Naoray
UserNaoray's personal Claude Code, Cursor & Codex skills. Connect in one command with scribe.
Categories
Indexed Skills (15)
apple-calendar
Use when the user asks to list Apple Calendar calendars or events, create/update/delete events, search appointments, or manage recurrence in Calendar.app on macOS. Inputs - calendar name when needed, event UID for read/update/delete, event title, start/end times, location/description/recurrence details for writes. Do not use when the user needs Google/Outlook calendar APIs, cross-platform sync, or general scheduling advice; use a service-specific calendar integration instead. Produces Calendar.app script commands and parsed event/calendar results. Escalate if calendar permissions are missing, the target calendar is read-only, dates are ambiguous, or deleting a recurring event could remove an entire series.
cleanup
Use when the user asks to clean up a project, remove old plans, tidy docs, cleanup stale files, prune completed specs, or inspect artifacts after shipping a major feature. Inputs - project root, current branch context, and user confirmation before deleting or rewriting files. Do not use when the user wants disk-space cleanup, dependency pruning, code refactoring, or documentation generation; use a system-cleanup, package, refactor, or docs workflow instead. Produces a cleanup report classifying artifacts as remove, update, keep, or review, then confirmed file/doc changes. Escalate if deletion risk is ambiguous, living docs are involved, or more than two docs need substantive updates.
evaluate-day
Use when the user says "/evaluate-day", "evaluate yesterday", or asks to turn a daily running log into an end-of-day reflection. Inputs - target date if not today, access to the daily note, existing Running Log entries, and user energy level/additions before writing. Do not use when the user wants to plan the day, log a new event, or write freeform journaling from scratch; use plan-my-day, record, or a writing skill instead. Produces grounded reflection answers written into the daily note. Escalate if the note is missing, the reflection already has answers, the log is too thin, or the user has not approved overwriting.
meeting
Use when the user says "/meeting [title]", "/meeting end", or wants live meeting note capture from raw fragments during an active meeting. Inputs - meeting title, type, attendees, active meeting state, and real-time notes or end command. Do not use when the user wants post-hoc meeting summarization, a transcript cleanup, or general note-taking outside meeting mode; use summarization or writing skills instead. Produces structured raw notes, action items, decisions, and a shareable meeting summary for review. Escalate if no title is provided, no meeting is active on end, another meeting is already active, or content appears sensitive enough to require confirmation before writing.
orchestrator-handoff
Use when the user says "time for a handoff", "start a new orchestrator", asks to preserve session state, or context budget is tight during coordinated agent work. Inputs - current project, Solo process state, active todos/scratchpads/timers, open PRs/issues, recent git activity, and durable memory references. Do not use when the user only wants a brief status update or progress summary; answer that directly without producing a handoff artifact. Produces a read-only handoff scratchpad plus a paste-ready prompt for the next orchestrator session. Escalate if required state sources are unavailable, project identity is ambiguous, or the user wants agents stopped or repo state changed.
orchestrator-mode
Use when the user says `/orchestrator-mode`, asks you to coordinate agents, or gives large multi-phase work needing parallel delegation, reviews, PRs, scratchpads, or handoffs. Inputs - project goal, repo context, Solo agents/processes, branch/worktree constraints, locked user decisions. Do not use for a direct small edit, a normal code review, or single-agent implementation; use focused coding/review skills instead. Produces delegation plan, agent briefs, monitoring protocol, review/merge routing, state hygiene rules. Escalate on unclear scope, product direction, merge authority, destructive cleanup, or tool availability. Delegates are Solo processes: prefer Solo MCP tools, falling back to the `solo` CLI only when MCP is unavailable - never the in-process Task/Agent tool.
plan-my-day
Use when the user says "plan my day", "help me schedule today", or asks to combine calendar events, reminders, and new tasks into a day plan. Inputs - target date if not today, relevant calendars/reminders access, calendar filters, available tasks, and approval before writing events. Do not use when the user only wants to list calendar events or capture a quick note; use calendar lookup or record instead. Produces a reviewed time-block schedule, calendar event plan, and daily note scaffold. Escalate if calendars/reminders are unavailable, calendar filters are missing, fixed commitments conflict, or the user has not approved writes.
record
Use when the user says "/record [message]" or when a meaningful workday event needs a concise timestamped entry in today's running log. Inputs - exact message for manual entries, current date/time, daily note location, and enough context to judge whether an automatic entry is meaningful. Do not use when the user wants a full journal entry, meeting notes, or end-of-day synthesis; use writing, meeting, or evaluate-day instead. Produces one deduplicated timestamped Running Log entry in today's daily note. Escalate if the daily note path cannot be created, the entry would duplicate existing content, or automatic logging would expose sensitive content.
research-mode
Use when the user asks to enable research mode, turn research mode on/off, require citations, fact-check claims, review technical specifications, or work where source grounding and anti-hallucination constraints matter. Inputs - research question, documents or sources to inspect, citation expectations, and whether mode should persist. Do not use when the task is creative brainstorming, drafting fiction, or casual ideation without factual claims; use normal generation instead. Produces cited answers grounded in verified sources and direct quotes when analyzing documents. Escalate if sources conflict, reliable evidence is unavailable, citations cannot be verified, or the user asks to present uncertain claims as fact.
session-plan
Use when the user says "/session-plan", "what should my next session look like?", or wants a focused practice/work block from current progress. Inputs - domain name if not default, time available, user state or constraints, and persistent domain context such as profile, learning path, progress log, subject notes, and recent measurements. Do not use when the user wants broad curriculum design, post-session analysis, or generic productivity advice; use planning, analysis, or coaching skills instead. Produces a prioritized session plan with one main outcome, timed blocks, and what to ignore. Escalate if context is missing, stale, ambiguous, or user constraints conflict with the likely plan.
skill-creator
Author or revise an AI-agent skill. Use when the user says "let's make a skill for X", invokes /skill-creator, asks to revise an existing SKILL.md, or wants to skill-ify a repeated workflow with 2+ prior invocations. Inputs - trigger phrase, artifact, evidence tier (E empirical / P practitioner / H heuristic). Do not use when the workflow is one-shot (write a snippet), is a phrasing trick or persona without a stable model, is an eval/benchmark loop (separate kit), or duplicates an existing skill (merge). Produces a skill directory with SKILL.md (5-part trigger description, lean body, no README/INSTALL/CHANGELOG) plus the registry-integration step for the active backend (see references/registry-integration.md). Escalate if no repeated workflow exists (suggest snippet), the model is H-tier with overreach ≥4 (manual-only), or the skill would compete with a stronger existing one (merge).
dev-browser
Use when the user asks to navigate a website, click UI, fill forms, take screenshots, scrape visible page data, test a web app, log into a browser session, or automate browser workflows with persistent page state. Inputs - target URL or existing page context, desired browser action, selectors or visible labels when known, credentials only when user explicitly provides them. Do not use when a plain HTTP request, local file edit, or Playwright test suite is the better artifact; use those tools instead. Produces dev-browser CLI commands or sandboxed JavaScript automation steps plus captured results. Escalate if login, payment, destructive actions, CAPTCHA, or sensitive personal data is involved.
changelog-pr
Create or update release/changelog artifacts using Keep a Changelog. Use when the user asks to create a changelog PR, update a changelog, refresh a release PR body, summarize changes since a tag, or prepare a PR description from a branch diff. Inputs - source/target branches (or current branch → main default), repo merge style (squash or regular), and existing CHANGELOG.md / release PR if updating. Do not use when the PR is non-release (write a normal PR body), the user wants raw commit summaries (use git log), the work is cutting a new release branch (separate workflow), or the request is a one-off email/note. Produces a Keep a Changelog-formatted PR body OR updated CHANGELOG.md [Unreleased] section, with sections only for categories that have entries. Escalate if merge style cannot be detected, existing manual release notes are present and may be stale, or source/target branches are ambiguous.
code-review-artifacts
Create code-review comprehension artifacts (diff briefs, ASCII flow maps, architecture x-rays). Use when the user asks "show me the flow", "what changed", "walk me through this", "xray", "show me the flows", "what does this codebase do", or wants to understand code before approving, merging, or refactoring. Inputs - branch or commit range, scope (file/function/route/CLI command/whole codebase), and a comparison base. Do not use when the user wants approval (this is comprehension, not approval), is doing functional/security/lint review (separate skills), wants a refactor (rewrite request, not review), or is reading already-shipped code that is unchanged. Produces a diff brief OR ASCII flow map OR architecture x-ray, each prefixed with an explicit "Inspected / Not inspected" scope statement. Escalate if scope is unclear, comparison base cannot be determined, or the codebase is too large for a single artifact (recommend a scoped sub-run).
visual-review
Visually verify rendered output for web pages, PRs, CLI commands, and TUIs. Use when the user asks for "visual review", "visual QA", "screenshot this", "check how this PR looks", "review CLI output", "capture a terminal command", or "record this TUI". Inputs - target URL or PR number, mode (browser / CLI / TUI / regression), and routes / commands / viewports to check. Do not use when the user wants functional QA (use a testing skill), brand-taste judgment (this verifies rendered output, not design taste), frontend-stack migration (out of scope), or wants to push commits (this is read-only). Produces a screenshot or recording set + a visible-issues report listing artifact paths, routes/commands/viewports inspected, and any layout/overflow/state-coverage gaps found. Escalate if the target is unreachable, the PR is too large for a single review pass (recommend scope reduction), or the local dev server cannot start.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.