AI Agent Workflow Collection

Crafts production-grade prompts for AI image generation (Midjourney, Flux, SDXL, Firefly, Imagen, ComfyUI workflows) — subject, composition, lighting, style references, negative prompts, ControlNet hints. Use when the goal is on-brand, repeatable imagery rather than a one-off lucky generation.

Quick guidance on choosing AI models (LLM/VLM/Embedding) based on task, VRAM, cost, and quality…

Expert guidance on RAG (Retrieval-Augmented Generation) system design including chunking strategies, embedding selection, retrieval methods, and vector database…

Expert guidance on cross-domain architecture decisions, technology selection, and infrastructure design requiring deep analysis of tradeoffs and long-term…

Writes batch image and video processing scripts (Pillow, ImageMagick, ffmpeg) for asset pipelines — generate size variants, format conversions, colorspace transforms, watermarks, optimization. Use when one design output needs to become 40 deliverables, or when an asset library needs cleanup.

Helps a solo founder or small team decide whether to build a feature in-house, buy/integrate a SaaS, or defer it. Considers MRR stage, team capacity, vendor lock-in risk, ongoing maintenance cost, and the "default to building" indie bias. Invoked when the user asks "should we build or buy [feature]", "is it worth integrating [tool]", "should we replace [vendor] with our own implementation", or "what's the cheapest way to ship [capability]".

[PRE-ALPHA] Generate a Mermaid flowchart of a code subgraph centered on a function, class, or module. Runs vco codegraph-diagram under the hood, writes the .mmd to .claude/diagrams/codegraph/ so it's indexed for hybridsearch, and gives a 3-5 line summary plus a link to open it in the launcher's DiagramsTab. Output may be incomplete, inaccurate, or visually broken — always tell the user to verify against the source code before sharing. Use when the user asks \"show me a call graph for X\", \"what does Y depend on\", \"draw the inheritance chain rooted at Z\", or any other request that maps to a small-to-medium subgraph extraction from the code graph.

Runs structured technical due diligence on a vendor, acquisition target, or strategic partner; produces a risk-ranked report with findings, evidence, and a…

Coordinates multi-channel incident response for a consulting engagement - drafts war-room updates, status-page entries, client comms, and the post-incident review; use when a client production issue is active or just…

Turns a directory of per-client engagement files into a board-ready portfolio status report; use when preparing a weekly digest, a steering-committee briefing, or any multi-engagement…

Guide for using /compact (Claude Code built-in) with the pre-compact save pipeline. Shows what gets saved before compression and what gets reinjected after.

Expert guidance on database design, schema optimization, query performance, and database technology…

Audits a mathematical equation or derivation for dimensional consistency, limiting behaviour, sign sanity, and common-error patterns. Use when the user pastes an equation, asks "is this derivation right", "check the units", "what should this reduce to in the limit", "I'm getting an off-by-factor-of-2 error", or shares a snippet of LaTeX they want validated before publication.

Systematically extract knowledge from scattered documentation to prevent catastrophic forgetting. Creates structured extraction reports with status tags.

Automated visual testing with Playwright MCP - test web apps, presentations, websites, and documents with scalable reviewer…

Quick GUI/UX/UI design consultations and…

Quick VRAM/RAM calculations, hardware recommendations, feasibility checks for AI…

Generates HPC job-submission scripts (SLURM, PBS/Torque, SGE/UGE, LSF) from a Python/R/Julia script with sensible resource estimates, partition selection, module loading, and container setup. Use when the user asks "how do I submit this to SLURM", "write me a sbatch script", "I need to run this on the cluster", "what resources should I request", or describes a script they want to run at scale.

Research using ONLY knowledge graph semantic search (no file tools, forces KG-first…

Reviews Kubernetes manifests (Deployment, StatefulSet, Service, Ingress, NetworkPolicy, etc.) for resource limits, probes, security context, PDBs, anti-affinity, image pinning, and network policies before they merge. Invoke when the user shares a manifest YAML, when a chart/kustomization PR appears, or before applying to prod.

Writes Adobe Photoshop automation scripts in UXP (JavaScript) or legacy ExtendScript (JSX), and GIMP scripts in Python (Script-Fu fallback). Use when a repetitive Photoshop task needs to run on dozens of files, when a custom panel/plugin is wanted, or when an Action recorder won't capture the logic needed.

Audits a scientific project for reproducibility — environment pinning, seed setting, data hashing, notebook discipline, workflow orchestration, and provenance capture. Use when the user asks "is this project reproducible", "what's missing for a reviewer to rerun this", "audit my repo before submission", "why do I get different results each run", or before submitting code with a manuscript.

Performs a diagnostic on a SaaS product's revenue and retention metrics from a CSV or spreadsheet of customers/subscriptions/events. Computes MRR, ARR, churn (gross/net), LTV, CAC, payback period, quick ratio, and cohort retention; flags anomalies; identifies the single highest-leverage fix. Invoked when the user asks "are my SaaS metrics healthy", "compute LTV for my data", "is my churn high", "review my MRR breakdown", or shares a billing/customer CSV.

Analyses a SaaS product's pricing page (current and competitor) and produces a concrete redesign with tier structure, value metric, anchoring, annual-discount math, and a measurable rollout plan. Invoked when the user asks "is my pricing right", "review my pricing page", "compare my pricing to [competitor]", "how should I raise prices", "should I add a third tier", or shares a competitor pricing URL with intent to react.