folder-finder
Use when user asks "where should I put this?" or wants to add new content. Automatically analyzes content type and recommends appropriate folder in chrome-extension-tcs (algorithms/client_cases/data_sources). Ensures proper organization by division and purpose.
fireflies-calls
Use when user says "find calls about [topic]", "get transcript for [meeting]", or "show calls with [person]". Automatically searches and analyzes Fireflies.ai call recordings. Extracts transcripts, summaries, action items, and meeting insights.
dts-raw-redash
Query raw DTS PostgreSQL via Redash tools.improvado.io. Use when user says "DTS raw", "DTS tables", "agencies table", "connections table", "dsas_extraction", "query DTS", "Redash tools".
dts-postgres
Query DTS PostgreSQL via Redash API for marketing data warehouse. Use when user says "DTS Postgres", "Redash query", "marketing warehouse", "funnel analysis".
claude-code-sessions
Use when user says "resume session", "what did I work on", "find conversation about [topic]", or "get my messages". Automatically searches, resumes, and analyzes Claude Code sessions. Handles session discovery, content search, automatic session restoration, and message extraction.
banner_text_copy
Generate structured banner ad copy and LinkedIn post text from landing pages and audience context. Use when user says "banner copy", "ad copy", "headline variants", "/banner_text_copy", or asks to prepare copy for banner design.
banners_design_nb
Generate Improvado marketing banner designs via HTML rendering, AI image generation (fal.ai), or Gemini batch generator. Use when user says "generate banners", "design banner", "/banners_design_nb", or asks for Google Ads creatives.
bee-daily-journal
Generate daily journal from Bee conversations + Google Calendar. Use when user says 'daily journal', 'journal for [date]', 'summarize my day', 'что я делал [дата]', 'дневник за [дату]'. Creates structured summary with Calendar vs Bee comparison, timeline Gantt, mind map by meetings/people, and action items.
claude-command-dispatcher
Use when the user asks to run or reuse a Claude Code custom command from .claude/commands (for example '/plan', '/tasks', '/specify', '/chat_sum'). Dynamically resolves any command file in .claude/commands without hardcoded command names.
claude-task-from-logseq
Execute autonomous tasks received from Logseq automation and write results back using PAGE_UUID-safe updates. Use when user says "execute Logseq task", "выполни задачу из логсек", or prompt contains AUTONOMOUS MODE with PAGE_UUID.
client-intelligence
Generate comprehensive project intelligence for Improvado clients. Use when user says "analyze client [name]", "client overview", "project intelligence for [client]", "what's happening with [client]". Automatically finds client folder, queries all context (Gong, Jira, emails), identifies 3-9 projects (MECE), generates detailed reports per project, and creates executive summary.
company-intelligence
Unified company intelligence pipeline that auto-detects stage (prospect/active/dual) from SFDC, runs stage-appropriate prompts, and outputs to Obsidian vault. Use when user says 'company intelligence for [domain]', 'deal brief for [prospect]', 'analyze [company]', 'what do we know about [company]'. Merges Deal Intelligence Brief (prospects) and Client Intelligence (active customers) into one skill.
deploy-lps-vercel
Deploy paid ads landing pages (`paid-ads-lps`) to Vercel via API script without dashboard clicks and without large local uploads. Use when user says "deploy lp", "задеплой лендинг", "deploy paid-ads-lps", "обнови lp.improvado.io", or asks for fast/stable Vercel LP deploy.
deploy-miras-vercel
Deploy Miras dashboards to Vercel. Use when user says "deploy miras", "vercel deploy", "deploy dashboards", "задеплой miras", "обнови дашборды". Handles production deployment with status reporting.
download-session-from-drive
Download and import Claude Code sessions from Google Drive. Browse available sessions with metadata, select desired session, and automatically install to current project for immediate resume. Use when recovering archived sessions, importing shared sessions from colleagues, or resuming work from different machines.
gong-call-analyzer
Use when user says "analyze Gong call", "extract call transcript", "summarize customer call", "find calls with [client]". Automatically searches Gong calls in ClickHouse, extracts transcripts, creates summaries, and organizes in proper client folder structure.
gong-to-jira-notion
Run Gong to Jira/Notion pipeline to extract call insights and action items. Use when user says "process Gong call", "gong pipeline", "gong to jira", "запусти пайплайн", or provides a Gong call URL for processing.
google-ads-experiments
Create and manage Google Ads A/B experiments via API. Use when user says 'A/B test', 'google ads experiment', 'split test campaign', 'эксперимент гугл', 'A/B кампании', or asks to test landing pages, ad copy, keywords, bids in Google Ads.
google-chat
Send and read Google Chat messages to Spaces and DMs. Resolve person names via ClickHouse. Use when user says 'send gchat', 'read google chat', 'DM [person]', 'gchat [space]', 'отправь в чат', 'прочитай чат'.
graph-add
Smart content addition to Obsidian vault via 2-pass Gemini. Phase 1: navigate vault tree, Phase 2: expand + decide + write content. Claude reviews and executes. Use when user says: 'add to vault', 'save this to obsidian', 'добавь в обсидиан', 'create vault page', 'graph add', 'запиши в vault'.
graph-find
Parallel multi-algorithm Obsidian vault search. Without arguments — auto-summarizes current session and maps it to vault nodes. With query — runs 3 search methods in parallel (LLM semantic, MCP text+dataview, filesystem), deduplicates & ranks results. Use when user says: 'find in vault', 'what do we have about [topic]', 'найди в обсидиане', 'search obsidian', 'vault search', 'найди контекст', 'graph find', 'map session'.
logseq
Operate Logseq workspace by reading and writing pages, searching blocks, and running graph analytics. Use when user says "add to Logseq", "create Logseq page", "search Logseq", "логсек", or "/logseq".
marketing-funnel
Analyze Improvado internal marketing attribution data, build funnel reports, and perform channel performance analysis. Use when user says "marketing funnel", "channel analysis", "marketing ROI", "анализ воронки", "маркетинговый фаннел", "ROI каналов", or requests Improvado marketing metrics, attribution analysis, or quarter-over-quarter comparisons.
mmm-model-builder
Build Marketing Mix Models with PyMC, adstock and saturation transforms, and mandatory out-of-sample validation. Use when user says "build MMM model", "построй MMM модель", "marketing mix model", or asks to train MMM on client data.
multi-agent-orchestrator
Orchestrate parallel CLI agents (Claude Code, Codex, Gemini) for competitive evaluation. Use when user says "run multi-agent", "compare agents", "launch competitive evaluation", "use parallel agents", or complex tasks (>7/10) where multiple approaches exist and best solution matters.
notion-tasks-analyzer
Use when user says "show my zero inbox", "what critical tasks", or "analyze my tasks". Automatically queries Notion for unscheduled tasks, critical/urgent work, priority breakdown, and backlog health metrics. Perfect for daily planning.
notion-tasks-operations
Use when user says 'create Notion task', 'update task status', 'find user', 'my tasks', 'append to Notion page', 'insert block after', 'extract table from Notion'. Tasks DB + block operations + table extraction.
obsidian
Primary knowledge base operations - vault navigation, .base tables, MCP access, entity system. Use when user says "obsidian", "найди в обсидиан", "create page in vault", "query base", "vault structure".
restate-cloud-troubleshooting
Troubleshoot Restate Cloud failures via Admin API, including stuck invocations, determinism errors, and scheduler recovery. Use when user says "restate troubleshooting", "fix restate invocation", "почини restate", or asks to diagnose Restate errors.
session-summary
Summarize Claude Code sessions in Knowledge Framework format with key actions, files, and outcomes. Use when user says "summarize session", "session summary", or asks what happened in the current session.
optimizing-queries
Analyzes and optimizes SQL/NoSQL queries for performance. Use when reviewing query performance, optimizing slow queries, analyzing EXPLAIN output, suggesting indexes, identifying N+1 problems, recommending query rewrites, or improving database access patterns. Supports PostgreSQL, MySQL, SQLite, MongoDB, Redis, DynamoDB, and Elasticsearch.
creating-handoffs
Creates comprehensive handoff documents for seamless AI agent session transfers. Triggered when: (1) user requests handoff/memory/context save, (2) context window approaches capacity, (3) major task milestone completed, (4) work session ending, (5) user says 'save state', 'create handoff', 'I need to pause', 'context is getting full', (6) resuming work with 'load handoff', 'resume from', 'continue where we left off'. Proactively suggests handoffs after substantial work (multiple file edits, complex debugging, architecture decisions). Solves long-running agent context exhaustion by enabling fresh agents to continue with zero ambiguity.
detecting-ai-code
Use when auditing code for AI authorship, reviewing acquisitions/contractors, verifying academic integrity, or during code review - provides systematic tiered framework for detecting fully AI-generated AND AI-assisted code patterns with confidence scoring
debugging-orm-queries
Converts ORM calls to raw SQL and analyzes query performance. Detects N+1 queries, missing indexes, and other anti-patterns. Use when debugging slow queries, tracing ORM-generated SQL, or optimizing database performance for Sequelize, Prisma, TypeORM (Node.js), GORM, sqlc, sqlx, ent (Go), or SQLAlchemy, Django ORM, Peewee (Python).
refining-requirements
Use when PRD is prose-heavy, ambiguous, has scattered file paths, missing API contracts, or says "similar to X" without explanation. Transforms rough requirements into implementation-ready specs. Auto-detects tech stack, validates file paths (EXISTS/CREATE/VERIFY markers), handles greenfield and multi-stack projects. Do NOT use for simple bug fixes, typos, or already-structured Jira tickets with clear file paths and acceptance criteria.
testing-skills-with-subagents
Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes
troubleshooting-kubernetes
Diagnoses and fixes Kubernetes issues with interactive remediation. Use when pods crash (CrashLoopBackOff, OOMKilled), services unreachable (502/503, empty endpoints), deployments stuck (ImagePullBackOff, pending). Also use when tempted to run kubectl fix commands directly without presenting options, or when user says "just fix it" for K8s issues.
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment - applies TDD to process documentation by testing with subagents before writing, iterating until bulletproof against rationalization
code-reviewer
Comprehensive code review skill for TypeScript, JavaScript, Python, Swift, Kotlin, Go. Includes automated code analysis, best practice checking, security scanning, and review checklist generation. Use when reviewing pull requests, providing code feedback, identifying issues, or ensuring code quality standards.
generating-adrs
Use when PRD/TRD contains architectural decisions to document - extracts decisions from refined requirements (architecture choices, data model decisions, API patterns, technology selections, integration strategies, reuse patterns) and generates MADR-format ADRs. One ADR per decision point. Also use when asked to document decisions, create decision records, or retrospectively capture architectural choices.
interviewing-plans
Use when a plan, PRD, or spec has vague requirements, undefined terms, or missing details - conducts structured interview using AskUserQuestion to surface hidden assumptions, challenge ambiguities, and produce implementation-ready specs. Also use proactively when encountering plans that say things like "make it faster" or "improve UX" without concrete definitions.
prd-to-ralph
Use when converting PRD/requirements into JSON format for Ralph Wiggum autonomous loops. Extracts user stories, orders by dependency (schema first, then backend, then UI, then dashboard), auto-adds standard criteria (typecheck, build, lint, tests), outputs structured JSON ready for autonomous iteration.
office:onboarding
Set up your personal productivity style and preferences. Use when you first install office or want to customize your workflow patterns.
office:email-management
Handle email tasks (checking inbox, drafting replies, managing threads, adding events to calendar). Use when working with emails to prevent common mistakes like broken threading or missing recipients.
office:crm-management
Manage contacts, companies, deals, and relationships. Use when adding contacts, logging interactions, or working with CRM data to prevent duplicates and maintain data quality.
office:calendar-management
Manage calendar events, check conflicts, handle scheduling from emails. Use when adding events or coordinating meetings to ensure proper timezone handling and conflict detection.
pda-reframing
Rephrase tasks and requests by avoiding Demand Avoidance triggers for someone with PDA autism spectrum disorder. It transforms demands into exploration and autonomous actions.
agent-history
Search and analyze Claude Code conversation history. Use when user asks about past conversations, previous solutions, what was discussed earlier, finding something from history, or analyzing usage patterns. Triggers include "what did we discuss", "find that conversation", "search history", "past sessions", "how much time", "token usage", "which tools".
file-to-base64
Convert files (PDF, images) to Base64 encoding with MIME type detection for API attachments. Use when you need to prepare file attachments for the FreeAgent API or any other API that requires Base64-encoded files.
decision-tracker
Git-powered state awareness - track file changes, session context, decisions, and work history. Query what happened in previous sessions and during current session. Auto-activates for state queries and before duplicating work.
Page 1252 of 1607 · 80307 results
