jasonkneen

Gated Gmail skill scaffold for OpenClicky. Use when the user asks to list, search, read, summarize, or draft replies to Gmail messages through local Google OAuth.

Draft, rewrite, summarize, triage, and prepare replies or outreach emails. Use for Gmail/Outlook/Mail tasks, email thread summaries, outbound sequences, follow-ups, humanizing drafts, and Gmail sends that require upgraded send permission plus explicit approval.

Use OpenClicky's Composio-backed Google Workspace integration for Gmail read/search, Gmail drafts and approved sends, Calendar events, Drive, Docs, Sheets, unread mail, files in Google Drive, and day-planning tasks.

Drive native macOS apps and browser UI through OpenClicky's local computer-use MCP background lane, backed by Cua. Snapshot state, prefer AX element_index actions, use explicit pixel/foreground paths only when the current OpenClicky tool surface exposes them, and verify via re-snapshot. Use when the user asks you to operate, drive, automate, or perform a GUI task in a real macOS application on the host.

Use OpenClicky's local gog CLI as the primary Google Workspace route for Gmail read/search, optional Gmail send only when already connected and explicitly approved, Calendar, Drive, Docs, Sheets, Chat, Contacts, auth status, and account inspection. Prefer gog over browser automation for normal Google Workspace work.

Connect to Google Workspace through the local gogcli (`gog`) command for Gmail, Calendar, Drive, Docs, Sheets, Slides, Chat, Contacts, Tasks, Groups, Admin, Classroom, Forms, Apps Script, People, and Keep. Use when the user asks OpenClicky to use Google Workspace, Gmail, Calendar, Drive, Docs, Sheets, Slides, Chat, Contacts, Tasks, Workspace Admin, or to set up/check gogcli auth.

Draft, rewrite, summarize, triage, and prepare replies or outreach emails. Use for Gmail/Outlook/Mail tasks, email thread summaries, outbound sequences, follow-ups, humanizing drafts, and Gmail sends that require upgraded send permission plus explicit approval.

Open, reveal, find, export, rename, move, organize, or explain existing Clicky-generated files and local artifacts. Use when the user asks where a PDF, CSV, DOCX, PPTX, XLSX, HTML page, report, deck, video, image, or generated file went, asks to open it again, show it in Finder, export it, or organize it. Do not use for creating the content from scratch unless another workflow already produced the artifact.

Use when changing Tiny World Builder renderer setup, shadows, smoke, voxel clouds, ghost board render cost, frame loop, or GPU performance.

Use when changing the first-class Island Viewer shell, sequential generated-island viewer routing, or viewer-scoped graphics defaults.

Use when adding, importing, designing, reviewing, or animating low-poly / stylized 3D assets in Tiny World Builder, including Three.js procedural meshes, GLB/GLTF assets, Poly Pizza models, material palettes, scale/orientation, silhouettes, clouds/planes/crop dusters, and toolbar thumbnails.

Use when adding or changing persisted user state — settings defaults, audio, camera/orbit, panel positions, feature flags, and the in-app "Save Defaults" pipeline that snapshots localStorage into tinyworld-defaults.json. Also covers the inline-script regex gotcha that has burned us twice.

Tinyverse collectibles lane — pack reveal, frozen islands, play-mode visits. Universe carousel is archived but code stays in repo.

Use when changing Tiny World Builder API, webhook, SSE, MCP, plugin, or automation examples.

Use when editing Tiny World Builder prompts, model-generated worlds, Auto suggestions, or any model behavior that should create coherent low-poly 3D board scenes.

Use when adding or changing GLSL effects in Tiny World Builder — landscape water, waterfalls, foam, smoke, explosions, damage/wear overlays, or the reusable TinyShaderFX library. Covers where shaders live, the override relationship between LandscapeEngine.js and engine/landscape/*.js, and the procedural-noise toolkit.

Create comprehensive steering documents for development projects. Generates project-specific standards, git workflows, and technology guidelines in .kiro/steering/ directory.

Effective communication strategies for AI-assisted development. Learn context-first prompting, phased interactions, iterative refinement, and validation techniques to get better results from Claude and other AI coding assistants.

Transform approved requirements into comprehensive technical designs. Define system architecture, component interactions, data models, and interfaces to create a blueprint for implementation.

Comprehensive testing and validation strategies for spec-driven development. Learn phase-specific validation techniques, quality gates, and testing approaches to ensure high-quality implementation.

Transform vague feature ideas into clear, testable requirements using EARS format. Capture user stories, define acceptance criteria, identify edge cases, and validate completeness before moving to design.

Systematic three-phase approach to feature development using Requirements, Design, and Tasks phases. Transforms vague feature ideas into well-defined, implementable solutions that reduce ambiguity, improve quality, and enable effective AI collaboration.

Convert technical designs into actionable, sequenced implementation tasks. Create clear coding tasks that enable incremental progress, respect dependencies, and provide a roadmap for systematic feature development.

Diagnose and resolve common issues during spec-driven development and implementation. Learn strategies for handling spec-reality divergence, dependency blocks, unclear requirements, and other execution challenges.

How I notice a recurring failure of my own, root-cause it, fix what I can myself (behavioral rules, config, ignore files), and — for anything needing a kernel change I can't apply — draft a verified proposal for the operator to review. The capstone that turns my mistakes into durable fixes. Use when I hit a repeated mistake, get corrected by the operator, see a failed VERIFY, or notice a pattern worth fixing.

The ONLY sanctioned way to delegate work to a lazar sub-agent. Uses locked bin/lazar-spawn (not agent-writable skills logic) — lints the prompt, bounds retries, wall-clock-kills wedged children, and gates success by re-checking declared claims against the filesystem. Raw `lazar -p` is vetoed by a pre-tool hook. Use whenever you need to fan out work, isolate context, or run something as a separate agent. Provider-agnostic.

Load, list, verify, and store API keys. Canonical source is macOS Keychain (service=lazar). Use when you need a credential, to check which providers work, or after rotating keys. Never print secret values.

Turn raw stream.jsonl logs into durable, readable memory — a work journal of what I built and worked on — so the multi-MB archives stop being the only record of my own history. Run after sessions, before pruning logs, or whenever I can't recall recent work. Pairs with _meta/distill (the learnings layer). Use when logs are large, when I've lost track of what I've done, or when preparing to prune/compress the log archives.

Verify lazar is installed correctly and all load-bearing behaviors work end-to-end. Runs static checks (kernel locked, env vars, skills present), boundary tests (sandbox enforcement), live behavior tests (log auto-rotation, memory persistence, recursion), and short end-to-end builds in TypeScript and Python. Runs in a temp directory under workspace/, cleans up after itself, prints PASS/FAIL with a summary at the end. Use after install, after kernel rebuild, after --reset-all, or anytime something feels off.

Scaffold a terminal interface for lazar — a small client project under workspace/<name>/ that consumes `lazar -p --output-format stream-json` and renders the events. Default stack: TypeScript + readline. Optional: Go + Bubble Tea, Python + Textual, or anything else the user wants. Use when the user asks for a "TUI", "chat UI", "interface" for lazar that's richer than `lazar-chat.sh`.

Run OpenWork UI evals on a Daytona sandbox or local Electron instance. Handles sandbox creation, service startup, and eval execution via CDP browser tools.

Guide users through browser automation setup using Chrome DevTools MCP only. Use when the user asks to set up browser automation, Chrome DevTools MCP, browser MCP, or runs the browser-setup command.

Manages Cargo.lock file updates and resolves --locked flag issues in CI/CD. Triggers when user mentions: - "cargo test --locked failed" - "cannot update the lock file" - "Cargo.lock is out of date" - "PR failed with --locked error" - "fix Cargo.lock"

Publish the openwork-orchestrator npm package with clean git hygiene. Triggers when user mentions: - "openwork-orchestrator npm publish" - "publish openwork-orchestrator" - "bump openwork-orchestrator"

Systematic security audit of Electron IPC handlers covering path validation, process lifecycle, environment leakage, network security, and authentication gaps

Systematic approach to breaking up god modules (>1000 lines) in TypeScript projects using domain extraction, barrel re-exports, and orchestrator patterns

Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks "why does this code exist", "who wrote this function and why", or to "explain the history of this function" before a rewrite, refactor, or risky edit. Runs entirely locally.

Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too broad, or what unrelated stuff they touched, and wants keep, split, or justify guidance. Operates locally and offline.

Query the user's data via the local screenpipe REST API at localhost:3030 — screen recordings, audio, UI elements, usage analytics, meetings, connected services, and the user's persistent memory store. Use for questions about screen activity, meetings, apps, productivity, media export, retranscription, connections, OR to save / remember / store information for later (POST /memories — survives across sessions, queryable by external agents).

Manage screenpipe pipes (scheduled AI automations) and connections (Telegram, Slack, Discord, etc.) via the CLI. Use when the user asks to create, list, enable, disable, run, or debug pipes, or manage service connections from the command line.

Use when controlling infinitty, driving/automating/testing terminal or TUI apps running inside it (vim, htop, REPLs), reading its screen or scrollback, sending keystrokes, or checking a command's output/exit code via the per-pane Unix control socket ($INFINITTY_SOCKET, /tmp/infinitty-*.sock).

Automated code review against project conventions (CLAUDE.md) and best practices

Move CPU-bound work off the main thread onto real OS threads (Web Workers / node:worker_threads) via unithread. Use when a UI is janky or frozen, a page locks up, an event loop is blocked, "this loop is too slow", or the user asks to parallelise a loop, use worker threads, offload work, or make something stop blocking.

Utilities for inspecting the local project workspace (list files, spot large folders, and determine where to focus).