Productivity

kesslernity Bundle

Turns plain-language requests (emails, chat messages, form submissions, meeting asks, voicemail or call notes) into one intake record per request (what is asked, who asks and for whom, urgency as evidenced, category, suggested owner, missing information with draft clarifying questions) and a triage table sorted for the operations lead to act on. Use when the user asks to "log these requests", "triage this pile of asks", "turn this message into an intake record", "who should own this request", "what is missing before we can start" or "build today's intake list". Do not use for customer support tickets, use ticket-triage-pack instead; for clearing a personal mailbox by reply bucket, use inbox-triage. Drafts for human review; never approves, authorises or signs off.

kesslernity Bundle

Reviews a RAID log (risks, assumptions, issues, dependencies) line by line and returns a DRAFT review pack: which entries are stale, overdue, duplicated, ownerless, incomplete or misfiled, why, and a proposed update per line as current text against proposed text with the decision the project manager must take. Never re-rates, closes, merges or edits the log. Use when the user asks to "review the RAID log", "clean up the risk log", "health-check the RAID log before the steering meeting", "which risks are stale", "find duplicate risks" or "refresh the issue log". Do not use for setting up a new RAID log or logging a single new risk, issue or decision, use project-status-tracker instead. Drafts for human review; never approves, authorises or signs off.

takusaotome Bundle

Generic helpdesk first-response skill for creating KB-based response drafts. Use when handling support tickets, creating response templates, or building a structured helpdesk workflow. Supports error code detection, keyword matching, confidence scoring, multi-language templates, and escalation workflows. Customize by providing your own KB articles and configuration.

takusaotome Bundle

Track and update action item status from natural language updates like 'Seanのメールには返信しておいた' or 'Lu対応予定'. Integrates with daily-comms-ops workflow. Use when managing action items across communication channels.

takusaotome Bundle

Analyze inbox emails to identify action-required items, prioritize by urgency/importance, classify by topic, and draft contextual replies. Use when triaging unread emails, prioritizing inbox, generating response drafts, or tracking email response status.

takusaotome Bundle

Periodic inbox scan that categorizes new emails by project/client, identifies action-required items, and generates prioritized summary with FYI/requires-response/requires-action/blocked-waiting classifications. Use for inbox overview, project-based email grouping, or action item extraction.

takusaotome Bundle

Compose professional internal emails for coordination tasks like vendor quote requests, task delegation, and follow-up communications. Generates bilingual (JA/EN) email drafts with proper business tone. Use when user needs to draft internal emails for vendor RFQ forwarding, quote compilation requests, status updates, or task delegation.

takusaotome Bundle

Cross-reference project artifacts (WBS, meeting minutes, requirements docs) by date, participant, and action items. Extract commitments from meeting minutes and link to WBS tasks. Generate traceability reports showing which decisions were captured in which documents.

takusaotome Bundle

Transform client hearing sheets and meeting notes into structured requirements documents. Use when converting raw hearing data (Japanese/English) into formal requirements, generating traceability matrices, identifying gaps/ambiguities, and mapping requirements to WBS items. Triggers include "hearing to requirements", "meeting notes to specs", "requirements traceability", "gap analysis for requirements", or requests involving hearing sheet analysis.

desko77 Skill

Добавить объект метаданных в конфигурацию 1С с формой, подсистемой и валидацией. Workflow: meta-compile → cf-edit → subsystem-edit → form-add → form-compile → validate.

desko77 Skill

Маршрутизатор задач по работе с конфигурацией 1С. Определяет нужный workflow или отдельный скил для задачи пользователя.

desko77 Skill

Полный цикл от записи встречи до планов разработки: локальная транскрибация с разбором экрана и скриншотами, извлечение списка задач, отдельный план разработки по SDD на каждую задачу, которой нужен код. Используй ВСЕГДА, когда пользователь дает путь к записи встречи или созвона и хочет получить задачи, план, поручения или разбор - даже если слово транскрибация не прозвучало. Триггеры: разбери встречу, что по итогам созвона, какие задачи со встречи, сделай план по записи, переговоры в задачи, meeting to tasks. НЕ для простой расшифровки речи без задач - там достаточно скила transcribe.

desko77 Skill

Создать новую конфигурацию 1С с нуля - scaffold + объекты + подсистемы + роли + формы. Workflow: cf-init → meta-compile×N → subsystem-compile → role-compile → form-add → validate.

desko77 Skill

Полный цикл создания расширения конфигурации 1С (CFE) - от scaffold до валидации. Workflow: cfe-init → borrow → patch → form → validate.

desko77 Skill

Полный цикл создания внешней обработки 1С - от scaffold до сборки EPF. Workflow: epf-init → form → template → bsp → build.

jorinyang Bundle

AI Native'S Workflow(er) — 7 阶段结构化工作流编排器。适用于任何从零开始的复杂构建任务：新业务/新产品/新技能/新方案/新流程/新系统/调研分析/策略规划/项目启动/决策支持/汇报演示/预算规划/复盘总结/运营营销/品牌策划/架构设计/迭代优化。以 design-flow 编排范式为核心，串联 clarify → brief → architect → standards → decompose → build → review。触发：answer / 梳理思路 / 从零开始 / 帮我规划 / 设计方案 / 启动项目 / 拆解问题 / 写方案 / 做BP / SOP / 做复盘 / 运营方案 / 营销计划 / from scratch / plan this 等 100+ 关键词。

forexgod21 Bundle

Claude defines and enforces its reliable operational limit before taking on parallel or high-complexity tasks. Beyond a certain span, reliability degrades. This skill makes that limit visible, prevents overextension, and ensures task quality is maintained rather than silently sacrificed for throughput.

forexgod21 Bundle

Claude must honestly assess and communicate its own confidence and capability before accepting or executing a task. Overconfidence and underconfidence are both failure modes. Accurate self-assessment is required.

forexgod21 Bundle

Claude introduces deliberate pause and surface clarity for high-stakes or high-uncertainty decisions. Scales with task criticality — seamless for low stakes, friction-heavy for high stakes. Prevents autopilot execution on decisions that deserve deliberate thought.

forexgod21 Bundle

Use for any task involving Google Sheets or Google Apps Script (.gs files): reading, writing, formatting, or analyzing sheet data; Apps Script automations, triggers, custom menus, sidebars, and custom functions; integrating Sheets with Gmail, Drive, Calendar, or external APIs; import/export; debugging; and batch performance. Trigger on any mention of Sheets, Apps Script, SpreadsheetApp, HtmlService, onEdit, or sheet-level automation — even when the request sounds simple.

forexgod21 Bundle

Claude maintains active awareness of task state across four monitoring levels — operational status, plan alignment, reasoning quality, and full state transparency. The level of monitoring scales with task complexity and stakes. Nothing runs unobserved.

forexgod21 Bundle

When a task is disrupted mid-execution — by a failure, a changed condition, a new priority, or an unexpected result — Claude must diagnose the trigger, assess urgency and reversibility, and select the correct corrective response before continuing. No silent pivots. No automatic retries without reassessment.

forexgod21 Bundle

Locks every response at the absolute output ceiling — no downscaling for simple tasks, casual tone, perceived user level, or session length. Always-on: activate at session start and hold for the entire conversation. Fires on any YVYC doctrine file, CLAUDE.md, or elite/Fortune 100 standard signal, and on every response thereafter regardless of task size.

forexgod21 Bundle

When passing tasks to tools, sub-agents, or external processes, Claude only grants the minimum permissions required for that specific sub-task. No inherited broad privileges. No raw credentials. No full-scope access when partial access is sufficient.

forexgod21 Bundle

Activate whenever the task involves recording, reviewing, or analyzing trading performance — building a trade journal, post-trade review, weekly or monthly performance analysis, evaluating whether a strategy has edge, backtesting review, "why am I losing," or turning trade history into system improvements. Trigger on any request to learn from past trades or measure a trading system. Fire because the journal is the only instrument that can distinguish a broken system from normal variance — and untracked trading is a system that cannot improve, only repeat.

forexgod21 Bundle

Claude has a clear decision tree for when to stop and require human input during task execution. Not every decision escalates — but specific triggers always do. Claude knows the difference and acts accordingly.

forexgod21 Bundle

When a task involves competing objectives, Claude surfaces the conflict explicitly rather than making a silent judgment call. The user sees the tradeoff, decides the priority, and Claude executes against a confirmed hierarchy — not an assumed one.

forexgod21 Bundle

Activate whenever output quality is at risk of scaling DOWN to perceived task size, conversational tone, or session fatigue — "it's a small task" quality reduction, casual-tone casual-work drift, late-session sloppiness, or any standard that flexes with circumstances. Trigger on designing quality standards for a person, team, or AI system, on diagnosing inconsistent output quality, and on any operation where the work must hold one standard across every deliverable. Fire because quality systems fail at their exceptions: the standard that bends for small tasks has announced that it bends, and everything thereafter negotiates.

forexgod21 Bundle

Activate whenever the task involves reading, analyzing, or acting on price charts — pattern identification, trend analysis, support and resistance, wave counts, candlestick reading, multi-timeframe analysis, or "what is this chart telling me." Trigger on any chart screenshot, any technical analysis request, and any Pine Script or indicator work that encodes pattern logic. Fire ESPECIALLY when a pattern is being seen with money already on the line — conviction bias reads charts through the position, and this discipline exists to read the chart that is actually there.

forexgod21 Bundle

Activate whenever the task involves preparing peer supporters, volunteers, mentors, or community workers for moments that exceed their scope — crisis escalation procedures, warm handoff design, scope-of-role training, safety protocol development for peer and community programs, or "what do I do when someone is in crisis." Trigger on any program design that puts non-clinical helpers in contact with people who may experience crisis. Fire at PROGRAM DESIGN time — the moment of crisis is the worst possible time to be designing the crisis response, and every peer program will meet that moment eventually.

forexgod21 Bundle

Activate whenever the task involves assessing, building, or planning around the resources a person or community brings to recovery — strengths-based recovery planning, recovery capital assessment, relapse-risk context mapping, reintegration planning for veterans or returning citizens, or designing recovery community programs. Trigger on "recovery plan," "strengths assessment," "what does this person have going for them," or any planning that starts from deficits and needs reorienting toward assets. Fire because deficit-only planning is the default in recovery services — and it plans around the hole while ignoring the ground the person stands on.

forexgod21 Bundle

Activate whenever the task involves structuring, preparing for, documenting, or improving peer recovery support work — peer specialist (PRSS) session planning, group facilitation for recovery communities, veteran peer support, mutual-aid meeting structure, or training peer supporters. Trigger on "peer support session," "recovery group," "peer specialist," or any request to design how lived-experience support gets delivered. Fire on structure and process questions — this skill governs the FRAME of peer work, and it holds the line that peer support is a discipline with a scope, not clinical care with a discount.

forexgod21 Bundle

Before executing any complex task, Claude must define acceptance criteria, verify the outcome is measurable, and confirm a verification method exists. If a sub-task cannot be verified, it must be decomposed further until it can.

forexgod21 Bundle

Enforces outcome-first learning design on anything meant to teach: curricula, courses, units, lessons, workshops, trainings, tutorials, onboarding sequences, and children's learning content. Trigger whenever the task involves designing, reviewing, or translating teaching material of any kind; whenever learning objectives, lesson plans, or assessments are being written; and whenever existing content must be converted into teachable form for a stated audience. The design order is fixed: name the outcome, define the evidence, and only then build the activity. Activities proposed before outcomes are the defect this skill exists to catch. Applies at every scale, from a semester curriculum to a five-minute explainer, and at every age level. Never assume content is too small to design backward.

ryankolean Skill

Take any complex, messy, or overwhelming process and break it into discrete, ordered, automatable steps with dependencies mapped. Activates when the user says "break this down", "decompose this", "I don't know where to start", or describes a large process they need to untangle. Turns chaos into a task list.

ryankolean Bundle

Capture, structure, and organize ideas from any source (URLs, screenshots, text, voice transcripts, calendar inbox events, iOS Shortcut payloads) into the ryankolean/mindspace GitHub repo. Classifies along two axes (project + idea-type) with emergent tags, auto-schedules High-priority items via Google Calendar reminder-hub conventions, and self-improves by appending to learnings.md after every session. Activates on "brain dump", "capture this", "add to mindspace", "process my inbox", "mindspace review", "what did I capture about X", or when the user shares a URL/screenshot/idea fragment without explicit instructions.