Sheshiyer

Arcplume runs Grok through the Grok Build CLI's own OAuth-authenticated session (grok login) for image generation, with strict preflight validation, secret-safe handling, and headless CLI-driven execution -- no separate XAI_API_KEY billing. Video falls back…

Shared reference for the Selemene cluster: the two report surfaces (deterministic Rust reports vs. narrative witness-pipeline readings), the @selemene/bridge CLI contract, the output manifest format, and non-prescriptive witnessing tone. USE WHEN deciding…

Route Selemene Engine tasks to the right surface: deterministic reports (birth/compatibility/transit) via selemene-core and the @selemene/bridge CLI, or narrative witness readings via selemene-report. USE WHEN the user wants anything under the Selemene/Noesis…

Generate Selemene Engine reports from a slash-command. Routes deterministic birth/compatibility/transit reports through the existing @selemene/bridge CLI and narrative witness readings through the packages/witness-pipeline. USE WHEN the user says…

Develop adaptability in changing environments through scenario planning, fast feedback, and flexible execution. USE WHEN a task matches the Craft workspace workflow for adaptability-coach.

Segment audiences by underlying needs, motivations, and behaviors to enable targeted strategy. USE WHEN a task matches the Craft workspace workflow for audience-segmentation-generator.

Craft compelling brand narratives that connect customer pain, transformation, and brand purpose. USE WHEN a task matches the Craft workspace workflow for brand-story-builder.

End-to-end brand identity orchestration system. Generates text strategy, visual assets, campaign copy, video deliverables, and publishing outputs using 44 specialized skills across 9 categories. Chains FAL.AI/Nano Banana/Flux visual generation with brand…

End-to-end brand identity orchestration system. Generates text strategy, visual assets, campaign copy, video deliverables, and publishing outputs using 44 specialized skills across 9 categories. Chains FAL.AI/Nano Banana/Flux visual generation with brand…

Transform markdown documentation folders into professional Astro-based wikis using refero-design principles (research-first, anti-AI-slop: no default emojis, no 3-column layouts, sections + dividers + media blocks over cards, neutral color system). Use when…

Defines brand voice persona and tone calibration using persona and positioning data to produce a reusable meta-prompt for copywriting.

Orchestrates the full crowdfunding workflow phase-by-phase, ensuring each Skill runs in sequence with proper handoffs and validation gates.

Browser automation for AI agents via inference.sh. Navigate web pages, interact with elements using @e refs, take screenshots, record video. Capabilities: web scraping, form filling, clicking, typing, drag-drop, file upload, JavaScript execution. Use for: web…

JavaScript/TypeScript SDK for inference.sh - run AI apps, build agents, integrate 150+ models. Package: @inferencesh/sdk (npm install). Full TypeScript support, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills,…

Python SDK for inference.sh - run AI apps, build agents, and integrate with 150+ models. Package: inferencesh (pip install inferencesh). Supports sync/async, streaming, file uploads. Build agents with template or ad-hoc patterns, tool builder API, skills, and…

Generate images with Alibaba Qwen-Image-2.0-Pro via inference.sh CLI. Professional text rendering, fine-grained realism, enhanced semantic adherence. Ideal for posters, banners, and text-heavy designs. Triggers: qwen image pro, qwen-image-pro, qwen 2 pro,…

Generates a deep-psychology buyer persona dossier. It strictly follows a 10-step market analysis protocol (Demographics, Failed Solutions, Tone Switching, Genie Simulation, Anti-Goals) to create a strategic foundation for marketing campaigns.

Orchestrates the full crowdfunding workflow phase-by-phase, ensuring each Skill runs in sequence with proper handoffs and validation gates.

Generates full campaign page content structured for Kickstarter/Indiegogo using positioning, product, and voice assets.

Produces a high-conversion crowdfunding video script outline and copy with hook, problem, mechanism, proof, offer, CTA.

Executes a deep-dive market intelligence protocol. Uses search tools to scrape competitor data (Specs, Price, Materials), analyzes customer sentiment (Reviews, FAQs), and synthesizes a product knowledge base.

Writes a comprehensive, feature-by-feature product description with specs and benefits that can serve as a universal prompt for downstream content generation.

Produces the full launch week email cadence (morning, evening, day 2 extension, reason

Generates live campaign ad headlines and bodies across urgency, discount, social proof, testimonial, and live-now motifs.

ZackAI project wrapper for cold-email. Use it for cold outreach emails and follow-up sequences, but always ground the work in ZackAI canonical markdown before drafting new copy.

ZackAI project wrapper for competitor-alternatives. Use it for comparison pages and battle-card style content, but always ground the work in the current competitive and product markdown first.

ZackAI project wrapper for content-strategy. Use it to plan content and content systems, but always map recommendations onto the current ZackAI markdown tree before suggesting new assets.

ZackAI project wrapper for copy-editing. Use it to improve existing marketing copy, but always edit against ZackAI source-of-truth voice, claims, and product context rather than producing parallel rewrites.

ZackAI project wrapper for launch-strategy. Use it to plan launch moments and announcements, but always assemble the plan from existing ZackAI launch assets before creating new GTM collateral.

ZackAI project wrapper for lead-magnets. Use it to plan lead capture offers, but always start from ZackAI’s existing marketing assets and nurture docs before proposing new gated content.

ZackAI project wrapper for marketing-psychology. Use it to apply ethical persuasion and behavioral thinking, but always anchor recommendations in ZackAI’s documented audience, voice, and messaging first.

ZackAI project wrapper for sales-enablement. Use it to create sales collateral and objection handling, but always build from ZackAI’s canonical messaging and adapt the motion to the actual business context instead of default SaaS assumptions.

Shared reference for all Explee skills: base URL, full endpoint catalog, API-key authentication, canonical curl templates, and shared error/retry/guardrail rules. Other Explee skills reference this instead of repeating boilerplate.

Cookie/session and EXPLEE_SECRETS KV credential model for Explee: build the Cookie header, the cookie-first/key-fallback rule, and the cookie-vs-tracking-param pitfalls. USE WHEN setting up or refreshing Explee auth. Endpoints and API-key auth: see…

Orchestrate an end-to-end AutoGTM flow: ICP query → account/person discovery → enrichment → prioritized outreach list. USE WHEN building a full GTM pipeline from a natural-language objective.

Route user intent to the correct Explee product skill (Search, Enrichment, Agents, AutoGTM), using cookie-first auth with API-key fallback. USE WHEN a user has an Explee task but hasn't named the specific product.

Use Explee Search APIs to find companies and people with natural-language targeting and optional AI scoring. USE WHEN finding accounts, prospects, or converting an ICP to filters.

Run Explee pre-built and custom AI agents, then poll run status and return structured outputs. USE WHEN running agent workflows for extraction, reasoning, or automation.

Use Explee enrichment APIs to find emails for contacts in single or batch mode and track async task status. USE WHEN completing outreach data or finding/verifying work emails.

Use when the user says "create architecture plan/specs", "turn this brief into docs", "generate frontend/backend/api specs", or "write the spec markdown files". Triggers on requests for end-to-end software architecture documentation from a product brief.

Generates full campaign page content structured for Kickstarter/Indiegogo using positioning, product, and voice assets.

Context-Aware Agentic Orchestrator that analyzes product context (budget, channel, maturity, timeline, team), recommends optimal execution scenarios, and generates budget-optimized campaign plans with 6 pre-built scenario templates.

Generate immersive, scrollytelling investor pitch experiences with glassmorphism UI, animated text effects, and parallel research agents. Use when users request pitch decks, investor presentations, business plan artifacts, or fundraising materials. Outputs…

Expert Prompt Engineer & Design System Architect capable of extracting design tokens and copy rules from raw templates to generate reusable prompt recipes.

Defines brand voice persona and tone calibration using persona and positioning data to produce a reusable meta-prompt for copywriting.

Run complex PAI work through the seven Algorithm phases with S-tier coordination, bounded workers, ISA evidence, and explicit escalation.

Execute one bounded PAI Native-mode task quickly with proportionate verification and no orchestration overhead.

Use in the Execute phase when 2+ independent, non-conflicting tasks can run at once and self-contained work should use a verified native Claude, OmniRoute batch, or direct external rail instead of consuming Sol quota.

Install an OpenCode/Cursor-first local PAI operator runtime with optional Claude/Codex compatibility, skill-cluster routing, optional peon-ping voice feedback, and CodeGraph-first .agents search.

Selemene Engine Bridge: Query 16 consciousness engines and 6 workflows for witnessing cosmic patterns. Non-prescriptive mirror — generates inquiry, not advice.

Use when facing 3+ independent failures that can be investigated without shared state or dependencies - dispatches multiple Claude agents to investigate and fix independent problems concurrently

Generate system-engineering task plans from repo specs and .context docs, including backend/frontend separation, phased sprints, dependencies, and hour estimates. Use when asked to create a task breakdown, sprint plan, or engineering workplan from…

Synthesize a tenant's Brand GTM Brief (a populated PublicCompaniesFilters + PublicPeopleFilters ICP) from the brand-docs corpus, for brand-enriched AutoGTM. Interpreter + Librarian; writes to Content-Engine/_gtm/ in_review for human approval. USE WHEN…

Community-seeding distribution for a tenant: discover high-fit threads, draft brand-voice contribution briefs (human-approve, never autopost), and queue them for review. Tenant-scoped; reads the Content-Engine _distribution vault. USE WHEN seeding…

Upgraded planning protocol for large-scale delivery plans: interactive discovery, 80-task default granularity, phase→wave→swarm orchestration, and execution-ready GitHub + agent automation.

Interactive Taskmaster planning protocol that produces 70–80+ granular tasks, organized into phases/waves/swarms, with verification gates and execution-ready GitHub + agent orchestration.

Auto-generate a modern, visually rich README.md by scanning the repo — with dynamic badges, architecture diagrams, ASCII art, and visual storytelling

Analyze a GitHub repo’s current issue/PR/code state, produce a concise status report, and propose/execute the next wave of work using parallel agents when useful.