itzikiusa
UserAgentic development environment for macOS: Claude Code / Codex sessions, multi-agent orchestration, git/PR review, DB & API clients — Tauri + Rust + Svelte.
Categories
Indexed Skills (38)
vault-repo-docs
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.
skills-reviewer
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-api-review
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-data-review
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-docs-review
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
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.
db-clickhouse
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.
db-mongodb
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-mysql
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.
db-redis
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.
okf-authoring
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.
vault-evidence-review
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.
good-focused
Reviews D2 diagram skill drafts for syntax workflow, diagram examples, references, and eval coverage. Use when asked to audit a D2-specific Agent Skill; do not use for generic code review.
excellent-skill
Use this skill when reviewing small API migration pull requests for the Acme Payments service, especially changes touching idempotency keys, retry behavior, webhook signatures, or migration SQL.
bad-bloated
Helps with everything and all tasks across coding, writing, research, diagrams, deployment, finance, product work, emails, analysis, and anything else.
bad-conflicts
Reviews release notes skill drafts for clarity, examples, references, and evals. Use when asked to audit release-note skills before publishing.
bad-no-examples
Audits SQL query optimization skills for trigger clarity, workflow structure, references, evals, and safe script usage. Use when reviewing a SQL-optimization Agent Skill package.
bad-script-risk
Checks deployment helper skills for script safety, examples, references, evals, and conflict risks. Use when reviewing a deployment Agent Skill that bundles shell or Python scripts.
bloated-conflicting-skill
Helps with everything related to documents, coding, research, travel, and productivity.
grill
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.
commit-message
Use BEFORE writing or finalizing ANY git commit message — when staging changes, running git commit, or asked to "commit", "write a commit message", or "draft a commit". Covers Conventional Commits, the repo's emoji/scope convention, the Jira key, splitting mixed changes, and the rule that a commit carries NO AI attribution.
d2-diagram
Use whenever asked to work on a diagram — create, update, improve, review, validate, or render one — including architecture / C4 maps, sequence & API flows, ERDs / SQL schemas, data flows & ETL pipelines, infrastructure / Kubernetes / deployment topology, dependency & module graphs, state machines, incident/debug timelines, and repo-derived diagrams. Produces durable D2 (`.d2`) sources plus rendered SVG in `docs/diagrams/`, with quality linting (d2_doctor) and layout/style rules. For Otto Canvas scenes (a per-scene `canvas.d2`/`canvas.mermaid`/`canvas.json` edited over HTTP), use the `otto-canvas` skill instead.
otto-canvas
Use when drawing/generating a diagram for the Otto Canvas, creating or editing canvas scenes, or driving Discovery Chat on a Product story, from an agent session over HTTP. Covers the FILE-BACKED canvas model with THREE modes — Mermaid (edit a per-scene `canvas.mermaid`; any diagram type), Excalidraw (edit a per-scene `canvas.json`; fully editable shapes), and D2 (edit a per-scene `canvas.d2`; modern declarative diagrams — architecture, sequence, SQL tables) — top-notch pretty-Mermaid styling, the D2 shape/class syntax, the Excalidraw simplified element format, the OTTO_API_TOKEN auth model, the Canvas + Discovery-Chat endpoints, and the canvas.mjs helper.
otto-mockup
Use when generating or refining a product MOCKUP for an Otto Product story from an agent session — the in-place "Create with AI" / "Refine" mockup agent. Covers the FILE-BACKED mockup model with TWO formats — HTML (edit a per-mockup `mockup.html`; a self-contained, sandbox-safe UI screen) and Mermaid (edit a per-mockup `mockup.mmd`; any diagram type) — the quality rules for each, and how the file is committed as a `kind:mockup` attachment that renders in the Mockups tab.
pull-request
Use BEFORE opening or drafting ANY pull request — when asked to "open a PR", "create a pull request", "draft a PR", or to write a PR title/description. Covers summarizing the whole branch, the Jira key as title prefix (never in the body), GitHub vs Bitbucket creation, and the rule that a PR carries NO AI attribution.
insights
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.
architecture-review
A focused, single-lens review of a change's design and structure — not its defects. Judges separation of concerns and SOLID, coupling and cohesion, module/layer boundaries and dependency direction, whether the right abstraction is present (and the wrong/early one is absent), files and functions that have grown too large or do too much, leaky abstractions, intent-hiding names, duplication that wants to be a shared unit, and whether the change fits how this codebase is already built. Every finding cites file/module:line, a severity, the future cost it imposes, and a concrete refactor direction. Constructive and pragmatic — flags structure that will cost future change, never taste.
correctness-review
A focused single-lens code review that hunts correctness bugs only — logic errors, off-by-one, inverted conditions, broken invariants, wrong state transitions, null/None/nil mishandling, and the unhandled branch the author never ran. For each suspected bug it hand-traces (and reproduces where it can) before asserting, then reports it with file:line, severity, why-it-matters, and a concrete fix. Run it alone for a sharp pass, or compose it with security/performance/etc. — it deliberately does not duplicate grill's exhaustive all-lens sweep.
security-review
A focused, single-lens security review of a change. The one specialist a user runs alone when they care about exploitability — not a general sweep. Core method is taint tracing - follow untrusted input from its source, across the trust boundary, to a dangerous sink - and prove the path is reachable before calling it a finding. Covers injection (SQL/NoSQL/command/LDAP), XSS, SSRF, path traversal, insecure deserialization, authn/authz gaps (missing permission checks, IDOR), secret handling, sensitive-data exposure in logs/errors/URLs, crypto misuse, and unsafe defaults. Every finding cites file:line, a severity (a real exploit path is a blocker), the concrete attack, and a fix.
test-review
A focused, single-lens review of test quality and coverage for a change — does the test actually exercise the new behavior AND its failure modes, or does it merely pass? Hunts happy-path-only coverage, weak assertions, tests that pass even when the code is wrong, over-mocking that tests the mock, missing negative/edge/error cases, flakiness, and tests coupled to implementation detail. Every finding asks "would this test fail if I broke the code?", cites file:line, a severity, why it matters, and the concrete missing case or stronger assertion.
missing-evals-skill
Use this skill when converting legacy CSV exports from the Northstar billing system into normalized JSON invoices.
jira-story-writer
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.
po-story-overview
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.
rfc-writer
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-architecture-overview
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.
story-clarifying-questions
Surface the fewest, sharpest clarifying questions that make a story unambiguous. High-leverage only, categorized, each with why it matters. Not over-defensive.
story-task-breakdown
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
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.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.