wesleysimplicio

Legacy compatibility alias for `/simplicio-loop`. Use only when an older install, adapter, or saved prompt still invokes `/simplicio-tasks`; immediately route the run through `.claude/skills/simplicio-loop/SKILL.md`, which now owns the public core + loop protocol.

Operate and troubleshoot local Hermes/Simplicio gateway services safely, including config edits, launchd/service restarts, and live verification with logs.

Transforma a memória do Simplicio (memory_items + embeddings all-MiniLM) em um knowledge graph consultável — nós + arestas, comunidades, god nodes, path/explain/query. Port do conceito Graphify (Graphify-Labs) reusando a infra já existente (neural-recall, vec0).

Legacy compatibility alias for `/simplicio-loop`. Use only when an older install, adapter, or saved prompt still invokes `/simplicio-tasks`; immediately route the run through `.claude/skills/simplicio-loop/SKILL.md`, which now owns the public core + loop protocol.

Learned skill -- when the task mentions "not", run this proven sequence (5 successful runs, confidence 1.00).

Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's `autoresearch` pattern (and the ECC `autoresearch-agent`) with mandatory yool guardrails (§11 caps), git-isolated branch discipline, an anti-Goodhart eval order (correctness gate FIRST, score SECOND, labeled tokenizer), a local-first mutation ladder, and a `simplicio.savings-event/v1` receipt per run. Use when the user says "optimize this by <metric>", "autoresearch loop", "evolutionary optimize", "mutate/eval/keep-revert", or asks to shrink tokens/latency/bundle size/improve pass-rate against a fixed, measurable eval. Worker: `scripts/autoresearch.py`.

Cut output and memory tokens without losing meaning — terse prose levels (caveman-style) that preserve code/paths/URLs byte-for-byte, plus a one-time memory/doc compaction pass that pays back every future turn. Use when replies or worker reports are verbose, when standing context (CLAUDE.md/AGENTS.md/notes) is bloated, or when simplicio-tasks needs its output-side + input-side token discipline. Compression NEVER touches code, identifiers, or a safety confirmation.

Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so they're applied not re-derived. Use after a run or at session end, when the user says "remember this", "do a retrospective", "learn from this run", or when simplicio-tasks closes its self-audit. Keeps memory lean: durable, reusable bullets only — no transcripts, no one-offs.

Unified public entrypoint for Simplicio's body-of-work orchestration: core + loop in one command. Use when the user types /simplicio-loop, says "ralph loop", "keep iterating until done", "finish all open issues", or asks to drain a queue of work autonomously. Runtime-agnostic: binds a real stop-hook where the host supports hooks (Claude, Cursor); otherwise self-paces via the host scheduler. The older /simplicio-tasks surface is a legacy alias; never escape the loop with a false promise.

Legacy compatibility alias for `/simplicio-loop`. Use only when an older install, adapter, or saved prompt still invokes `/simplicio-tasks`; immediately route the run through `.claude/skills/simplicio-loop/SKILL.md`, which now owns the public core + loop protocol.

One-shot bootstrap skill that wires HyperFrames (https://github.com/wesleysimplicio/hyperframes) into a marketing-engine clone as a first-class video provider — the three runtime skills, the provider class + mock, the routing matrix rows, env vars, and CLAUDE.md updates. Idempotent. Invoke when a fresh clone needs HyperFrames added, or when reapplying the integration after a rebase that dropped any piece of it.

Runs the HyperFrames CLI dev loop — init, lint, inspect, preview, render — for compositions authored under the `hyperframes` skill. Invoked after the composition HTML is on disk and before the piece is marked complete.

Translates a marketing-engine piece brief into the input shape the `hyperframes` skill expects (composition spec) and the flags the `hyperframes-cli` skill needs to render it. Selected by `video-prompt-builder` when the routing matrix resolves to the `hyperframes` provider.

Author HTML-as-source-of-truth motion compositions (kinetic type, motion quote cards, programmatic data-viz reels) for the HyperFrames renderer. Used whenever the video provider resolved by the routing matrix is `hyperframes`.

Assembles a video generation prompt by picking the provider via PROVIDERS.md and delegating to the matching provider-specific builder

Use RTK CLI (https://github.com/rtk-ai/rtk) to cut tokens during repo exploration and verbose validation

Generates new .skills/<slug>/SKILL.md entries on demand from a one-line description, guarded by a review gate so unreviewed skills do not become defaults.

Use simplicio-cli to turn a one-line task into a verified code change (diff + test + verify loop). Trigger ALWAYS when the user asks for a small/medium code edit in a known file — "hide X for non-admins", "add validation to Y", "fix the empty-state on Z", "rename the prop in <file>" — even if they do not mention the word "simplicio". Especially trigger when the active model is small/local (Ollama, Gemma, Llama 3 sub-8B, Phi, Qwen 7B), or the user mentions "task-to-code", "diff+test", "verify loop", "6-layer contract", "pass-rate", "precedent + skill router", or any of the benchmark numbers (+39 pts, +51 pts, +58 pts, 99% pass-rate). Use this skill BEFORE writing the edit by hand — simplicio-cli measurably boosts pass-rate on the same model from ~41% to ~99% on frontier and ~35% to ~74% on sub-4B by stacking mapper + precedent + skill-router + 6-layer prompt + test + verify-loop. Also trigger on explicit invocations: `$simplicio`, `/simplicio`, "use simplicio", "rode o simplicio".

Human review workflow for baseline rows where code generation is disabled.

Validate generated FastAPI CRUD scaffolds before they enter release evidence.

Review Go Gin CRUD release evidence before human approval.

Human review workflow for issue-closure audit artifacts and blocker traceability across issues.

Review Laravel API CRUD scaffold release evidence for routes, JSON codes, tests, and Pint.

Audit mechanical Next.js App Router CRUD scaffolds for correctness, security, UX, and maintainability.

otimiza um documento de skill (SKILL.md) com o loop SkillOpt (Rollout -> Reflect -> Edit -> Gate) contra uma suíte de tarefas, sem treinar o modelo

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Use when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

Author a new HyperFrames registry block (caption style, VFX block, transition, lower third) or component (text effect, overlay, snippet) and ship it as an upstream PR to the hyperframes repo. Use ONLY when the user wants to CONTRIBUTE to the public catalog — for in-project caption/transition authoring use the `hyperframes` skill, for installing existing registry items use the `hyperframes-registry` skill.

GSAP animation reference for HyperFrames. Covers gsap.to(), from(), fromTo(), easing, stagger, defaults, timelines (gsap.timeline(), position parameter, labels, nesting, playback), and performance (transforms, will-change, quickTo). Use when writing GSAP animations in HyperFrames compositions.

Create video compositions, animations, title cards, overlays, captions, voiceovers, audio-reactive visuals, and scene transitions in HyperFrames HTML. Use when asked to build any HTML-based video content, add captions or subtitles synced to audio, generate text-to-speech narration, create audio-reactive animation (beat sync, glow, pulse driven by music), add animated text highlighting (marker sweeps, hand-drawn circles, burst lines, scribble, sketchout), or add transitions between scenes (crossfades, wipes, reveals, shader transitions). Covers composition authoring, timing, media, and the full video production workflow. For dev-loop CLI commands (init, lint, inspect, preview, render) see the hyperframes-cli skill; for asset preprocessing commands (tts, transcribe, remove-background) see the hyperframes-media skill.

Translate an existing Remotion (React-based) video composition into a HyperFrames HTML composition. Use ONLY when the user explicitly asks to port, convert, migrate, translate, or rewrite a Remotion composition as HyperFrames (e.g. "port my Remotion project to HyperFrames"). Do NOT use when (a) authoring a NEW HyperFrames composition (even if A/B-testing a Remotion video); (b) Remotion is mentioned in passing; (c) Remotion code is shared as reference, not for translation; (d) the user wants "the same video as my Remotion one" without explicitly asking to migrate the source — treat as a fresh HyperFrames build. When in doubt, default to the `hyperframes` skill. Detects unsupported patterns (useState, useEffect side effects, async calculateMetadata, third-party React component libraries, `@remotion/lambda`) and recommends the runtime interop escape hatch instead of a lossy translation.

escrever ou atualizar testes end-to-end com Playwright neste projeto, garantindo trace, screenshot, vídeo e asserções consistentes

Use this skill when the user asks for image, video, music, 3D, audio, or LLM generation backed by the PiAPI inference platform (https://piapi.ai). Covers Midjourney, Suno, Kling, Luma, Hailuo, Flux, Hunyuan, Faceswap, Trellis, MMAudio, F5-TTS, Veo 3, Gemini 2.5 Flash Image, and Seedance via a single unified `POST /api/v1/task` envelope. The CLI also wraps the OpenAI- compatible `POST /v1/chat/completions` LLM surface.

Image, video, music, 3D, audio, and LLM generation via PiAPI. Wraps the unified `POST /api/v1/task` envelope plus the OpenAI-compatible `POST /v1/chat/completions` LLM proxy.

PiAPI inference gateway — image, video, music, 3D, audio, and LLM generation through one async-task envelope and an OpenAI-compatible LLM proxy.

Portable, agent-agnostic spec for the PiAPI inference gateway. Single async-task envelope at `POST /api/v1/task` aggregates Midjourney, Flux, Kling, Luma, Hailuo, Veo 3, Suno, Hunyuan, MMAudio, F5-TTS, Trellis, Gemini Nano Banana, Seedance, and Faceswap. `POST /v1/chat/completions` is an OpenAI-compatible LLM proxy. Auth header is `x-api-key`.

Generate images, video, music, 3D, audio, and chat completions through PiAPI's unified async-task gateway. Aggregates Midjourney, Flux, Kling, Luma, Hailuo, Veo 3, Suno, Hunyuan, MMAudio, F5-TTS, Trellis, Gemini Nano Banana, Seedance, and Faceswap behind a single `POST /api/v1/task` envelope, plus an OpenAI-compatible `POST /v1/chat/completions` LLM proxy.

PiAPI inference gateway. One unified `POST /api/v1/task` envelope for Midjourney, Flux, Kling, Luma, Hailuo, Veo 3, Suno, Hunyuan, MMAudio, F5-TTS, Trellis, Gemini Nano Banana, Seedance, and Faceswap. Plus an OpenAI-compatible `POST /v1/chat/completions` LLM proxy.

PiAPI inference gateway. One async-task envelope plus an OpenAI-compatible LLM proxy. Aggregates Midjourney, Flux, Kling, Luma, Hailuo, Veo 3, Suno, Hunyuan, MMAudio, F5-TTS, Trellis, Gemini Nano Banana, Seedance, and Faceswap.

Unified public entrypoint for Simplicio's body-of-work orchestration: core + loop in one command. Use when the user types /simplicio-loop, says "ralph loop", "keep iterating until done", "finish all open issues", or asks to drain a queue of work autonomously. Runtime-agnostic: binds a real stop-hook where the host supports hooks (Claude, Cursor); otherwise self-paces via the host scheduler. The older /simplicio-tasks surface is a legacy alias; never escape the loop with a false promise.

Legacy compatibility alias for `/simplicio-loop`. Use only when an older install, adapter, or saved prompt still invokes `/simplicio-tasks`; immediately route the run through `.claude/skills/simplicio-loop/SKILL.md`, which now owns the public core + loop protocol.

Evolutionary optimize-by-metric loop — mutate a target, evaluate against fixed criteria, KEEP if the score improves (commit) or REVERT if it doesn't (git checkout), repeat, plateau-break after N stagnated runs. Adapts Karpathy's `autoresearch` pattern (and the ECC `autoresearch-agent`) with mandatory yool guardrails (§11 caps), git-isolated branch discipline, an anti-Goodhart eval order (correctness gate FIRST, score SECOND, labeled tokenizer), a local-first mutation ladder, and a `simplicio.savings-event/v1` receipt per run. Use when the user says "optimize this by <metric>", "autoresearch loop", "evolutionary optimize", "mutate/eval/keep-revert", or asks to shrink tokens/latency/bundle size/improve pass-rate against a fixed, measurable eval. Worker: `scripts/autoresearch.py`.

Terminal-first execution — answer facts with the shell, never with the LLM. Use whenever a step needs a fact about the filesystem, git, processes, or system resources, or runs a build/test/lint/diff whose output would flood context. Substitutes deterministic shell/CLI calls for native LLM operations and clamps their output 60–90% (rtk-style) with a failure-safe tee cache, signatures-only reads, and an optional auto-rewrite hook. This is the token-economy spine of simplicio-tasks, usable standalone.

Deep, adversarial branch review — parallel subagents on separate rubrics (security/correctness, code-quality, and does-it-reproduce), spawned in one message, then deduped into one verdict. Runs for EVERY item, no TRIVIAL/SMALL shortcut — it is 3 of the 6 roles in simplicio-tasks' minimum-agent floor. Use before merging any work, when the user says "review this branch/PR hard", "thermo-nuclear review", "is this safe to merge", or when simplicio-tasks needs the Step 4c adversarial verify gate. Scopes strictly to the diff; refutes rather than rubber-stamps.

Persist what a run taught you so the next run is cheaper and more correct — mine high-signal lessons from the trajectory, dedup them, and write them back to AGENTS.md / memory so they're applied not re-derived. Use after a run or at session end, when the user says "remember this", "do a retrospective", "learn from this run", or when simplicio-tasks closes its self-audit. Keeps memory lean: durable, reusable bullets only — no transcripts, no one-offs.

Cut output and memory tokens without losing meaning — terse prose levels (caveman-style) that preserve code/paths/URLs byte-for-byte, plus a one-time memory/doc compaction pass that pays back every future turn. Use when replies or worker reports are verbose, when standing context (CLAUDE.md/AGENTS.md/notes) is bloated, or when simplicio-tasks needs its output-side + input-side token discipline. Compression NEVER touches code, identifiers, or a safety confirmation.

Generate images, video, audio and avatars via the WaveSpeedAI inference platform (700+ models incl. FLUX, Kling, Veo, Luma, Stable Diffusion, Seedance, Z-Image, Wan, Qwen, Higgsfield), or call the OpenAI-compatible LLM gateway (290+ models incl. Claude, GPT, Gemini, DeepSeek, Llama, Mistral). Use whenever the user asks to create AI media, run a `wavespeed-ai/*` model, upload a media asset for inference, list available models, check account balance, configure a webhook, or call an LLM through the WaveSpeed proxy. Wraps the official Python SDK (`pip install wavespeed`) plus a thin CLI for one-shot calls.

Generate images, video, audio, avatars (700+ models — FLUX, Kling, Veo, Luma, Seedance, Z-Image, Wan) or call OpenAI-compatible LLMs (290+ — Claude, GPT, Gemini, DeepSeek, Llama) via the WaveSpeedAI inference platform. Wraps the official Python SDK plus a thin CLI shim.

WaveSpeedAI inference gateway — 700+ media models and 290+ OpenAI-compatible LLMs through one API key. Use for AI media generation (image/video/audio/avatar) and for cheap proxied LLM calls (Claude/GPT/Gemini/Llama).

Generate images, video, audio and avatars (700+ models) or call OpenAI-compatible LLMs (290+ models — Claude, GPT, Gemini, DeepSeek, Llama) through the WaveSpeedAI inference platform. Use whenever the user asks to create AI media, run a `wavespeed-ai/*` model, upload a media asset for inference, list available models, check account balance, or call an LLM via the WaveSpeed proxy.

WaveSpeedAI inference gateway — 700+ media models (FLUX, Kling, Veo, Luma, Seedance, Z-Image, Wan, Qwen, Higgsfield) and 290+ OpenAI-compatible LLMs (Claude, GPT, Gemini, Llama, DeepSeek, Mistral) through one API key. Wraps the official Python SDK and a thin CLI.

WaveSpeedAI inference gateway — 700+ media models (FLUX, Kling, Veo, Luma, Seedance, Z-Image, Wan, Qwen, Higgsfield, ace-step) and 290+ OpenAI-compatible LLMs through one API key. Use whenever the user wants to generate AI media, list available models, check balance, or call Claude/GPT/Gemini through the WaveSpeed LLM proxy.

WaveSpeedAI inference gateway — 700+ media models and 290+ OpenAI-compatible LLMs in one API. Use for AI image/video/audio generation and for cheap proxied LLM calls.

Modo de resposta terse (estilo caveman) para economizar tokens de saída ~65%. Sempre ativo neste projeto. Preserva precisão técnica, código, commits, PRs intocados.

padronizar mensagens de commit seguindo Conventional Commits (type, scope opcional, subject curto, breaking change marcado)

Bundle de ~60 agents + ~221 skills cobrindo reviewers, build-resolvers, TDD, E2E, security, autonomous loops. Padrão do projeto — usar o MÁXIMO de agents possível em paralelo a cada alteração.

escrever ou atualizar testes end-to-end com Playwright neste projeto, garantindo trace, screenshot, vídeo e asserções consistentes

Loop autônomo de coding (read → plan → execute → lint → unit → e2e → fix → repeat) até DoD verde. Padrão deste projeto em TODA task técnica com acceptance criteria mensurável.

descreva em uma frase quando o agente deve ativar essa skill

Configure, extend, or contribute to Hermes Agent.

Map any code project with @wesleysimplicio/llm-project-mapper before doing work, so the Hermes Turbo Agent has the AGENTS.md / INIT.md / specs / skills scaffolding it needs to ship effectively.

Use RTK CLI (https://github.com/rtk-ai/rtk) to cut tokens during repo exploration and verbose validation

Delegate work with compact subagent outputs.

Apply ECC engineering patterns in Hermes.

N-Nest protocol — multi-level gate-corrected agent tree. PRIME depth verification, BH port.port.port addressing, per-level confabulation catch.

Tuple-Space + Yool safe-speed runtime for coding tasks. Use when the user asks to implement, refactor, fix, build, or explain code in a repository that vendors the simplicio-prompt spec (presence of YOOL_TUPLE_HAMT.md, kernel/yool_tuple_kernel.py, or a simplicio-prompt block in CLAUDE.md / AGENTS.md). Routes any user input through a Hilbert-indexed tuple graph with lazy batch_spawn, LaneWorkerPool, receipt cache, jittered backoff, circuit breakers and context compression. Scales to 1,000,000+ subagents without enumeration.

Autonomous sprint delivery. Reads a Jira / Azure DevOps / GitHub sprint, delegates each task's code edit to simplicio-cli, captures evidence, and opens a draft PR. Triggers on "rode o sendsprint", "executar sprint", "entregar sprint", "run sendsprint", "ship my sprint", "deliver my sprint", "ejecutar sprint".