AI Agent Workflow Collection

Compare two document versions and produce a structured changelog — no git needed. Use for PRDs, SOPs, contracts, strategy docs. Triggers: 'compare these two documents', 'what changed between versions', 'generate a changelog', 'сравни две версии документа', 'что изменилось', 'сделай changelog'.

Build a comparative feature matrix and gap analysis from a folder of competitor notes (md/txt). Works fully offline — no web access needed. Use when preparing roadmap reviews, competitive analysis sessions, or feature prioritization. Triggers: 'build feature matrix', 'competitive feature matrix', 'compare competitors from notes', 'составь feature matrix', 'матрица фич конкурентов'.

Compile weekly analytics CSV exports from Instagram, YouTube, Google Analytics, LinkedIn, TikTok, Facebook, and Twitter into a narrative performance report: what worked, what didn't, the week's pattern, and concrete recommendations. No code, no dashboards, no API required. Triggers: 'content performance report', 'analyze my content performance', 'what worked this week', 'weekly content report', 'compile my analytics', 'отчёт по контенту', 'что сработало на этой неделе', 'анализ контент-аналитики', 'еженедельный отчёт по контенту', 'скомпилируй аналитику'.

Generates a ready-to-use project-context.md file for Claude Cowork through an interactive interview. Triggers EN: 'create project context', 'new project context', 'context-builder', 'generate context file', 'quick context'. Triggers RU: 'создай контекст проекта', 'новый проект контекст', 'сформируй контекстный файл', 'быстрый контекст'.

Assess the health of your current Claude session context and get a clear action recommendation — no technical metrics needed. Use when your session feels long, Claude seems to be forgetting earlier details, or you are unsure whether to continue or start fresh. Triggers: 'check my context', 'context health check', 'is my context running out', 'should I start a new session', 'проверь мой контекст', 'оценка контекста', 'контекст заканчивается'.

Audit active Cowork plugins and get a keep/disable table. Reduces token usage and cognitive noise. Use when reviewing Cowork setup, adding new plugins, or starting a new project. Triggers: 'audit my plugins', 'cowork plugin audit', 'which plugins to disable', 'аудит плагинов', 'какие плагины отключить'.

Generate a pre-session brief for Cowork: current status, session goal, and prioritised work plan from local project files — before your first real message. Use when starting a session, returning after a break, or needing focus. Triggers: 'session brief', 'prepare my session', 'start my cowork session', 'бриф сессии', 'подготовь сессию', 'что делать в этой сессии'.

Analyze CSV files with business data through a dialogue-based flow — no code, no Python, no plugins. Profiles dataset structure, asks what you want to understand, then delivers numbered insights and a plain-language interpretation. Use when analyzing sales exports, task lists, survey results, CRM data, or any CSV file. Triggers: 'analyze my CSV', 'analyze this CSV file', 'help me understand this data', 'what insights can you find in this spreadsheet', 'проанализируй CSV', 'разбери мой файл данных', 'что в этом CSV', 'помоги понять данные из таблицы'.

Reconstructs a chronological log of every significant decision made across project email threads — what was decided, who decided it, when, and what alternatives were considered. Use when a project manager or team needs a decision audit trail or wants to understand how the project got to its current state. Triggers on "decision log", "what decisions were made", "decision history", "who decided", "decision audit trail", "log of project decisions".

Interactive skill for Cowork that generates a structured delegation…

Transform a metrics snapshot into a board-ready executive narrative tied to revenue and LTV. Generates Headline KPIs, Executive Summary, Revenue & Unit Economics, Trend Analysis, and Outlook sections. Use when preparing board decks, C-suite reviews, or investor updates. Triggers: 'exec metrics report', 'board metrics report', 'C-suite metrics story', 'отчёт по метрикам для борда', 'нарратив метрик для руководства'.

Interpret A/B test results in plain language and get a ship/rollback/extend recommendation with a stakeholder summary. Use when you have experiment results from any analytics tool and need a clear go/no-go decision. Triggers: 'interpret experiment results', 'read my A/B test results', 'should I ship this experiment', 'интерпретируй результаты эксперимента', 'помоги прочитать результаты A/B теста'.

Generate a multi-format feature announcement pack from a single product description — no copywriting experience needed. Produces 4 ready-to-use formats: changelog entry, email, in-app push, and social post. Use when launching a new feature, announcing a beta, or preparing a communication pack for multiple channels. Triggers: 'write feature announcement', 'feature announcement writer', 'generate announcement for my feature', 'напиши анонс фичи', 'создай пакет анонса', 'генератор анонса фичи'.

Helps non-technical Claude users instantly understand any Claude feature or capability.

Generates a project charter from brief, stakeholder answers, and constraints. The charter is the first artifact of the Initiation phase. Once approved, it unlocks dependent tasks: generate-risk-register, generate-project-plan, generate-estimate. Accepts both structured briefs and free-form notes.

Generates a project closure report aggregating data from charter, plan-fact report, risk register, and lessons learned. Last artifact of the Closing phase. Summarizes project outcomes, deviations, realized risks, and lessons.

Generates a communication plan from project charter, project plan, and stakeholder data. Includes stakeholder matrix (influence/interest), communication matrix, and escalation rules. Phase 2 artifact. In MVP stakeholders are extracted from charter; in P1 — from stakeholder-map.md.

Generates a meeting protocol from free-form notes. Extracts decisions, action items, and plan changes. If project plan is available — links changes to WP-xxx/Mx IDs. Phase 3 artifact, but usable in any phase. Independent skill with no upstream dependencies.

Generates a plan-vs-actual report comparing planned and actual project data across three dimensions: timelines, budget, and scope (deliverables). Part of the Closing phase. Output feeds into generate-closure-report. Format: .md, manual data input via chat.

Generates a project plan from the approved charter, scope, and optional duration/resource estimates. The plan is the first artifact of the Planning phase. Once approved, it unlocks: generate-risk-register (mode: detailed) and generate-comm-plan (can run in parallel). Accepts both structured estimates and free-form descriptions.

Generates a risk register from project charter (initial mode) or enriches it with project plan data (detailed mode). Two modes: initial — phase 1 after charter approval; detailed — phase 2 after project plan approval.

Generate a structured weekly status report for all candidates in your hiring pipeline from interview notes and evaluation sheets. Flags stuck candidates, summarizes scores, and recommends next steps. Use when reviewing hiring pipeline, preparing for recruiter sync, or deciding next steps on candidates. Triggers: 'review hiring pipeline', 'hiring pipeline status', 'статус по кандидатам', 'ревью пайплайна найма'.

Turn a folder of articles and industry clippings into a weekly trend signals brief for your product team. Use when preparing for planning sessions or roadmap reviews. Triggers: 'industry trend brief', 'trend signals from articles', 'тренд-бриф из статей', 'создай brief по трендам'.

Aggregate numeric KPIs from local files (.md, .txt, .csv) into a weekly snapshot with delta vs. previous week. Use when preparing weekly reports. Triggers: 'build kpi digest', 'weekly kpi snapshot', 'собери KPI дайджест', 'еженедельный снапшот KPI'.