, pdf export, placeholder replacement, visual QA, or smoke testing via native powerpoint com automation. prefer this skill over libreoffice-based flows when powerpoint desktop is available.

Deprecated for GPT-5.6 Sol. Native Codex Plan Mode performs read-first repository grounding and evidence collection.

Deprecated for GPT-5.6 Sol. Use native Codex Plan Mode for grounded, decision-complete implementation plans.

Use when Codex needs to create, run, package, revise, or verify a standalone web artifact such as an HTML report, dashboard, microsite, interactive explainer, data story, or browser-delivered deliverable with runtime, screenshots, console capture, and evidence packaging.

Use when a plan needs hostile review before execution, especially high-risk coding, business deliverables, migrations, no-git changes, weak validation, stale assumptions, rollback gaps, or plans that must be safe for another agent to execute.

Use when the user says grill me, wants to stress-test a plan or design, needs a rigorous interview before committing to a decision, or asks for adversarial product, architecture, or implementation questions.

Use when the user wants to stress-test a plan against project terminology, domain language, CONTEXT.md, ADRs, existing docs, or code-backed architectural decisions.

Use when the user asks for a handoff, session summary, context packet, continuation note, or wants another agent or future session to pick up the current work.

Use when a plan needs proof criteria before execution, especially coding changes, business deliverables, mixed business-coding projects, acceptance criteria, rollback triggers, manual checks, or final validation design.

native microsoft word automation for windows .docx workflows. use when chatgpt or codex is running on windows with microsoft word installed and needs to create, edit, review, convert, or verify word documents through word com automation. trigger for .docx or .doc requests, professional word deliverables, no-template document polish, tracked changes, comments, find and replace, table of contents, headers and footers, page numbering, layout-sensitive edits, or exporting a word document to pdf for review. prefer this skill over libreoffice-based document workflows when word is available.

Use when Codex needs to build, revise, debug, or verify canvas, SVG, WebGL, Three.js, custom charting, diagram, game, generative visual, or pixel-based browser artwork where screenshot, pixel, animation, or image bounds evidence matters.