Explore skills

Annotate any file in Plannotator's browser UI. Markdown and HTML files are passed through directly; other files are wrapped in a temporary `.md` with a fenced code block, annotated, then the temp file is deleted.

Externalize a project that has become a hairball into a visible map plus one concrete next action. Use when the user says they are "overwhelmed", "lost", "stuck", "drowning", "buried", "spinning", "don't know where to start", "can't see the shape", "too many pieces/things/tabs", "spending too many cycles", or asks to "map this project" / "zoom out" / "what's next". Sub-actions: map (default), next

Load, validate, and use a user's private personal profile from Bitwarden CLI for form filling, PDF completion, applications, and identity/contact/employment/housing reuse. Use when an agent needs stable personal data backed by Bitwarden, language-aware profile values, a bundled schema for personal facts, or a safe workflow that materializes real profile values outside Git.

Install and configure browsers for Windows plus WSL2. Use when a user wants native Linux Chrome inside WSL to work for normal browsing or sign-in flows, or when a tool in WSL needs a Windows host Chrome or Edge instance exposed over CDP. Prefer this skill before any tool-specific browser automation setup.

Install, configure, and debug AeroSpace on macOS. Use when Codex needs to set up AeroSpace with Homebrew, create or repair ~/.aerospace.toml, configure window movement hotkeys for multi-monitor workflows, diagnose Accessibility or server/config problems, or automate binding tests with the AeroSpace CLI.

Install and configure `agent-browser` on a Windows machine with WSL2 after a browser path is already working. Use when a user wants the `agent-browser` CLI, its downloaded runtime, the `vercel-labs/agent-browser` repository, or an `agent-browser` attachment to a Windows host browser bridge from WSL2.

Access OpenAI Codex CLI conversation history to continue work started in Codex, or to find a past Codex chat by topic or keyword. Use when the user says "codex history", "continue from codex", "what was I doing in codex", "pick up from codex", "codex session", "find the codex chat about X", or wants to resume or locate a task that was started in Codex CLI.

Turn macOS caffeinate sleep prevention on or off, check its status, or explain the launchd-backed setup. Use when the user says to enable, disable, start, stop, toggle, inspect, or troubleshoot caffeinate / coffee Nate / keep-awake behavior for local terminal, Codex, Claude Code, or other agent workflows.

Ingest the live documentation manual into the ontology as ground-truth Doc nodes, then enrich them with doc→ontology DESCRIBES links. Runs the mechanical doc extractor (docs-ingest → doc-nodes.jsonl, split by heading/anchor, prose referenced from ../documentation), rebuilds the graph (embeds the doc prose), spawns the doc-analyser subagent per un-enriched page (live-URL verification + DESCRIBES to

Generate clean architecture and system-design diagrams as SVG files. Use this skill whenever the user wants to visualise how services, systems, or components connect: migration diagrams, current-state vs target-state architectures, integration maps, data-flow diagrams, platform overviews, or any diagram that shows technology boxes with arrows between them. Triggers on phrases like: "draw a diagram

Read research reports from product-pulse (daily, weekly, deep-dive) and create status/needs-triage items in the configured issue tracker. Diffs against existing issues, current codebase, and out-of-scope rejections to avoid duplicates. Uses ingestion watermarks to process only new reports. Trigger: "ingest research", "process reports", "import findings", or /pm:ingest.

Draft an upstream-repo GitHub issue on disk. Creates the next ISS file under issues/{repo}/ with paste-ready frontmatter + body skeleton. The actual filing into GitHub is a deliberate human action — this skill never opens a real issue.