dkyazzentwatwa

Create REST/GraphQL API endpoint with validation, error handling, and tests. Auto-invoke when user says "add endpoint", "create API", "new route", or "add route".

Generate backend tests (unit, integration, mocks). Auto-invoke when user says "write test for", "add test", "test this", or "create test".

Create database migration with schema changes and rollback. Auto-invoke when user says "create migration", "add table", "modify schema", or "change database".

Create React/Vue component with TypeScript, tests, and styles. Auto-invoke when user says "create component", "add component", "new component", or "build component".

Generate frontend component tests (unit, snapshot, e2e). Auto-invoke when user says "test this component", "write component test", or "add component test".

Clear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits.

Initialize Navigator documentation structure in a project. Auto-invokes when user says "Initialize Navigator", "Set up Navigator", "Create Navigator structure", or "Bootstrap Navigator".

Run tasks until complete with structured completion signals. Auto-invoke when user says "run until done", "keep going until complete", "iterate until finished", "loop mode", "autonomous mode".

Opportunity management, proposals, negotiation, and deal closing

Account growth, retention, upsell planning, and relationship management

Synthesizes intelligence, monitors signals, and produces structured briefs

Blog posts, copy, case studies, email sequences, and marketing assets

Onboarding, health checks, QBRs, renewals, and expansion plays

Metrics analysis, dashboards, reporting, and data-driven recommendations

Manages schedule, meeting ops, briefings, and executive communications

Onboarding, benefits, compliance, culture programs, and HR documentation

Run multi-indicator technical analysis on crypto or market OHLCV data. Use for deterministic trend, momentum, volume, and divergence analysis.

Analyze datasets and turn them into narrative reports with charts, audits, comparisons, and statistical summaries. Use for exploratory analysis and executive-ready outputs.

Convert PDFs, Office docs, markdown, HTML, and tables between editable formats. Use for best-effort document conversion, PDF utilities, form filling, and table extraction.

Run loan, investment, NPV, retirement, savings, and risk calculations with schedules and charts. Use for deterministic financial modeling tasks.

Parse, convert, geocode, visualize, and measure geographic data. Use for address cleanup, geo file conversion, mapping, and distance workflows.

Process images for cleanup, conversion, metadata, comparison, icons, palettes, collages, and sprite sheets. Use for single-image or batch image workflows.

Plan and build MCP servers with agent-friendly tools, schemas, error handling, and evaluation. Use when creating or refactoring MCP integrations.

Process audio and video with clipping, conversion, analysis, captions, thumbnails, GIFs, and batch utilities. Use for practical media manipulation workflows.

Use when the user wants to turn an idea into a fully formed design or spec before writing any code or building anything. Triggers on requests to build a feature, create a component, add functionality, modify behavior, or any creative work that requires clarifying intent, requirements, and design first.

Use when the user asks for captions, emails, sales copy, launch copy, website copy, DMs, scripts, posts, content rewrites, or nurture sequences in a specific brand voice. Also use when the user says things like "write this in my voice", "make this sound like me", "rewrite this", "does this sound on-brand", "too formal", "too robotic", or any request where the output needs to match a specific tone, style, or personality. Also trigger when the user pastes their own draft and wants it improved or adjusted.

Use when the user wants to repurpose a draft, article, transcript, research dump, or outline into multiple platform-specific outputs across Substack, LinkedIn, Threads, Instagram carousel, and Substack Notes.

Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.

Use when the assistant needs to synthesize multiple rough inputs — messy notes, scattered emails, transcript excerpts, meeting context, or uploaded documents — into a concise executive briefing. Especially relevant for founder prep, leadership updates, weekly operating briefs, post-meeting readouts, launch status briefs, partnership updates, hiring or finance summaries, and any situation where conflicting or incomplete inputs must be turned into decision-ready output.

Use when the assistant needs to locate files, inspect folders, summarize drive contents, create or rename folders, move or delete files, manage sharing, detect inherited or external access, clean duplicates, or run organization workflows through connected Google Drive. Connector-first operator for searching, reading, organizing, sharing, auditing, and automating Drive files and folders.

Use when the assistant needs to search, inspect, summarize, create, update, restructure, or maintain Notion pages, databases, tasks, docs, wikis, project trackers, meeting notes, content calendars, or operating systems through the Notion connector. Trigger for requests involving Notion read/write workflows, database updates, page creation, workspace search, status reporting, documentation generation, task management, content planning, or converting messy context into Notion-ready structures.

Use when improving a prompt, rewriting a prompt for better results, generating a prompt from a brief, adapting a prompt for a specific model, diagnosing why a prompt is failing, or producing prompt variants for speed, quality, extraction, reasoning, or creativity. Optimizes rough, under-specified, or inconsistent prompts into stronger prompts with clearer instructions, context, constraints, examples, and output schemas.

Review a local codebase, turn validated findings into small GitHub issues, and order them by fix path. Use when the user wants a code review that produces GitHub issues instead of code changes, especially for requests like "scan this repo and create issues", "do a multi-agent review", "open fix-path issues", or "review without editing code".

Activates a structured multi-agent workflow (Team Lead + specialized Employees) to handle complex tasks that require decomposition, specialized execution, and synthesis. Use when a user request: (1) Involves multiple distinct domains (e.g., research, coding, testing), (2) Is large enough to be split into parallel sub-tasks, (3) Requires high-quality synthesis of diverse inputs. Triggers on requests like: 'Research 3 competitors...', 'Build a feature with backend/frontend/testing...', 'Analyze a business idea with market/risk/monetization agents...'

Run this skill when a Flow Healer run fails or behaves unexpectedly and the user wants a fast, deterministic diagnosis. Use for requests like "triage this healer failure", "why did the run fail", "classify this issue state", or "tell me if this is an environment problem or a product bug".

Run this skill when Flow Healer triage points to connector or patch generation failures and the user wants a deterministic connector-focused debug pass. Use for requests like "debug the connector", "why did the proposer emit no patch", "validate the verifier payload", or "compare proposer and verifier output contracts".

Run this skill when the user wants a guarded live Flow Healer smoke test on a real GitHub repo. Use for requests like "do a live smoke", "test this repo live", "open a real PR through the healer", or "validate issue-to-PR plumbing on GitHub".

Run this skill when the user wants safe local validation before any live Flow Healer action. Use for requests like "run local checks", "validate the healer locally", "do a dry run first", or "make sure the repo is healthy before live GitHub actions".

Run this skill when the user wants to validate or execute a Flow Healer PR follow-up on an existing live PR. Use for requests like "rerun the same PR", "ingest review feedback", "follow up on this healer PR", or "reuse the existing issue and PR after comments".

Run this skill before any Flow Healer live operation when the user wants to validate GitHub auth, repo readiness, Docker, Python environment, open issue/PR surface, and local healer SQLite state. Use for requests like "preflight this repo", "is Flow Healer ready", "check live readiness", or "validate the healer environment before a run".

Use when the user wants Agent Office to route work to the right employee, coordinate multiple employee roles, act like an office manager, or respond as a named employee. Triggers include requests to triage work, decide who should handle something, simulate the office team, delegate across roles, or run the uploaded employee roster as an interactive office.

Use when the user says "run triage", "do daily triage", "process my inbox", "start the day", or asks to delegate today's tasks. Runs the full daily email and task triage workflow.

Use when the user says "health check", "how is the office doing", "check team capacity", "office status", "what's overloaded", or asks for a team overview. Reviews utilization, projects, escalations, and coordination gaps.

Use when the user says "add a new agent", "create a new role", "hire a [role]", "onboard a [role]", or wants to add a new employee to the office. Guides through role definition, capability scoping, coordination setup, and roster update.

Use when the user says "standup", "what's on today", "quick status", "what are we working on", or asks for a snapshot of current work. Generates a fast status report across active tasks, blockers, and agent capacity.

Use when the user says "weekly brief", "weekly summary", "wrap up the week", "how did this week go", or asks for a weekly status report. Synthesizes daily logs and project files into an executive summary.

Core routing and troubleshooting skill for Apple Flow gateways (Mail, Reminders, Notes, Calendar). Use when deciding which `apple-flow tools` command to run, applying shared safety rules, or debugging gateway permissions/resource-name mismatches.

Deep workflow skill for Apple Flow Mail operations. Use for unread triage, message-id content fetch, mailbox/account targeting, label moves, and reply/send flows where deterministic sequencing matters.

General Apple Numbers automation for Apple Flow. Use when working with `.numbers` files through `apple-flow tools`, including creating new sheets, appending structured rows, choosing insertion behavior (`after-data`, `after-headers`, `at-end`), and validating/debugging row placement with read-back checks.

Universal Markdown-to-Apple-Pages formatting skill for Apple Flow. Use when converting `.md` files into polished `.pages` documents with accurate structure (headings, lists, tables, code blocks, links) and clean business-ready styling.

Use when working on Apple Flow in the apple-flow repository. Enforces safe defaults, beginner-first startup, focused debugging, config hygiene, and required verification.

OSINT Investigator v2.1 — comprehensive open-source intelligence skill. Triggers on: OSINT, recon, digital footprint, dorking, social media investigation, username lookups, email tracing, domain recon, entity mapping, OPSEC, image verification, metadata analysis, threat intel, people search, background research. Slash commands: /dork, /recon, /pivot, /entity, /timeline, /analyze-metadata, /verif-photo, /sock-opsec, /report, /simple-report, /full, /track, /link, /entities, /confidence, /export-entities, /import-entities, /compare, /timeline-entity, /find-path, /visualize, /stats, /export-graph, /risk-score, /anomaly, /pattern, /threat-model, /sanitize, /export-risk, /wizard, /template, /simple-mode, /progress, /save-checkpoint, /load-checkpoint, /qa-check, /coverage, /gaps, /verify-sources. Professional playbooks: journalist verification, HR background checks, cyber threat intel, private investigation. Integrations: Maltego, Obsidian, Notion.

OSINT Investigator v2.1 — comprehensive open-source intelligence skill. Triggers on: OSINT, recon, digital footprint, dorking, social media investigation, username lookups, email tracing, domain recon, entity mapping, OPSEC, image verification, metadata analysis, threat intel, people search, background research. Slash commands: /dork, /recon, /pivot, /entity, /timeline, /analyze-metadata, /verif-photo, /sock-opsec, /report, /simple-report, /full, /track, /link, /entities, /confidence, /export-entities, /import-entities, /compare, /timeline-entity, /find-path, /visualize, /stats, /export-graph, /risk-score, /anomaly, /pattern, /threat-model, /sanitize, /export-risk, /wizard, /template, /simple-mode, /progress, /save-checkpoint, /load-checkpoint, /qa-check, /coverage, /gaps, /verify-sources. Professional playbooks: journalist verification, HR background checks, cyber threat intel, private investigation. Integrations: Maltego, Obsidian, Notion.

Use when the user wants viral short clips from either a YouTube URL or an uploaded/local video file for Instagram Reels or TikTok.

General Apple Numbers automation with a local CLI for `.numbers` files. Use when creating workbooks, adding sheets, appending rows with insertion control (`after-data`, `after-headers`, `at-end`), styling ranges, and validating data placement.

build complete claude cowork plugin marketplaces from a plain-language idea and package them as an install-ready zip. use when claude needs to create a multi-plugin office, plugin marketplace, cowork team, or full plugin suite rather than a single plugin. trigger on requests like "build a marketplace," "make me an instant office," "create a 7-plugin cowork setup," or "package a full claude plugin ecosystem." support optional official connector wiring through .mcp.json files and generate top-level plugin.json plus all plugin folders, commands, skills, hooks, and readmes.