cryptopafi

@cryptopafi source repo

28 skills
0 followers
3 hours ago last updated

▌
Opt · cryptopafi
Optimize any prompt or text using the PromptForge pipeline. Default behavior for opt, /opt, or [$opt] followed by a task is optimize-and-execute with a detailed preview. Use opt explain, /opt --prompt-only, or optimize only when the user only wants the improved prompt.

0 installs
▌
Goal · cryptopafi bundle
Manage persistent Codex thread goals using Codex's native goal tools. Use when the user says /goal, goal mode, set a goal, keep working until a condition is met, continue autonomously until done, check goal status, or asks to complete a long-running coding/task objective across turns. Also proactively suggest this skill when a non-technical user asks for work with a clear end state that may take multiple turns, retries, checks, or follow-up validation.

0 installs
▌
Delphi · cryptopafi bundle
Dispatch Delphi/NexusOS research jobs from Codex through the existing Delphi Pro plugin. Use when Pafi asks Codex to run Delphi, D1-D4 research, deep research, scout/citation-heavy research, or NexusOS research briefs.

0 installs
▌
Council · cryptopafi bundle
Run a 3-model advisor council for strategic decisions, architecture choices, and plans. Use when Pafi asks for /council, council review, or multi-model decision audit. ANTI-PATTERN: Do not use for code artifact quality review; use audit-pro.

0 installs
▌
Goalopt · cryptopafi bundle
Optimize a rough objective into a precise completion contract, then create a native Codex goal from it. Use when Pafi says /goalopt, goalopt, optimize this goal, or asks to turn a vague task into an autonomous Codex goal with clear verification, constraints, boundaries, and stop conditions. Ported from the Hermes /goalopt plugin behavior, not from the NexusOS dispatch adapter.

0 installs
▌
Handoff · cryptopafi
Run a comprehensive Codex session handoff: save important findings to Cortex, update impacted project cards and sync them to Cortex, write durable findings to LLM-Wiki when reusable, append Genie updates, write a session summary, preserve pending tasks, check agents/modes, sync relevant git repos when available, and return a final report. Use when Pafi says handoff, /handoff, save session, wrap up everything, session end, or prepare next session. ANTI-PATTERN: Do not use for quick summaries, single-file saves, or WISH Step H task delegation.

0 installs
▌
Ralplan · cryptopafi
Consensus architectural planning — a GPT-5.6 Sol/high planner drafts RALPLAN-DR, two parallel GPT-5.6 Sol/max auditors critique it, and a Sol/max reconciler produces the final verdict. Output saved to ~/.nexus/workspace/plans/{name}.md. Default SHORT mode; pass '--deliberate' for pre-mortem + expanded test plan. Auto-invoked by TECH when Source Plan is missing. Triggers: 'ralplan', 'consensus plan', 'plan this properly', 'architect this', 'plan with review', 'planifică asta', 'plan consensual'. NOT for: prompt optimization (promptforge-scope), research (delphi), Q&A.

0 installs
▌
Grill Me · cryptopafi
Interview the user relentlessly about a plan, design, or decision until reaching shared understanding. Resolves each branch of the decision tree one-by-one, providing recommended answers. Use when user says '/grill-me', 'grill me', 'stress-test this plan', 'challenge my design', 'interview me about this', or wants to validate a decision before implementation.

0 installs
▌
Audit Pro · cryptopafi bundle
Portable Audit Pro workflow for Codex. Use for '/audit-pro', '/audit', 'audit this', 'review this code', 'check this procedure', or an NPLF quality gate across code, procedures, skills, plugins, config, prompts, and architecture. Codex/GPT-5.6 Sol is final authority; optional cross-model discovery uses Claude and Ollama Cloud GLM 5.2. Do not use for ordinary explanation or direct bug fixing without an audit request.

0 installs
▌
Sol Cycle · cryptopafi
Run one Self-Optimization Loop queue item through audit, validation, auto-mode or approval, patch application, Cortex save, and manifest update. Use when Pafi asks for sol-cycle or one SOL optimization cycle. ANTI-PATTERN: Do not use for general prompt optimization; use opt.

0 installs
▌
Forgebuild · cryptopafi
Create, convert, assemble, or build portable NexusOS procedures, skills, and plugin bundles using the canonical FORGEBUILD v2.1 procedure. Use when Pafi says forgebuild, forge/build a procedure, create a reusable workflow, turn a procedure into a skill, build a plugin/skill bundle, or standardize a skill across Codex/Claude runtimes. ANTI-PATTERN: Do not use for one-off task execution, ordinary code edits, or prompt optimization.

0 installs
▌
LLM Council · cryptopafi bundle
Run decisions through Ole Lehmann's LLM Council: five advisor lenses, anonymous peer review, chairman synthesis, HTML report, and transcript. Use when the user says council this, run the council, war room this, pressure-test this, stress-test this, debate this, or asks for multi-perspective pressure testing of a real decision. ANTI-PATTERN: Do not use for factual lookups, simple yes/no questions, ordinary content generation, or summarization.

0 installs
▌
Agent Browser · cryptopafi
Control websites through the local agent-browser CLI for navigation, screenshots, form interaction, login flows, text extraction, and website-access testing. Use when auditing whether websites are reachable or extractable, when the Codex in-app Browser plugin is unavailable/insufficient, or when a repeatable shell-driven browser workflow is needed. ANTI-PATTERN: Do not use for pure HTTP checks that curl can answer, source-code review, or restricted authenticated content without credentials.

0 installs
▌
Brand Harvest · cryptopafi
Harvest ALL design elements from a target website at maximum fidelity for banner/ad production. Extracts logos (SVG/PNG variants), color palette (hex + CSS vars + gradients), typography (font families, weights, @font-face URLs), spacing tokens, button/CTA styles, hero imagery, multi-breakpoint screenshots. Outputs brand-kit.json (W3C Design Tokens spec) + asset directory ready for gpt-image-banner. Use when starting custom banner production for a new brand/site (Casino Rewards, SMSads creative work). Trigger signals: 'harvest [site]', 'extract brand from [url]', 'brand kit [domain]', 'get design tokens from [site]', 'scrape [site] for banner production'. ANTI-PATTERN: Not for code audit, SEO, content scraping, or competitive intel — use apify-competitor-intelligence or apify-market-research instead.

0 installs
▌
Moa Candidate · cryptopafi bundle
Use when Pafi asks for “MoA candidate mode”, “MoA/council QA”, “compare default vs council vs MoA”, “is this worth MoA?”, or when a request affects Hermes routing, profile/SOUL/skill policy, architecture, sensitive final QA, RUO/Supabase safety, OpenClaw retirement, or high-stakes strategy. This skill classifies whether MoA-style synthesis or a council critique pattern is worth the cost and returns a decision packet. It does not enable live MoA routing by itself.

0 installs
▌
Prompt Fable5 · cryptopafi
Turn any task into a prompt package optimized for Claude Fable 5 / Mythos 5 — recommends effort level, selects only the behavior blocks the task needs (anti-overplanning, brevity, progress-grounding, subagents, memory, send_to_user, etc.), and enforces the Fable 5 footguns (no reasoning-extraction, Opus 4.8 refusal fallback, adaptive-thinking-only). Use when the user says /prompt-fable5, 'prompt fable 5', or 'optimize this for Fable 5'. ANTI-PATTERN: not for general prompt optimization with no Fable 5 target (use /opt), and it does not execute the built prompt.

0 installs
▌
Telegram Send · cryptopafi bundle
Send Telegram messages/documents with dry-run, MTProto session safety, Pafi copy, SHA/message-ID delivery logs, and reusable scripts. Use when asked to send, forward, deliver, DM, or Telegram a message/file to named people or handles from Codex. ANTI-PATTERN: Do not use for Slack/email/WhatsApp, unauthorised external outreach, or casual reply drafting without sending.

0 installs
▌
Banner Critique · cryptopafi
Vision-based design critique for banners, creatives, or any rendered visual. Use AFTER any banner production step and BEFORE showing the user. Reads the image through Codex vision and scores it on 5 axes (readability, hierarchy, depth, brand fit, professional polish), returns top 3 issues + 3 specific fixes + PASS/REVIEW/FAIL verdict. Use when user says '/banner-critique', 'critique this banner', 'rate this design', or as a self-check gate before delivery. ANTI-PATTERN: do not use for code review (use code-review), text review (use audit-pro), or non-visual outputs.

0 installs
▌
Shared Reporter · cryptopafi bundle
Generate premium HTML reports from any NexusOS agent. 3 tiers: Card, Full, Immersive. Dark-first glassmorphism. GitHub Pages deploy (primary). VPS fallback. Standardized across all agents.

0 installs
▌
Banner Visual QA · cryptopafi bundle
Validate raster banner ads before delivery with deterministic checks plus a forced visual gate. Use when reviewing, QA-ing, exporting, or preparing final SMSads, RCS, WhatsApp, push, in-app, Rewards Affiliates, casino display, or other raster ad banners. ANTI-PATTERN: Do not use for generating banner concepts, writing copy, or subjective design critique alone; use imagegen/gpt-image-banner/banner-critique for those.

0 installs
▌
Ruo Restock Planner · cryptopafi bundle
Calculate RUO Peptides/PeptraLabs restock recommendations (read-only) from current stock, empirical customer-sale velocity, open restocks, a conservative single-number lead time, COA economic-batch floor, 2-year shelf-life cap, and a Bucharest/Ibiza transfer-first gate. Use for weekly reorder planning, after a customer order to decide whether to restock, or when Pafi asks what to order next. ANTI-PATTERN: Do not create supplier orders or mutate Supabase; do not treat staff/internal transfers, gifts, losses, or supplier substitutions as customer demand; do not use per-patient protocol vials as an aggregate rate or fold assumed stack demand into the default recommendation.

0 installs
▌
Ruo Task Colour Marker · cryptopafi bundle
Colour-code and reconcile the RUO Peptides/PeptraLabs task dashboard from Pafi's latest instructions. Use when Pafi asks to mark task colours, update red/yellow/green gate states, classify dashboard tasks from new information, or make the shared task dashboard readable by other agents.

0 installs
▌
Self Optimization Loop · cryptopafi bundle
Full NexusOS Self-Optimization Loop (SOL) procedure for continuous prompt improvement: discover, audit, build, approve, apply, track, and persist prompt optimizations. Use when Pafi says /sol, asks for SOL governance, or requests the complete continuous prompt-improvement workflow.

0 installs
▌
Ruo Supabase Guardrails · cryptopafi
Enforce read-only RUO Peptides/PeptraLabs Supabase access for non-Hermes agents and route every mutation as a validated instruction set to Hermes-main/default, the sole mutation owner. Use for RUO reads, write requests, migrations, schema/config/RLS/storage/RPC changes, syncs, or agent access. ANTI-PATTERN: Never use this skill to authorize or execute a direct non-Hermes Supabase write.

0 installs
▌
Casino Banner Production · cryptopafi
Produce LP-anchored casino affiliate display banners from a landing page URL and bonus copy. Runs brand harvest, HTML compositor authoring, headless Chrome render, visual critique, iteration, i18n variants, and final JPG delivery for Rewards Affiliates / Casino Rewards style campaigns. Use when asked to make casino banners, display creatives, IAB 250x250/500x500 casino assets, or brand-faithful casino affiliate creatives. ANTI-PATTERN: Do not use for unrelated visual design, generic research, or VOX SMS+ unless explicitly requested as an 800x418 no-CTA variant.

0 installs
▌
Patient Bloodwork Protocol · cryptopafi
End-to-end patient bloodwork → Bachmeyer peptide/supplement protocol → published report pipeline. Use when the user provides (or points to) a patient's lab/blood-test documents and asks to analyze them, build a peptide/supplement protocol 'like the other patients', get full dosing, or publish a health report. Handles batched lab bulletins (latest/complete supersedes), updates the patient PROJECT-CARD first, cross-references Bachmeyer NLM + LLM-Wiki for FULL dosing, adds plain-language for non-medical readers, and publishes a de-identified report to GitHub Pages. Trigger signals: 'analyze patient X bloodwork', 'check blood test for [name]', 'run full pipeline on these labs', 'get the peptide/supplement protocol like we did for the other patients', 'full protocol with dosing', 'publish the health report'. ANTI-PATTERN: do not use for the owner's own Apple-Health daily metrics (that is the health-pro daily pipeline), for non-patient research, or for code/marketing reports.

0 installs
▌
Ruo Supabase Mutation Audit · cryptopafi bundle
Convert every proposed RUO Peptides/PeptraLabs Supabase mutation into a validated Hermes-main/default instruction set while keeping Codex read-only. Use after ruo-supabase-guardrails for data, schema/config/RLS/storage/RPC, dashboard sync, runtime access, or migration changes. ANTI-PATTERN: Never treat HANDOFF_READY as permission for Codex to execute a Supabase mutation.

0 installs
▌
Ruo Financial Audit Controller · cryptopafi bundle
Control-gate RUO Peptides financial-audit updates so corrections propagate across source evidence, cash/treasury, customer credit, participant balances, inventory, owner investment, COA costs, and published outputs. Use for RUO accounting corrections, transaction reconciliation, inventory/account balance changes, or audit-summary updates. ANTI-PATTERN: Do not use for generic legal strategy, normal website copy edits, or one-off prose that does not change audit facts.

0 installs

28 published skills