Use this skill whenever you change the shape of the 0.5 backend database — a new table, a new column, an index, a constraint, a backfill, or a data reshape. It owns the authoring contract (one numbered .sql file under services/platform/backend/db/migrations/, applied at boot in filename order inside one advisory…
Use this skill whenever you write or edit end-user documentation — a page under a docs content tree, a docs navigation or sidebar file, a docs landing or overview page, a screenshot or code example embedded in docs, or a failing docs structural check. It owns the journey-first method — organize every page around what…
Use this skill whenever you edit any non-English file under services//messages/ (e.g. de.yml, fr.yml), packages/ui/src/i18n/messages/, or any page under docs/ /, add a locale, or touch a glossary term — Tale ships as one narrator written natively per language, never a word-for-word render of the English. Load it…
Runs after a tool call finishes for Edit, Write and mcp__pencil__batch_design tool calls, executing format.sh with --cached and --quiet (2 commands). From tale-project/tale.
Instructions for tale-project/tale: The canonical contract for working in this repository is AGENTS.md at the repo root — the shared tale-project contract — followed by .agents/repo.md, the repo-specific contract (layout, domain rules, skills index, debt ledger). Read both and follow them.
Lets the agent drive a real browser: open pages, click, type, take screenshots and read the accessibility tree, using Playwright. Runs locally from the @playwright/mcp npm package.
Instructions for tale-project/tale, covering working in this repository, read the repo contract next, how to work, discover the conventions — don't memorize them and non-negotiable boundaries.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when…
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying…
Run this as the FINAL review step once you have finished a UI change you can load in a browser — it is the visual-regression gate, run once at the end (not after every edit), and the change is not done until it reports score: 100. It drives a real browser over the page, auto-detects its relevant elements (no…
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or…
Ein Agent ist eine Persona — Anweisungen, die Tools und Skills, nach denen er greifen darf, das Wissen, das er durchsuchen darf, und wer ihn benutzen darf.
Vom leeren Dialog zu einem einsatzfähigen Agenten — benennen, Anweisungen schreiben, Tools und Skills gewähren, Wissen eingrenzen und im Chat ausprobieren.
Ein Agent kann über das spawnagent-Tool einen fokussierten Worker für eine Aufgabe starten. Diese Seite gibt dir das Denkmodell — wann sich ein Worker lohnt, wie Fähigkeiten begrenzt bleiben und was die Job-Karte zeigt.
Coding-CLIs, die ein Modell in einer isolierten Sandbox ausführen — welche Harnesses mitkommen, wo du eines wählst, woher der Zugang stammt und was die Box erreicht.
Bildgenerierung ist ein Tool, das du jedem Agenten gewähren kannst — generateimage liefert ein Bild direkt in der Antwort, auf einem pro Zug gewählten Modell.
Wie ein Skill aus der Bibliothek einen Agenten erreicht — die Agenten eines Projekts ausrüsten, wessen Sichtbarkeit zählt und wie ein Bundle in einer Sandbox-Sitzung landet.
Die Berechtigungen pro Tool, die ein Agent über die Texterzeugung hinaus trägt — die Tool-Kategorien, Web-Zugang als Tool und Connectors und Automatisierungen als Fähigkeiten.