executiveusa

Use when Hermes needs to discover, qualify, and track grants for a nonprofit or social-purpose organization.

Use when Hermes is designing websites, internal micro apps, grant workflows, donor flows, or other practical systems for social-purpose teams.

Use when Hermes needs live browser verification, page inspection, or proof that a public flow actually works.

Use when Hermes should reason with CLI-first workflows, indexed lookup, jcodemunch-style token savings, or command-oriented execution.

Use when Hermes needs to track evidence, dependencies, blockers, decisions, and learning loops as a graph.

Use when Hermes should record verified learnings, improve its own routing, or capture stable patterns for later reuse.

Use when Hermes needs a grouped index of external repos, skills, and references it can reuse.

NWKids nonprofit operations as MCP tools. Use when asked to find grants, write bilingual social posts, log program impact, or check operations health. Works with Claude Code, ChatGPT, Cursor, and any MCP-compatible client. Get an API key at nwkids.ai/dashboard.

Pre-code system configuration for any AI agent. Detects model, applies token optimization, estimates input tokens, compresses context, calculates real-time savings (to the token), and tracks cost delta before coding starts. Works with all 11 models. Agent runs this BEFORE writing code—saves 75-95% tokens + cost on every project. Triggers: "before i code", "set up token optimization", "configure system", "what model am i", "estimate tokens", "how much will this save", "show me savings", "pre-code checklist", "token tracker", "cost me to code this"

Publish agent capabilities and accept Agent2Agent task requests through the local HTTP receiver.

Verify that a Vercel deployment URL displays a real page instead of a 404, auth wall, blank shell, or error page.

Verify and normalize GitHub webhook payloads for deployment automation. Use when a GitHub push, deployment_status, or workflow_run event arrives.

Iterate deployment visibility failures using only no-code-safe actions and stop when source-code changes are required.

Inventory GitHub repositories and Vercel projects, then map repos to deployments for a visibility sweep.

Link, deploy, inspect, and verify Vercel projects using Vercel CLI/API with token-based authentication.

Policy for deciding what enters memory, what stays transient, and what must be redacted.

Brain knowledge base operations. The core read/write cycle: brain-first lookup, read-enrich-write loop, source attribution, ambient enrichment, back-linking. Read this before any brain interaction.

Enrich brain pages with tiered enrichment protocol. Creates and updates person/company pages with compiled truth, timeline, and cross-links. Use when a new entity is mentioned or an existing page needs updating.

Brain health checks: back-link enforcement, citation audit, filing validation, stale info detection, orphan pages, and benchmarks. Use when asked to check brain health, run maintenance, or audit quality.

Ingest meeting transcripts into brain pages with attendee enrichment, entity propagation, and timeline merge. A meeting is NOT fully ingested until the enrich skill has processed every entity.

Manage background agents via Minions job queue. Use when: spawning subagents, checking agent progress, steering running agents, pausing/resuming work, parallel task execution, fan-out research. Replaces sessions_spawn for durable, observable, steerable agents.

Answer questions using the brain's knowledge with 3-layer search, synthesis, and citation propagation. Use when the user asks a question, wants a lookup, or needs information from the brain.

Set up GBrain with auto-provision Supabase or PGLite, AGENTS.md injection, first import

Always-on ambient signal capture. Fires on every inbound message to detect original thinking and entity mentions. Spawn as a cheap sub-agent in parallel, never block the main response.

Playbook for orchestrating an end-to-end UGC video on the agent-media vNext runtime. Read this before deciding whether to call the one-shot make_ugc_video skill or to chain the four primitives (make_portrait → make_character_sheet → make_simple_selfie → make_subtitles) manually.

Up-to-30s vertical talking-head video: the actor speaks full-frame while a user-supplied b-roll video is overlaid on the lower half. <=15s renders as a single take (zero cuts); 16-30s uses two takes where the voice, face and setting carry across the cut automatically (take 1's voice and final frame seed take 2) — consistent speaker and continuous scene, not a jump-cut. Provide actor_image_url (any https image) + broll_video_url (any https video — both re-hosted to R2 automatically) and EITHER script (Seedance voice) OR audio_url (your own audio, single clip <=15s). Optional: subtitles; broll_width_rate (0.1-1.0, e.g. 0.8 = b-roll 80% width centered with black margins; omit for full width); broll_start_time (seconds before the b-roll appears); broll_fade_out (dissolve the b-roll at its end).

Generate a magazine-style character sheet from a portrait. Provide EITHER portrait_url (must be R2-hosted) OR portrait_image_base64 (PNG/JPEG, ≤10 MB; the API will upload it to R2 first). Optional ≤10-word description for name/age/vibe hints.

Bring your own audio: lip-sync a face (an R2-hosted image / character sheet, OR an existing clip) to a provided audio track. No text-to-speech or voice cloning — the character speaks your uploaded recording. Output is a 9:16 talking-head video.

Generate one photoreal portrait. Optionally takes a reference photo (R2-hosted) and a realism preset. Identity is locked from the reference image when provided.

Generate a 5/10/15s vertical UGC video where your character holds, wears, and shows a product. Provide a character_sheet_url (R2-hosted) and the product image (product_image_url — any https URL — OR product_image_base64; re-hosted to R2 automatically). Two modes: script for a lip-synced talking-head product review (2-4 words/sec), OR scene_action for a silent demo / b-roll. Set subject (e.g. "a young woman") to lock the person's gender/appearance so a gendered product can't drift it. framing: "close_up" (chest-up, default) or "full_body" (head-to-toe, for turn-arounds / showing the whole outfit). Both the person and the exact product are locked from the reference images.

Generate a 5/10/15-second vertical UGC selfie video from a character sheet. Two modes: provide a script for a lip-synced talking-head (2-4 words/sec), OR provide scene_action for a non-speech clip (dancing, b-roll, vibes) with optional background_music and no dialogue. Subject is framed waist-up, hands free, TikTok aesthetic.

Burn TikTok / Hormozi-style captions onto any vNext video (R2-hosted). Auto-transcribes via Whisper when transcript is omitted. Styles: hormozi (default), tiktok, minimal.

Production agent harness for designing, creating, organizing, validating, and documenting Impact City game assets. CLI at agents/pi-game-creator/.

Drives Blender 5.1 headless on the user's laptop to generate Impact City 3D assets. Verified working.

Turns real AI risks into age-appropriate codex content. Use for all AI-risk educational content.

Prepares a clean asset workflow. Use when creating or organizing visual/audio assets.

Applies the Emerald Gothic Hopepunk visual system. Use after a playable route exists.

Owns the Impact City MVP from repo scan to final build. Use first and throughout.

Connects positive game actions to transparent impact tracking. Use for any mission/rebuild/purchase/dashboard event.

Designs suspenseful missions without combat. Use whenever implementing missions or challenges.

Use this skill when managing API access based on billing status. Trigger when: a tenant's trial expires, a payment fails, a tenant upgrades to paid, a suspension is requested, or a resume is requested. The billing gate controls API access but never destroys tenant data.

Use this skill when generating an interactive educational HTML course from a codebase so that non-technical operators can understand the system. Trigger when: onboarding a new client to their backend, explaining the factory pipeline to an operator, generating operator documentation from source code, or creating visual system walkthroughs.

Use this skill when managing the directory listing, lead capture, lead scoring, lead routing, or consent controls for a tenant. The directory is the trust hook — it gives potential clients a free listing and a discoverable landing page that generates inbound leads. Trigger when: creating directory listings, capturing form/chat/call leads, scoring leads, routing leads to the business, or managing consent and spam controls.

Use this skill when managing org structure, budgets, goals, governance, or agent heartbeats. Paperclip is the business control plane — it does not replace Pi but governs the business that Pi runs inside. Trigger when: creating or updating org charts, setting goals, tracking budgets, registering agents, receiving or sending heartbeats, enforcing human approval gates for business decisions.

Use this skill when executing tenant chat, ingestion, memory reads, skill routing, or API calls on behalf of a tenant. Pi is the backend agent runtime. Trigger when: a tenant message arrives, a document needs ingesting, a skill needs routing, memory needs loading, or any API call targets /v1/tenants/*.

Use this skill when running quality checks on any deliverable before reporting it as complete. Trigger when: finishing a website build, completing a tenant setup, deploying any frontend, committing any code, or generating any operator-facing output. Reject anything that fails the gate.

Use this skill when implementing, extending, or debugging the factoryctl Rust CLI. Trigger when: adding new CLI commands, implementing API client calls in Rust, writing Cargo.toml config, generating CLI help text, implementing the audit runner, or integrating factoryctl with Pi API endpoints.

Use this skill when designing or building the operator-facing backend UI for Pauli Pipeline or a tenant's admin dashboard. Follows Synthia 3.0 / Hyperagent-style layout. Trigger when: building admin panels, operator dashboards, agent management views, tenant memory browsers, billing status views, or integration configuration UIs.

Approval loop / Ciclo de aprobación

Builder handoff compiler / Compilador de handoff

Graph-first discovery / Descubrimiento graph-first

Relentless interview / Entrevista rigurosa

Universal intake / Intake universal

Privacy by design / Privacidad por diseño

Bilingual brand system / Sistema de marca bilingüe

Cinematic Seedance 2.0 video prompt skill for Food & Beverage brands. Use for CPG, snacks, drinks, supplements, sauces, meal kits, any edible product. Produces Higgsfield-ready prompts with hook, money shot, sound, and lighting specs. Source: beshuaxian/higgsfield-seedance2-jineng skill 14

One-question-at-a-time client interview skill. Run before any content generation. Drills down on brand, customer, product, taste, and goals. Produces brief.yaml. Based on mattpocock/skills grill-me pattern. Never batch questions.

Score social media content units for viral potential (0-100) with transparent breakdown by dimension. Use after content generation, before surfacing to human for approval. Produces ranked output with reasoning. Required for all content.

Anti-AI writing guardrails for all verbal content. Use on every caption, hook, script, email subject, button label, and UI copy before it leaves the pipeline. Triggers automatically on all text output. Source: hardikpandya/stop-slop

Generate UGC-style video prompts for Seedance 2.0 on Higgsfield for Beauty, Apparel, and Home & Lifestyle brands. Use when creating influencer-style product reviews, demos, unboxings, lipsync, or lifestyle ads. Based on Sirio Berati's AI UGC workflow. Source: sirioberati/Seedance-2.0-AI-UGC

Operate the Agent Maxx OpusClip backend bridge for turning owned or licensed long-form videos into short clips, transcripts, public shares, social copy, publish or schedule tasks, thumbnails, and safe edit jobs. Use when the task mentions OpusClip, clip generation, video-to-short workflows, posting clips, scheduling clips, video transcripts, clip collections, or MAXX media execution.

Turns a public YouTube channel or video source into a Markdown briefing that captures the latest uploads, recurring hooks, topic clusters, pacing, visual motifs, and clear instructions for how Agent MAXX should adapt the pattern.

Runs the first-session MAXX setup interview in plain language, captures answers one at a time, and writes a resumable local handoff note before implementation begins.

Agent Zero dispatch SOP for paulis-pope-bot (thepopebot) Docker job agents. Use when Agent Zero (Claude Code / GitHub Copilot) needs to dispatch background work to autonomous Docker job agents — tasks that require long-running execution, scheduled jobs, or parallel background processing. PopeBots execute jobs, create PRs, and notify. Agent Zero supervises and merges. PopeBots NEVER have git authority to push directly to main. Source: git@github.com:executiveusa/paulis-pope-bot.git

SYNTHIA™ Systems Design Intelligence. Designs backend AI architecture, agent graphs, data pipelines, and system infrastructure using Donella Meadows' systems thinking. Enforces feedback loop integrity, stock/flow discipline, leverage point identification, and emergent behavior control. Applies 12-axis UDEC scoring to architecture quality (floor 8.5/10). Auto-iterates until threshold is met. Use for any architecture decision, MCP server design, agent graph topology, or system quality scoring. Blocks all anti-patterns that create brittle, non-self-healing systems.

Comprehensive end-to-end testing command. Launches parallel sub-agents to research the codebase (structure, database schema, potential bugs), then uses the Vercel Agent Browser CLI to test every user journey — taking screenshots, validating UI/UX, and querying the database to verify records. Run after implementation to validate everything before code review.

Scan the dashboard-agent-swarm codebase for stubs, TODOs, hardcoded values, broken routes, and unimplemented features. Produces a prioritized fix list. Run this after any major feature branch merge to keep technical debt visible.

Manage GitHub repo assignments across the 313-repo executiveusa fleet. Run this skill to audit repo assignments, assign repos to agents, identify unassigned repos, or generate the full assignment export. Agent Zero (PAULI BRAIN) commands the ecosystem — all unassigned repos default to Agent Zero's guardian fleet.

Master skill file for DOS2A — AI-powered audio, lighting, and AV production platform. Combines design doctrine, humanizer, video prompt generation, course creation, and multi-agent orchestration into one unified skill surface. Trigger on: any DOS2A development, design review, content generation, or course creation task.