itzikiusa
@itzikiusa
Public Skills
db-redis
by itzikiusa
Specialized assistant for exploring and querying a Redis keyspace read-only in Otto's DB Explorer — type-aware reads, SCAN instead of KEYS, key-pattern/namespacing conventions, big-key care, and producing a final command.
PO Story Overview
by itzikiusa
Summarize and assess a product story (Jira/Confluence) from a Product Owner lens — value, clarity, scope, and acceptance-criteria completeness. Stay at product altitude, not implementation.
Jira Story Writer
by itzikiusa
Guidelines (not strict rules) for writing an excellent Jira story. Use to suggest a rewrite and to review an existing story. PO-level — frame value and acceptance, stay out of technical implementation.
Grill the Story
by itzikiusa
Adversarially grill a product story or PRD — hunt scope holes, ambiguities, non-testable acceptance criteria, unhandled edge cases, hidden dependencies, and conflicting requirements. Evidence-based and specific; never invent requirements.
db-mysql
by itzikiusa
Specialized assistant for exploring and querying a MySQL/MariaDB database read-only in Otto's DB Explorer — dialect idioms, safe schema discovery, EXPLAIN-driven performance, and producing a single final query.
RFC Writer
by itzikiusa
Guidelines (not strict rules) for writing an excellent RFC / proposal. Use to suggest a rewrite and to review one. Product/decision altitude — frame the problem, the options, and the recommendation; light on deep technical design. Audience is decision-makers and stakeholders.
Story Clarifying Questions
by itzikiusa
Surface the fewest, sharpest clarifying questions that make a story unambiguous. High-leverage only, categorized, each with why it matters. Not over-defensive.
db-mongodb
by itzikiusa
Specialized assistant for exploring and querying a MongoDB database read-only in Otto's DB Explorer — find vs aggregation pipelines, $lookup joins, explain plans, schema-less discovery, and producing a single final query.
db-clickhouse
by itzikiusa
Specialized assistant for exploring and querying a ClickHouse database read-only in Otto's DB Explorer — columnar/OLAP idioms, FINAL and merge semantics, system.* introspection, approximate aggregates, join pitfalls, and producing a single final query.
Story Task Breakdown
by itzikiusa
Turn a refined product story into a superpowers-style implementation plan — an ordered list of small, independently-verifiable tasks. Each task states a goal, concrete steps as checkboxes, and a verification. PO-readable but actionable; right-sized, TDD where it fits, never over-engineered.
Story Test Cases
by itzikiusa
Draft readable, right-sized test cases for a story — happy path plus meaningful validations and realistic errors. Not over-defensive. Plain language a PO can approve and a dev can implement against.
Story Architecture Overview
by itzikiusa
Map a product story to the actual codebase — related repos/modules, functionalities touched, integration/contract points, data impact, and technical risks. Inspect the working directory; cite real file paths and line numbers.
Insights
by itzikiusa
Generate an action-first coding-agent usage report across ALL providers Otto uses (Claude, Codex, agy/Gemini) for a chosen period (day/week/month or explicit range), compare it to the previous comparable period for trends, and emit a self-contained HTML report where every finding — even the good ones — carries Evidence/threshold → Action → Expected effect. Use when the user wants a usage/productivity insights report, a weekly/daily/monthly review, or trend tracking of how they work with AI agents.
okf-authoring
by itzikiusa
Use when creating, maintaining, consuming, converting, or validating Open Knowledge Format bundles, especially Otto Vault documentation for repositories, services, APIs, data assets, decisions, runbooks, metrics, and references.
Otto Design — 3D scenes (scene3d) — in-place agent
by itzikiusa
Use when creating or editing a 3D SCENE for an Otto Product story from an agent session — the Design tab's scene3d format (a scene.json file the arena's three.js viewport renders and the inspector round-trips) — or when asked for a game-level blockout, a product shot, a kiosk/booth/room layout, a 3D concept for a story. Covers the exact otto-scene3d v1 schema with a full example, blockout conventions (metres, y-up, floor at y=0), lighting recipes, naming/grouping rules, the validation limits, how GLB models are referenced (attachment_id, never a URL), and when to prefer the Blender MCP tools / the server-side Blender render+script export instead of editing the file.
Otto Product Design artifacts — in-place agent
by itzikiusa
Use when generating or refining a DESIGN artifact for an Otto Product story from an agent session — the Design tab's in-place "Create with AI" / "Refine" agent — or when a swarm agent publishes a mockup with the otto-mockup helper. Covers the FILE-BACKED model with FOUR formats — HTML screen (design.html), Mermaid diagram (design.mmd), Excalidraw board (design.excalidraw) and 3D scene (scene.json, scene3d) — which file to edit for which ask, the always-valid/whole-file rule, how the file is committed as a kind:design attachment and previewed live, the otto-mockup --format flags, and where the per-format authoring rules live (otto-design-2d, otto-design-3d).
Otto Design — 2D screens & boards — in-place agent
by itzikiusa
Use when creating or refining a 2D DESIGN for an Otto Product story from an agent session — the Design tab's Figma/Canva-style side — an Excalidraw BOARD (design.excalidraw: frames as artboards, wireframes, user flows, component sheets, moodboards) or an HTML SCREEN (design.html: a self-contained, script-free, high-fidelity UI screen shown in a device frame). Covers Excalidraw JSON authoring rules (document shape, element fields, frames, bound text, arrows with bindings, 8-pt grid, palette, reusable components), HTML screen rules (no network, no JS, realistic content, light/dark), and the quality bar for each.
skills-reviewer
by itzikiusa
Reviews Agent Skills / SKILL.md packages for quality, spec compliance, trigger clarity, examples, references, eval coverage, bloat, conflicts, and risky instructions. Use when asked to audit, review, improve, score, or validate an agent skill.
vault-repo-docs
by itzikiusa
Use when indexing, scanning, or documenting a repository into the Otto Vault as a durable OKF bundle, including full, focused, and incremental scans or feature dependency maps; not for code review or one-off repository questions.
vault-api-review
by itzikiusa
Review Otto Vault repository documentation specifically for complete HTTP/RPC/WebSocket contracts, real request and response bodies, errors, auth, examples, OpenAPI parity, and runtime side effects. Use as a focused post-scan reviewer; do not author or repair docs.
vault-docs-review
by itzikiusa
Review an Otto Vault repository-documentation run for missed surfaces, shallow concepts, unsupported claims, broken coverage, and incomplete API/data/runtime detail. Use as the default general reviewer after a Vault scan; do not use to author or silently repair the bundle.
vault-runtime-review
by itzikiusa
Review Otto Vault repository documentation specifically for runtime flows, messages, schedules, reconciliation, startup/shutdown, failure handling, retries, idempotency, observability, and external side effects. Use as a focused post-scan reviewer; do not author or repair docs.
vault-data-review
by itzikiusa
Review Otto Vault repository documentation specifically for complete relational, document, analytical, and Redis schemas; real reads/writes; indexes/TTL; consistency; relationships; and field-level impact. Use as a focused post-scan reviewer; do not author or repair docs.
vault-evidence-review
by itzikiusa
Review Otto Vault repository documentation specifically for citation precision, claim-to-source support, source hierarchy, invented examples, stale contradictions, coverage-status evidence, and honest uncertainty. Use as a focused post-scan reviewer; do not author or repair docs.