@tonydzi
Technical lead, Palo Alto AI Research Lab. Security engineer (MSc, crypto). Evidence-first reliability work for AI agents. Triathlete.
239 スキル2 リポジトリ 18
Send and read messages between machines in a fleet over a shared Telegram group, so cross-machine coordination survives a file-sync outage and humans can watch the machines talk. A synced folder stays as the fallback for oversized payloads. Triggers: "/bus", "post to the bus", "check the bus", "tell the other machines".
日本語の概要は準備中です。原文の説明を表示しています。
Repair the Cursor editor when it crashes, fails to launch, or new Agent chats break. Use with a Request ID, fresh logs, CursorRule.parse_error or invalid UTF8 in skill frontmatter, or a better-sqlite3 NODE_MODULE_VERSION mismatch. Finds a reproducible cause, applies a narrow reversible fix and proves it with two new chats. Triggers: /cursor-repair, Cursor won't start, Cursor agent broken.
日本語の概要は準備中です。原文の説明を表示しています。
Verify someone else's code fix against your own live corpora (agent transcripts, sessions, memory files) before trusting or merging it. Use when an external PR or patch touches how transcripts, sessions or agent memory are read. Triggers: /corpus-bench, run it on our corpus, verify the fix on our transcripts, corpus bench.
日本語の概要は準備中です。原文の説明を表示しています。
Run one full mining pass over an imported community-chat corpus: deterministic detector, LLM judge, harvest, review screen. Works on any imported corpus through a per-source config and is safe to re-run, being idempotent by message id. Triggers: "/community-alpha <source> [month]", "mine alpha from <community>".
日本語の概要は準備中です。原文の説明を表示しています。
Cross-vendor code review: this agent reviews the other agent's diff and the other agent reviews this one's, so the final check always comes from a different model. Verdicts are APPROVE or REQUEST_CHANGES with file:line references. Triggers: "/codex-review", "cross-review this diff", "have the other vendor check this".
日本語の概要は準備中です。原文の説明を表示しています。
Pull new and changed claude.ai web conversations into an Obsidian vault, extract artifacts as first-class notes, concept-link them, and refresh the RAG index and dashboard. Idempotent: curated notes are never overwritten. Triggers: "/claudeai-sync", "pull claude.ai", "grab new claude.ai chats".
日本語の概要は準備中です。原文の説明を表示しています。
ЧИП ТОЛЬКО ПО ПРЯМОМУ ЗАПРОСУ ЮЗЕРА (anton 14.08): сделать ЧИПЫ (spawn_task), которые юзер нажмёт сам.
日本語の概要は準備中です。原文の説明を表示しています。
Find a Telegram chat, group or channel by name and return its numeric id and t.me link from a local index, with no live crawl. Also answers which groups you share with a person or company. This is the chat lane, not people search. Triggers: "/chat <query>", "find the <X> chat", "chat id for <X>".
日本語の概要は準備中です。原文の説明を表示しています。
Finds free backlink and brand mention opportunities across Hacker News, Quora, GitHub, directories, and niche communities. Outputs a prioritized action plan with draft responses ready to post. Use after brand research and content creation to amplify reach and AI engine citations.
日本語の概要は準備中です。原文の説明を表示しています。
Verifies truthfulness, accuracy, and link integrity of content before publishing. Catches fabricated statistics, dead URLs, misattributed sources, and company claims that contradict the brand DNA.
日本語の概要は準備中です。原文の説明を表示しています。
Read the system-architect map: a deterministic catalog of everything the setup is made of (vault, import scripts, scheduled tasks, MCP servers, SQLite databases, hooks, skills, dashboards), what is healthy and what fell off. Consult it before changing shared infrastructure and re-scan after. Triggers: "/arch", "/arch broken", "/arch scan", "what broke in the system".
日本語の概要は準備中です。原文の説明を表示しています。
LLM-judge stage of an alpha-mining pipeline: take a miner's deterministic candidate list, keep only real signal, drop noise, and propose additions to that miner's curated note. Use after any zero-token detector run. Reads only the candidate digest and the home note, never the corpus. Triggers: "/alpha-judge <miner>", "judge the candidates".
日本語の概要は準備中です。原文の説明を表示しています。
Print a ready-made /compact line in a canonical handoff format, so the operator pastes it as the next message and shrinks working memory without losing the thread. Use at the end of a long session. Triggers: "/cc", "compact", "finish via compact".
日本語の概要は準備中です。原文の説明を表示しています。
Run a daily accountability loop grounded in the owner's identity layer in the vault: a morning kick (mirror, one rock for the day, known-pitfall guard) or an evening review (what moved, what slipped, tomorrow's rock). Triggers: "/coach", "morning review", "evening review", "keep me on track".
日本語の概要は準備中です。原文の説明を表示しています。
Takes existing content markdown files and builds production-final resource center pages on client websites using their existing tech stack and design system. Output is live-ready — no review pass, no placeholder content, no prototype styling. Implements hub pages, section listings, article pages, and cross-linking for Blog, Guides, Learn, and Comparisons sections.
日本語の概要は準備中です。原文の説明を表示しています。
Recover a session after a hard crash (app died, machine rebooted, context lost mid-work): replay the turn-state ledger for the last requests, files and decisions, run a green/red health ping over the system map, file sync and MCP connectors, then rebuild the previous session history for pickup. Triggers: "/1", "resume after crash", "wake".
日本語の概要は準備中です。原文の説明を表示しています。
Look up the registry of declined and deferred decisions, so the same idea is never re-pitched: what was rejected, why, and under what condition to revisit. Read-only, and can also run the detector for new rejections in recent sessions. Triggers: "/declined", "did we reject this before".
日本語の概要は準備中です。原文の説明を表示しています。
Build a dashboard from idea to live link in one pass: create the visualization, file it in one shared catalog, cross-link it with the others, publish to GitHub Pages and return the working URL right away. Use when results carry more than one fact to decide on. Triggers: /dash, build a dashboard, show it visually, publish the dashboard, give me the dashboard link.
日本語の概要は準備中です。原文の説明を表示しています。
Sync CRM knowledge notes in a vault with the live CRM code repositories: pull the read-only repos, detect which changed, and refresh only the affected reverse-engineering notes and the keep/drop/decide note. Triggers: "/crm-sync", "refresh CRM knowledge", "what changed in the CRM code".
日本語の概要は準備中です。原文の説明を表示しています。
Creates data visualizations (charts, graphs, tables) optimized for AI engine parsing and citation. Produces inline SVG/HTML with text summaries, data tables, and JSON-LD so AI engines can quote the data.
日本語の概要は準備中です。原文の説明を表示しています。
Watch incoming feedback from outside engineers on your open-source repos: comments, reviews, issues, mentions. Use when you need to find who replied to your pull requests or issues, triage human versus bot responses, and answer within a day with evidence.
日本語の概要は準備中です。原文の説明を表示しています。
Drive the current task to a verified result instead of stopping at a plausible report. Use when the user says /continue, keep going, not done yet, push further, or is unhappy with the result. Rebuilds requirements from the conversation, re-checks real state, fixes root causes, verifies from the consumer side, offloads side quests.
日本語の概要は準備中です。原文の説明を表示しています。
After shipping a repo, release or feature, find who on GitHub actually needs it: search issues, discussions and catalogs for the symptom, rank live threads and draft one precise reply per consumer. Use right after any artifact goes public. Triggers: /consumer-hunt, /ch, find consumers, where to submit.
日本語の概要は準備中です。原文の説明を表示しています。
Work the comments under published posts in one pass: list unanswered ones, reply only where a reply is genuinely expected (at most three per pass), name top commenters as warm-DM candidates, and prepare reply drafts on approval. Triggers: "/comments", "unanswered comments", "who is commenting".
日本語の概要は準備中です。原文の説明を表示しています。