Claude Skills by mishahanin

Objective-defect detector for the memory ecosystem (auto-memory + Odin brain). Runs scripts/memory-hygiene.py, which flags ONLY mechanically-verifiable rot - dangling/circular superseded_by refs, orphan memory files not linked from MEMORY.md, and an over-budget MEMORY.md - into a dated report, and exits non-zero when any are present. It never mutates memory. Use when the user says "memory hygiene", "check memory health", "memory rot", "scan memory for defects", or wants to know whether the me...

Change the reported IMEI on a configured GL.iNet travel router (GL-XE300 or GL-E5800, auto-detected) for work testing. Generates a fresh, never-reused device-class IMEI locally (TAC from per-device config), connects to the modem over SSH, records the outgoing IMEI with a timestamp, applies the change, confirms the device AND the reset with the operator, resets the modem, and verifies the new IMEI is live. EXPLICIT INVOCATION ONLY via /modem-tune. Personal-hardware tool: dormant on any instanc...

Benchmark Mullvad VPN relays by real network latency and connect on selection. Default invocation (/mullvad with no args) detects current connection state, disconnects if needed for an unbiased measurement, runs the parallel ICMP benchmark via scripts/mullvad-fastest.py, and presents the 3 fastest servers as a numbered menu. When the user replies with "connect 1", "connect 2", or "connect 3" (or an equivalent natural-language selection from the 3 shown), the skill executes mullvad relay set l...

State-aware "what's next" recommender. Reads what just happened (the session handoff pointer, the newest outputs/ files, recent git commits, active business threads) plus the skill-relationship catalog, then names the logical next step(s) and the exact slash-command to run -- "you finished X, the next step is Y, run /Y." Read-only: it recommends commands, it never runs them. Use when the user says "what's next", "what should I do now", "where were we", "logical next step", "recommend next", o...

Google NotebookLM CLI integration. Creates topic notebooks, adds sources (URLs, text, files), queries with grounded citations, generates audio overviews (AI podcast), runs research discovery, generates briefing reports, downloads artifacts. CEO-only - not synced to exec workspaces. Uses undocumented Google APIs via notebooklm-mcp-cli CLI tool. Triggers on "notebooklm", "audio overview", "podcast from sources", "create a notebook", "notebook research". Does NOT trigger on generic "research" (u...

Odin - personal AI advisor with persistent knowledge brain. Ingests books, articles, videos, documents. Builds principles and positions. Gives referenced advice prioritizing learned knowledge. Nine modes: learn (ingest material), consult (give advice), reflect (review brain), recall (query brain), teach (direct learning), log (record an episode - something that happened), collect (scan business threads + captured comms for episodes you forgot to log), compile (unified linting across brain and...

Produce a 31C official document (board resolution, formal notice, letter of position, certificate of authority) using the locked corporate template. Authoritative voice, declarative language, reference numbering, and official seal block. Renders to PDF + DOCX. Trigger when the user says "board resolution", "formal notice", "letter of position", "certificate of authority", "official document", "official letter", or describes a document that must be issued under corporate authority.

EXPLICIT INVOCATION ONLY -- never auto-trigger. This skill activates ONLY when the user literally types '/osint-advanced' or says 'run osint-advanced'. DO NOT trigger from 'investigate', 'research', 'dig into', 'OSINT', 'intelligence on', 'background check', 'due diligence', 'profile', 'recon', 'dossier', 'deep dive', or ANY general intelligence request -- those belong to /osint. This skill queries specialized OSINT databases (sanctions lists, corporate registries, breach databases, threat ac...

Deep OSINT intelligence gathering on any target - company, person, market/region, or technology. The master intelligence skill that feeds all other intel skills. Produces executive-grade intelligence briefs with confidence ratings, source attribution, and 31C business relevance. Use when the user says 'OSINT', 'investigate', 'dig into', 'deep dive on', 'intelligence on', 'find out everything about', 'who is', 'what do we know about', 'research [company/person/market/tech]', 'background check'...

Produce a 31C partnership document (MOU, Letter of Intent, or term sheet) using the locked corporate template. Legal-adjacent document defining mutual obligations, governance, territory, exclusivity, and confidentiality between 31 Concept and a counterparty. Renders to PDF + DOCX. Trigger when the user says "MOU", "LOI", "memorandum of understanding", "letter of intent", "term sheet", "partnership agreement", "partnership document", or describes a collaboration framework with mutual obligatio...

Export a Pencil (.pen) deck to PNG + PDF + PPTX + a self-contained HTML on WSL. PNG and PDF come from Pencil natively through the execute tool. PPTX defaults to an EDITABLE twin (identical look, native editable text, brand fonts embedded); the image-per-slide locked-look PPTX is opt-in via pptx-flat. The PPTX and self-contained HTML branches dump the frames to one HTML, then scripts/pencil-export.py renders each frame in isolation via chromium and assembles the formats. Pencil never receives ...

Drive a real browser for a SCRIPTED, non-interactive job: screenshots, scraping a JS-rendered page, filling a form, PDF from a page, or reading a YouTube video's transcript. Do NOT use for a plain URL fetch that WebFetch already handles, and do NOT use for live interactive browsing (clicking around a session by hand) - that is agent-browser.

Generate and edit presentation slides as PPTX files. Also create LinkedIn carousels and manage reusable slide layouts. TRIGGERS - Use this skill when user says: - "create slides for [brand]" / "generate presentation for [brand]" / "make slides for [brand]" - "create a carousel for [brand]" / "linkedin carousel" / "make a carousel about [topic]" - "edit this pptx" / "update the slides" / "modify this presentation" - "create a new layout" / "add a layout to the cookbook" / "make a [type] layou...

Initialize a working session. Loads full workspace context (personal info, business, strategy, current data, pipeline, key contacts, datastore index), runs CRM and sync health checks, surfaces what needs attention, and lists available skills with recommendations for the day. Use at the start of every working session. NEVER auto-trigger from natural language - this is an explicit "/prime" command only.

Produce a branded 31C proposal (PDF + DOCX) for a commercial deal or partnership using the locked corporate template. Covers sales, partnership, channel, and government proposal types with executive opening, opportunity framing, solution structure, pricing with Voss precision, and next steps. Trigger when the user says "write a proposal", "draft a proposal", "partnership proposal", "sales proposal", "commercial proposal", or asks to prepare a formal business proposal. For MOU / LOI / term she...

CEO-only: publish workspace content to all executives via the corporate repo. EXPLICIT INVOCATION ONLY - never auto-trigger.

CEO-only: Publish workspace updates for all executives. Single command that commits the engine clone and the data overlay, classifies, publishes corporate-routed content to the corporate repo, bumps BUILD.json, pushes both repos through scripts/push-all.py, refreshes the operator's own CRM aggregate, and reports. Each executive then pulls; this command drives no exec workspace. EXPLICIT INVOCATION ONLY - never auto-trigger.

Compose a short message and deposit it into the Action Queue as a GATED draft card that waits for an explicit human approve before it can ever send. Use to stage an outbound draft (e.g. a demo email) for later review, and as the reference draft-tier skill the headless runner (`heading skill queue-draft`) exercises. NEVER auto-trigger - explicit `/queue-draft` (or an explicit headless run) only. It deposits a draft; it NEVER approves, sends, or calls a send transport.

Terminal-native Action Queue - the one lane where proactive agents (cold-sweep, email-intel, viraid) deposit drafted actions for the CEO's go/no-go. Runs scripts/action-queue.py to list drafts, show one, approve (= SYNCHRONOUS send, watched, in the same command), edit a draft, dismiss, or retry a failed send. Daemon-free and browser-free. Use when the user says "queue", "action queue", "show my drafts", "what's waiting to send", "approve/send the first one", "retry that failed send", or wants...

Manual-actions + silent-health detector. Runs scripts/ops-radar.py, which surfaces which high-consequence MANUAL actions are objectively overdue (backup, publish-to-fleet, weekly-review, cold-sweep, Odin collect/reflect) and which machine-domain states have degraded (ollama down, memory-index stale), self-healing the latter (Tier A) and nudging only on exception for the former (Tier B), counts-only. Use when the user says "radar", "ops radar", "what's overdue", "what do I need to run", "what ...

Semantic recall across the whole workspace - Odin brain, threads, CRM, context, plans, outputs, knowledge and auto-memory - answering only from retrieved sources with file citations, or saying \"not in memory\". Use for \"what do we know about X\", \"where did we decide Y\", \"have we touched Z before\". Do NOT use for counting or aggregating across many files, where the answer sits in no single chunk - that is /census. Do NOT use for Odin-brain-only advice - that is /odin.

Request a new skill from the CEO - describe what it should do, and the request is emailed to the admin. EXPLICIT INVOCATION ONLY - sends external email.

Produce a structured response to a formal Request for Proposals or government tender. Maps requirements to ODUN.ONE capabilities, drafts executive summary, technical response, commercial proposal, and compliance matrix. Use when responding to an RFP, ITT, government procurement, or formal bid. Trigger when the user says "RFP response", "respond to this tender", "bid response", "government tender", or pastes RFP requirements.

Ultrathink principal-engineer review gate. Runs a Validate-Identify-Improve-Adjust (VIIA) pass over a target - a plan awaiting approval, just-executed work, a specific file or directory, or the entire workspace - then runs an adversarial refutation layer (Phase 2.5) with cross-family judge rotation (Claude and Kimi k3) and optional two-agent debate on BLOCKER + HIGH findings before presenting findings with concrete proposed fixes for batched approval. Blocks forward progress until approved. T...

Manage the Sentinel background daemon that monitors corporate email (Exchange) and Telegram for urgent messages. Start, stop, check status, view logs, and configure monitoring. EXPLICIT INVOCATION ONLY - daemons live on the always-on service host and are off-limits without CEO sign-off.

Import logged-in cookies from a real Chromium-family browser (Brave, Chrome, Chromium, Edge) into the workspace's Playwright/headless cookie store at outputs/browser/cookies.json, using the workspace-native scripts/utils/chromium_cookies.py reader. Use before QA-testing or scraping pages that require an authenticated session. For the browser automation itself use /playwright.

Interactive setup wizard for HEADING OS and 31C exec workspaces. Walks the user through ~22 questions (public) or ~9 questions (exec), enriches short answers into rich docs, captures API keys securely, and produces a completion-% dashboard on re-runs. Refuses to run on the CEO master workspace. EXPLICIT INVOCATION ONLY - mutates workspace skeleton (.env, reference/, context/, personal/).

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, update or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. EXPLICIT INVOCATION ONLY - mutates workspace skill infrastructure.

Diagnostic assessment of a workspace operational function or the whole system - a 15-minute State Check in the Navigation Principle sense, reporting operational state, drift, and course corrections rather than rigid pass/fail targets. Use when the user says "state check", "how are we doing", "operational state", or "function health". Do NOT use for the full morning briefing (use /dashboard), full context load (use /prime), or end-of-week review (use /weekly-review).

Manually trigger workspace sync - git pull of the code/data clones, then a push-all backup. EXPLICIT INVOCATION ONLY - never auto-trigger.

Use this skill to communicate via Telegram as Misha's personal account. Handles all Telegram messaging: send messages to contacts or groups, read conversations, check unread, search message history, forward messages between chats, reply to specific messages, send files/photos, download media, list chats/groups, view contacts, and mark as read. This is a live Telegram client that sends and receives real messages on Misha's behalf. Trigger for any request to interact with Telegram as a user: se...

Open, log, close, find threads in the operational threads registry. Triggers on 'open a thread', 'log to the [name] thread', 'close the [name] thread', 'thread list', 'thread find'. NOT for: single emails (use /email-draft), notes (use /zk), CRM logs (use /crm).

Translate text between Russian and English (or other languages on request), preserving register, tone, and meaning rather than producing a literal word-for-word rendering. Use when the user wants a passage translated. Trigger when the user says "translate", "translate this to Russian/English", or pastes Russian text that needs an English rendering (or vice versa). Do NOT use for drafting new content (use the relevant content/comms skill).

Draft an internal message to the 31C Tribe in Misha's voice - heading-setting, Navigation-Principle framing, maritime register where natural. Use for any internal all-hands or Tribe-wide communication. Trigger when the user says "tribe message", "message to the tribe", or "write to the tribe". Do NOT use for the recurring Monday cadence message (use /tribe-monday) or external-facing content (use /linkedin-post, /corporate-letter).

Draft the recurring Monday Tribe message - the weekly heading-set for the 31C Tribe, framing the week's operational state and priorities in Misha's voice. Use specifically for the weekly Monday cadence. Trigger when the user says "monday message", "weekly tribe message", or "monday tribe". Do NOT use for an ad-hoc, non-Monday Tribe message (use /tribe-message).

Fact-check a draft against the DataStore source documents and flag every claim that has no backing source. Use before anything external ships. For structure and argument order use /editorial-review.

Viraid virtual assistant -- reads new messages from M's VIRAID Telegram channel, analyzes and categorizes each message (CRM action, calendar, task, research, note), enriches with workspace context (CRM contacts, calendar policy, pipeline), proposes actions for approval, then executes (write tasks, log CRM interactions). Supports `/viraid sweep` to review and triage active tasks. Use when the user says 'viraid', '/viraid', 'check viraid', 'process viraid', 'viraid messages', 'what's in viraid'...

Tactical negotiation and conversation coaching engine based on Christopher Voss's FBI methodology. Produces situation-specific playbooks with accusation audits, calibrated questions, labeling scripts, and scenario maps. Use when preparing for any important conversation - deal negotiations, difficult internal discussions, investor pitches, partnership talks, conflict resolution, or any high-stakes communication. Trigger when the user says "voss", "negotiate", "prepare for negotiation", "tactic...

CEO weekly review -- sea state, heading, pipeline movement, Tribe state, content cadence, priorities, and continuity tracking. Use at the end of each week (Friday) or start of the next (Sunday/Monday). Saves the completed review to outputs/operations/reviews/ for longitudinal tracking.

EXPLICIT INVOCATION ONLY -- never auto-trigger. Comprehensive deep audit of the entire workspace producing an 8-section report (executive summary, methodology, inventory matrix, architectural findings, Context7 validation, 2026 best-practices gap analysis, competitive mapping, prioritized recommendations). This is the heaviest workspace skill - dispatches up to 7 parallel inventory agents, runs Context7 validation on every external pin, scores 34 best-practice points, produces a markdown + br...

On-demand X.com (Twitter) intelligence scanner. Fetches recent posts from a curated, categorised YAML account list (peer CEOs, DPI competitors, sovereign-tech thinkers, AI policy figures, personal interest), applies a two-stage engagement-then-judgement filter via Apify, and produces an MD/HTML/PDF brief with top-3 highlights, per-category breakdown, and 31C relevance + actions. Use when the user says "x-pulse", "/x-pulse", "what's on X", "scan X for", "twitter pulse", "what are [accounts] sa...

Produce a 31C OnePager (xPager) using the locked corporate template. Three-page branded document - dark full-bleed cover with ODUN.ONE wordmark, capability page, and proof/contact page. Renders to PDF + HTML. Trigger when the user says "xPager", "x-pager", "onepager", "one-pager", "1-pager", "product one-pager", "capability sheet", or asks for a single concise branded summary of a 31C product, module, or offering.

Domain-agnostic YouTube intelligence scanner. Searches YouTube for videos in any topic area (AI, DPI, cybersecurity, markets, sailing, etc.), identifies trending topics, ranks videos by engagement quality, deep-analyzes the top video with full transcript extraction, and delivers an actionable intelligence brief in MD, HTML, and PDF formats. Automates daily YouTube scanning. Use when the user says "yt-pulse", "youtube pulse", "scan YouTube for", "what's trending on YouTube about", "YouTube int...

Zettelkasten knowledge base - add, enrich, find, connect, distill, garden, stats, and brief across the knowledge/ second brain shared with Zettlr. Use when the user says "zk", "add a note", "knowledge base", "distill this", "garden", "what do we know about", "connect this to", or asks to capture an idea, insight, signal, or decision. Also use when processing outputs from other skills into durable knowledge.

Draft one LinkedIn post in Misha's voice. Use when the ask is a single standalone post. For a multi-post plan with a shared arc use /linkedin-series; to file a post that is already published use /linkedin-archive.

Plan a multi-post LinkedIn series - three or more posts with one arc and a publishing order. Use when the ask names a week, a plan, or a post count. For a single post use /linkedin-post.

Сохранить manual checkpoint текущей сессии в outputs/operations/handoff-archive/ без выполнения /compact. Используй когда хочешь зафиксировать состояние работы и иметь возможность вернуться позже с чистым контекстом. NEVER auto-trigger - вызывается ТОЛЬКО явной командой /checkpoint.

Initialize a working session. Loads full workspace context (personal info, business, strategy, current data, pipeline, key contacts, datastore index), runs CRM and sync health checks, surfaces what needs attention, and lists available skills with recommendations for the day. Use at the start of every working session. NEVER auto-trigger from natural language - this is an explicit "/prime" command only.

Parse documents (PDF, DOCX, PPTX, XLSX) with spatial bounding boxes via LiteParse. Answer questions with visual citations showing exact source locations on page images. Generate 31C-branded HTML/PDF reports. Maintains a parse cache for efficiency. Use when: "parse this document", "docparse", "visual citations", "show me where it says", "document analysis with citations", "parse with bounding boxes", "extract from this PDF". NOT for: plain text extraction without spatial data (use datastore-ex...

Market or regional intelligence brief for a sector or geography - TAM/sizing, competitive landscape, regulatory environment, entry timing, and 31C positioning, framed through the sovereign/DPI+ lens. Use for sector- or region-level analysis, not a single company. Trigger when the user says "market intel", "market for [sector]", "regional analysis", "sector overview", or "TAM for [sector]". Do NOT use for a specific named company (use /competitor-intel or /osint) or global geopolitical briefs ...