AI Agent Skills

Convert a PDF (or image/DOCX/PPTX/XLSX) to Markdown or plain text, via the deterministic Linux extract engine (pymupdf/pypdf; optional MinerU). Triggers when the user ty…

Senior-engineer code review across five domains — Code Quality, Security, Performance, Blueprint/Spec Consistency, and Test Quality — plus conditional lenses au

Keep USER-FACING documentation honest against the current codebase — README, docs/CODEMAPS/*, architecture-as-markdown, public API docs. Generates/refreshes cod

Device memory management for dpnp arrays on Intel CPUs and GPUs. Use when a dpnp script grows in memory until it fails, when a dataset does not fit in device me

Semi-automatic end-of-session ritual. Scans the session and machine for loose ends, presents ONE categorized report, and on approval executes cleanup + closing

Routes documentation work to the modernized Inside Macintosh skill set. Use when asked to write, plan, restructure, explain, document, or review APIs, SDKs, CLIs, framew…

Create a new specification document following the project's spec system templates and conventions. Use when adding a new domain, component, contract, architecture doc, o…

Customize Frappe Desk UI with form scripts, list view scripts, report scripts, dialogs, and client-side JavaScript APIs. Use when building interactive Desk experiences,…

Create reports in Frappe including Report Builder, Query Reports (SQL), and Script Reports (Python + JS). Use when building data analysis views, dashboards, or custom re…

Reverse-engineers existing source code into a two-layer artifact ladder — a concrete reproduction spec (preserves behavior-affecting constants, same-tick ordering, input…

WeChat official account (公众号) article writing. Use when the user asks 公众号/公众号文章/爆文/写公众号/改公众号/去AI味/封面提示词/标题/微信排版/转微信格式, or pastes source material and wants it turned into…

Assess agent code, changes, traces and evaluations; report findings and prepare missing evals only with confirmed authorization.

Read-only data quality audit of the connected CRM - field completeness per mapped property, duplicate candidates, stale records, enrichability estimate. Produces a repor…

Use when named or when the user requests additional context for code review. Review Bitbucket/GitHub PRs or local changes using TWG context, create JSON and Markdown, an…

Careful bibliography verification and entry-addition for papers — verify every author, title, journal, volume, pages, year, arXiv ID, and DOI against authoritative onlin…

Use before circulating any outward-facing scientific document — simulate the strongest standard objection from every audience it claims and verify the document answers e…