avivsinai
- 35 skills
- 0 followers
- 10 hours ago last updated
- ▌
- ▌
- ▌ Finding Unknowns · avivsinai bundleGuide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when the user explicitly asks for a blindspot pass, unknown unknowns, "what am I missing / what should I be asking", a one-question-at-a-time interview, or several directions to react to; when ambiguity or unfamiliarity is high enough that building now would likely cause rework; when a reference implementation must be understood before porting; or for a named after-walk slice — implementation notes / deviations log, a buy-in doc, a quiz gate before merge, or a session handoff (run only that slice). Do not invoke for ordinary implementation of a sufficiently specified task.
- ▌ Sabx · avivsinai bundleManage SABnzbd queues, history, NZBs, priorities, limits, RSS feeds, schedules, and server state through sabx.
- ▌ Yoetz · avivsinai bundleFast CLI-first LLM council, bundler, and multimodal gateway. Use ONLY when user explicitly mentions "yoetz", "yoetz ask", "yoetz council", "yoetz review", "yoetz generate", "yoetz bundle", "yoetz browser". NOT triggered by generic "second opinion" or "ask another model" requests.
- ▌ Shaon · avivsinai bundleManage personal Hilan attendance, corrections, payslips, and salary data through shaon.
- ▌ Release · avivsinaiBump version, update all version references, build release binary, and create git tag. Use when cutting a new release of shaon.
- ▌ Snagline · avivsinai bundleHandle Snagline cases, inert advice, operator tools, Buzz projections, and SSP verification within Snagline's trust boundary.
- ▌ Eval Skills · avivsinaiEval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each example input, grade the artifact against a per-case bar, and let the gaps drive the edits. Use when the user wants to test/eval/improve/harden a skill, says "this skill keeps producing X / keeps missing Y", or hands a skill plus cases with a bar for what good looks like. Pairs with write-skills (the authoring principles every fix obeys). Judgment-first and harness-free — prefer skill-creator for harness-based benchmarking, variance analysis, or description-optimization loops.
- ▌ Write Skills · avivsinaiCreate or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill, improving trigger descriptions, or deciding what belongs in a skill versus references, scripts, assets, or ordinary docs. This is the judgment layer — authoring principles and failure modes for manual, principle-level work; prefer skill-creator when the user wants end-to-end interactive creation with generated test harnesses or quantitative description optimization.
- ▌
- ▌ Gifgrep · avivsinai bundleSearches for GIFs from Tenor/Giphy and downloads them for sending via Telegram. Use when users want reaction GIFs, memes, or animated images.
- ▌ Weather · avivsinai bundleFetches weather forecasts using wttr.in. Use when users ask about weather, temperature, forecasts, or conditions for any location.
- ▌ Humanizer · avivsinaiAudits text against AI writing tells and rewrites it into natural prose. Use when the operator wants drafted content de-AI-ified, especially before publishing on X/LinkedIn/Threads or sending to readers.
- ▌ Summarize · avivsinaiExtracts and summarizes web content from URLs. Use when users share links or ask to summarize articles, YouTube videos, or web pages.
- ▌ Daily Brief · avivsinaiUse when the operator asks for a daily or morning Telegram brief, agenda digest, inbox highlights, or Hermes-style operator preset. This is a read-only private-agent workflow that gathers today's Google Calendar, recent Gmail inbox highlights, and weather, then returns a concise Telegram brief.
- ▌ Cron Manager · avivsinaiUse when the user wants to create, inspect, update, or remove telclaude scheduled jobs, especially natural-language schedules like "every weekday at 9am". Prefer this skill for cron CRUD behind WRITE_LOCAL+.
- ▌ Meeting Prep · avivsinaiPrepare a concise Telegram briefing before an upcoming calendar event using read-only Google Calendar and Gmail context through the telclaude provider proxy.
- ▌ Skill Manage · avivsinaiCreate, patch, pin, unpin, rename, or archive agent-authored telclaude skills through the guarded managed-skill writer. Use only for private/telegram agent work when durable skill changes are clearly useful.
- ▌ Video Frames · avivsinai bundleExtracts frames from video files using ffmpeg for visual analysis. Use when users send videos and want frame-by-frame analysis, thumbnails, or key moment extraction.
- ▌ Security Gate · avivsinaiClassifies inbound Telegram messages for telclaude as ALLOW/WARN/BLOCK with brief rationale.
- ▌
- ▌ Social Posting · avivsinaiGuides the social agent on crafting posts and threads for X/Twitter. Use when creating proactive posts, threads, or engaging with timeline content. Covers thread structure, hook techniques, formatting, and structured output format.
- ▌ Telegram Reply · avivsinaiCrafts Telegram-friendly replies for telclaude sessions, respecting media, heartbeats, and brevity.
- ▌ Text To Speech · avivsinaiConverts text to speech audio using OpenAI TTS API. Use when users request audio versions of text or want responses read aloud.
- ▌ Codex Work Unit · avivsinaiUse when the operator wants to delegate a bounded, single-shot repo task to Codex through telclaude background jobs.
- ▌ Image Generator · avivsinaiGenerates images using GPT Image 1.5 API. Use when users request image creation, illustration, or visual content.
- ▌ External Provider · avivsinaiAccess configured sidecar providers (health, banking, government) via CLI commands.
- ▌
- ▌ Weekly Business Report · avivsinaiUse when the operator asks for a weekly business report, Monday-morning business digest, revenue/support/CRM/analytics roundup, or wants to schedule workflow
- ▌ Amq Spec · avivsinai bundleUse two agents to research a design independently and converge on one specification through AMQ. Trigger for collaborative design or messages labeled workflow:spec; use amq-cli for ordinary coordination.
- ▌ Amq CLI · avivsinai bundleCoordinate coding agents through AMQ. Use for agent messages, inboxes, receipts, sessions, wake delivery, cross-project routing, managed launches, or AMQ diagnostics. Use amq-spec for collaborative design; do not use this for general message queues or single-agent work.
- ▌ Langfuse · avivsinai bundleInvestigate AI traces, observations, exceptions, latency, sessions, prompts, datasets, annotation queues, and scores through Langfuse MCP. Use when the request names Langfuse or asks to diagnose recorded AI behavior.
- ▌ Jk · avivsinai bundleManage Jenkins controllers with jk, including jobs, runs, logs, artifacts, credentials, nodes, queues, and plugins.
- ▌ Bkt · avivsinaiOperate Bitbucket Cloud or Data Center repositories, pull requests, branches, issues, pipelines, permissions, and webhooks with bkt. Use when a request names Bitbucket or bkt; confirm the platform before platform-specific commands.