Initialize or update Titan Memory Loom records as candidate memory with source refs, confidence, and authority warnings.
Propose redaction, tombstone, or pruning candidates for Titan memory without silent deletion or canon rewrite.
Gate Forge workspace-write work with explicit intent, target paths, prechecks, validation, and rollback or stop posture.
Retrieve Titan candidate memory records with source, record id, authority note, confidence, and verification path.
Create, validate, note, or close Titan session receipts as witnesses rather than final truth. Use when a Titan service-cohort route needs this explicit bounded step.
Activate Forge mutation or Delta judgment lanes only through matching explicit runtime gates on a Titan receipt.
Begin an explicit Titan service-cohort session with Atlas, Sentinel, and Mneme active and Forge or Delta locked.
Bind Titan bridge events, approvals, and replay state to explicit thread and turn ids for inspectable continuity.
Tito integration. Manage data, records, and automate workflows. Use when the user wants to interact with Tito data.
Helps the TiyCode AI agent understand itself as a product — what it is, what tools it has, how to manage MCP servers, skills, and config files, and how to guide users through…
Create tldr summaries for GitHub Copilot files (prompts, agents, instructions, collections), MCP servers, or documentation from URLs and queries.
使用 tlsx 进行 TLS 证书和配置分析。当需要提取 SSL/TLS 证书信息（SAN/CN）、检测 TLS 版本、加密套件、JARM/JA3 指纹、证书错误配置时使用。tlsx 是 ProjectDiscovery 出品的 TLS 探针工具。任何涉及 SSL/TLS 分析、证书信息收集、JARM 指纹的场景都应使用此技能
TMetric integration. Manage data, records, and automate workflows. Use when the user wants to interact with TMetric data.
Open Chrome, navigate to ChatGPT LG13 project, open recent conversations in sequence so Tampermonkey capture script saves them to L:\\LG13\\inbox\\chatgpt\\.
Convert markdown files to visually appealing PDF, Word, or HTML documents with Slovak diacritics support, professional themes (professional, minimalist, technical, basic), and…
Expert tmux session, window, and pane management for terminal multiplexing, persistent remote workflows, and shell scripting automation.
Управление задачами в Obsidian через плагин TaskNotes. Создание, редактирование, фильтрация и удаление задач с поддержкой проектов, приоритетов, дедлайнов и тегов.
Extract CLI command structure from commander/yargs for AI agent skill generation Use when working with agent-skills, cli, commander, documentation, skill-generation, yargs.
MCP server documentation conventions for high-quality generated skills. Use when writing tool descriptions, `_meta.toSkills` annotations, or input schemas for MCP extraction.
Write the current conversation's planning context into a spec.md file with plan directory scaffolding and optional Solo sync. Invoke with /to-spec.
Toast integration. Manage data, records, and automate workflows. Use when the user wants to interact with Toast data.
Cookie-based toast notification system for Next.js. Use when user asks to "show toast", "toast notification", "user feedback after action", "toast after redirect", "success…
帳をおろしてプロジェクトを開始する（STG0 儀式）。 自然言語の意図を構造化された契約に変換し、tobari-session.json を生成する。 エイリアス: /orose, /startproject 「/tobari」「帳をおろす」「/orose」で呼び出される。
Design backlog — add/list/pick design tasks. Writes to .design/TODO.md.
Audit a file for TODO comments, pending work items, or technical debt markers. Useful for checking code readiness before a commit or reviewing task status.
Secure TODO tracker with input validation and safe file operations. Use for task management across sessions.
Automate Todoist task management, projects, sections, filtering, and bulk operations via Rube MCP (Composio). Always search tools first for current schemas.
Manage Todoist tasks, projects, labels, filters, sections, comments, reminders, and workspaces via the `td` CLI.
Check Todoist for tasks due today (and overdue) that involve pinging, emailing, or following up with someone. Auto-draft the emails using meeting context and notify via WhatsApp.
Implements Getting Things Done methodology on Todoist using the Todoist Sync API v9. Automates inbox processing, context labeling, weekly reviews, and project-to-next-action…
Implements Getting Things Done methodology on Todoist using the Sync API v9. Automates weekly reviews, context tagging, and project decomposition into next actions.
Parses natural language task descriptions into structured Todoist API v2 task objects with due dates, priority levels, and project assignments.
Automates Todoist project management using the Todoist REST API v2 and Sync API. Creates task templates, manages recurring workflows, and syncs with external project trackers.
Orchestrates complex task workflows using the Todoist Sync API v9 with incremental sync via sync_token.
Scan codebase for TODO comments and create professional GitHub issues with context
Automate time tracking workflows in Toggl Track -- create time entries, manage projects, clients, tags, and workspaces through natural language commands.
Toggl Track integration. Manage Workspaces. Use when the user wants to interact with Toggl Track data.
Toggle proactive messaging mode. When enabled, Agent proactively sends greetings, task reminders, and key recaps via IM channel.
Add or remove files from .gitignore — with presets for common visibility modes
Fast session-start pre-flight for Toke. Loads project context, runs a health check across Brain + Homer + hooks, and delivers a one-screen briefing so godspeed routes to the…
Token integration. Manage data, records, and automate workflows. Use when the user wants to interact with Token data.
Audit Claude Code configuration to measure fixed-context token overhead and produce a prioritized action plan.
Use BEFORE dispatching 2+ Agent tools, BEFORE writing implementation plans or design specs that will trigger subagents, or whenever the user asks about agent strategy / model…
Token budget tracking and enforcement for Gastown convoy-level execution. Hard limits with pre-execution checking, per-convoy and per-agent tracking, structured stop reasons.
Audit project token usage by area (always-loaded, skills, examples, docs, worktrees, templates, ops bots), surface offenders, emit area-grouped cleanup plan. Trigger /token-review.
Keep compaction budgets under control by compacting incrementally and reinjecting truncated attachments only when the reasoning surface remains stable.
Enforce token quota management at session start with conservation rules, delegation checks, and compression review.
Open the Token Optimizer dashboard. Collects latest session data, regenerates the dashboard, and opens it in your browser.
Handhaaft token-efficiënte workflows: taakclassificatie, Plan Mode, TodoWrite, strikte modelkeuze (goedkoop vs premium), contextgrenzen en rapportage bij complexe taken.
Comprimir respostas para reduzir uso de contexto. Ativa com "modo eficiente", "comprimir respostas", "economizar contexto".
Token integration and implementation analyzer based on Trail of Bits' token integration checklist. Analyzes token implementations for ERC20/ERC721 conformity, checks for 20+ weird…
Map an extracted Figma / source-code token bag onto the active OD design system, producing a deterministic mapping the generate stage can consume.
Token Metrics integration. Manage data, records, and automate workflows. Use when the user wants to interact with Token Metrics data.
Automate Token Metrics tasks via Rube MCP (Composio). Always search tools first for current schemas.
Use when working in a monorepo or large codebase and session token budget is constrained; baseline utilities (grep, cat, git, find) waste 60-90% of tokens vs.
Audit your OpenClaw setup for token waste, context bloat, and cost optimization opportunities
Use for minimizing token usage while preserving quality, through strict context filtering, indexed history retrieval, concise reasoning formats, output budgeting, and low-overhead…
Explique et configure le routing Haiku/Sonnet/Opus pour économiser les tokens. Utiliser quand l'utilisateur s'inquiète du coût ou veut optimiser.
Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary.
For interpreters: separate lexing from parsing, token stream to AST, structured text processing in stages.