AI & ML

arfar-x Skill

Changes the tone/style the agent uses for the rest of the conversation -- neutral, alpha, angry, sarcastic, flatterer, or too-kind. Invoke as "/mood <mode>" or in plain language ("be angrier", "roast me", "be an alpha about this", "tone it down", "go back to normal"). Affects delivery only, never substance: never skips a safety refusal or a write-confirmation gate, never fabricates an answer, and is never directed at anyone outside this conversation.

arfar-x Skill

Writes or updates an AGENTS.md file for a target project (or, for a monorepo, a root AGENTS.md plus nested per-subproject AGENTS.md files) -- the open, tool-agnostic convention (agents.md) that gives a coding agent the build/test/architecture/style context a README doesn't. Infers the project's real structure from workspace tooling and CI, not guesses. Searches the whole project tree for AGENTS.md files that already exist in subdirectories and inspects each for staleness or gaps -- without mechanically listing every one in the root's Project map, since agents already find the nearest one by directory proximity -- and asks the user before enhancing any of them. For a monorepo, asks before even scanning the tree for subdirectories that would benefit from their own nested AGENTS.md (that scan can be slow on a large repo), then asks again before creating any of the files it finds. A nested AGENTS.md this skill writes stays scoped to its own subtree -- it never restates the root file's overview or structure. Only

neomjs Bundle

Expert tactical knowledge on sequencing Neural Link MCP tools to inspect, debug, and manipulate live Neo.mjs applications. Triggers: Use this skill if the user asks you to interact with the browser, inspect the UI natively, patch live code, or use the Neural Link.

neomjs Bundle

Execute autonomous diagnostics, verify MCP server stability, and treat system degradation using tests and memory core forensics. Triggers: [Healthcheck, run health checklist, diagnose system collapse, MCP infrastructure failure, troubleshoot agent OS, system degraded, Sandman handoff verification failure, self-repair, system recovery]

neomjs Bundle

Standardized guidelines and procedural execution flow for opening a Pull Request. CRITICAL: Do NOT run default `npx playwright test` (use custom configs). MANDATORY ROI WARNING: Skipping the PR body template guarantees CI lint failure. Triggers: Code modifications complete; before opening PR — stepping-back reflection, commit format, cross-family review mandate, post-comment A2A commentId hand-off (author→reviewer) per review-response-protocol.md §14, Evidence declaration line for substrate/runtime-AC PRs per the [Evidence Ladder](https://github.com/neomjs/neo-agent-brain/blob/dev/learn/agentos/process/evidence-ladder.md).

neomjs Bundle

Authoritative protocol for creating Neo.mjs GitHub issues. Enforces duplicate sweep, Fat Ticket body structure, strict label rules, title hygiene, and the six-stage challenge chain at creation time. CRITICAL: Do NOT run default `npx playwright test` to verify issues; Neo uses multiple custom playwright configs (e.g., unit, e2e) which must be explicitly targeted. Use immediately before calling the create_issue MCP tool. Triggers: Use this skill before any invocation of the create_issue MCP tool. This is the creation-side dual of ticket-intake (which consumes existing tickets).

neomjs Bundle

Authoritative protocol defining the "Pre-Execution Reflection Gate". Mandates architectural validation, negative ROI calculation, and duplicate sweeps before an agent is permitted to begin working on a GitHub Issue. Triggers: Use this skill immediately when assigned a ticket whose authoring you did NOT see, before checking out a branch or writing any codebase modifications. A ticket YOU authored this session is exempt EXCEPT the prescription check; one you authored in an earlier session runs a cheap drift probe instead — never an exemption you judge for yourself.

neomjs Bundle

Authoritative protocol for maintainer-side label triage of unlabeled contributor tickets. Codifies the social contract for what happens when a ticket arrives without `ai`, primary (`bug`/`enhancement`/`epic`), or secondary labels. Triggers: Use this skill when an agent with maintainer permissions (`WRITE` permission or higher) encounters a ticket lacking `ai`, primary, or secondary labels — typically authored by a non-maintainer contributor or a lower-privileged agent who couldn't apply labels at create-time.

neomjs Bundle

Authoritative protocol for gracefully terminating an agent session. Mandates structured handover comments, mental-model states, and memory persistence to prevent Zero-State Amnesia. Triggers: When concluding a long-running session, executing the Sunset Protocol, handing over work for the next agent, or terminating an agent cycle.

neomjs Bundle

Proactive architectural review skill using Frontier Model semantic RAG to sweep historical issues and Memory Core sessions for technical debt. Triggers: Use this skill when conducting architectural analysis, proactively searching for technical debt, auditing the repository for abandoned logical loops, when explicitly requested to scan for ambient architectural debt, or during PR review for fundamental architectural shifts.

neomjs Bundle

The L2 Channel Separation and Prompt Firewall defense mechanisms to prevent injection attacks and Helpful Assistant regression.

neomjs Bundle

High-level umbrella router for navigating broad, cross-substrate architectural ambiguity. Triggers: Use when no narrower pre-flight clearly applies, or when work spans multiple trigger families such as new subsystems, protocols, MCP tools, or cross-substrate refactors.

prayceo Bundle

Break mental blockers using Oblique Strategies (Brian Eno/Peter Schmidt). Use this skill whenever the user says they're stuck, blocked, in a rut, can't decide, overthinking, going in circles, need a fresh perspective, or asks for a creative prompt / random strategy / oblique strategy / lateral thinking. Also trigger when the user says 'draw a card', 'give me a strategy', 'help me think differently', 'I'm blocked on...', 'unstick me', 'shake things up', or any variation of seeking creative unblocking. Even if the user just says 'oblique', 'Eno', 'OS Skill', or 'OS' (short for Oblique Strategies), use this skill.

richkuo Skill

Use when the user wants a task planned by a Fable 5.1 planning subagent before building it. Spins up a Plan subagent running on Fable 5.1 to produce an implementation plan, relays the plan back to the main agent, and — if a GitHub issue is referenced — posts the plan as a comment on that issue and asks the user whether to continue building now before proceeding. Trigger on "/fableplan", "fableplan this", or "plan this with fable".

richkuo Bundle

Use when the user wants the current large language model to plan and build a task in the same session without a subagent. When an issue is referenced, it posts the plan and asks whether to build. Without an issue, it builds and opens a pull request after presenting the plan. Trigger on "/issueplan", "issueplan this", or "plan this issue in this session".

richkuo Skill

Required dispatch procedure for running a build, fix pass, or validate pass on an external coding CLI — the Codex CLI (`codex exec`) or the Cursor CLI (`agent -p`) — when an issue's Execution block stamps that harness as the Build model or the Validate model. Preflight, the shims, the prompt-as-data rule, the background-and-poll rule, result parsing, the substitution check, attribution, and the failure table. Load BEFORE dispatching any Codex CLI or Cursor CLI build or validate pass.

richkuo Skill

Use when the user wants a task executed by the current session model with a persistent Fable 5.1 advisor overseeing it. A read-only Fable 5.1 subagent writes the plan and answers checkpoint consults; a separate fresh Fable 5.1 reviewer issues a binding pre-commit verdict. Accepts a GitHub issue or a prose task. Trigger on "/fable-advisor", "fable-advisor <task or issue>", or "execute this with a fable advisor".

richkuo Skill

Use when the user wants a GitHub issue validated by a Fable 5.1 subagent. Spins up a read-only subagent running on Fable 5.1 that executes the validate-issue procedure (claim tracing, architecture/consistency checks, complexity score), then relays the verdict back to the main agent, which presents it and takes any follow-on action (update issue, work on issue). Trigger on "/fable-validate", "fable validate <issue>", or "validate this with fable".

richkuo Skill

Use when the user wants a GitHub issue created by a Fable 5.1 subagent. Spins up a read-only subagent running on Fable 5.1 that executes the new-issue procedure (duplicate check, code grounding, approach design, complexity score) and returns a fully-composed issue draft, which the main agent spot-checks and files. Trigger on "/fable-new-issue", "fable new issue <description>", or "create this issue with fable".

gktuoktay Skill

LLM bağlamı şiştiğinde, alakasız dosyaları bellekten temizleme kapasitesi.

gktuoktay Skill

Veritabanı, GitHub, Jira gibi MCP bağlantılarını otonom sisteme dahil eden kural seti.

gktuoktay Skill

LLM'in pahalı bulut çözümlerini engelleyip, en ucuz mimariyi dayatan ajan.

gktuoktay Skill

Dış yapay zekalardan gelen JSON yanıtlarını denetleyip halüsinasyonları durduran kapı.

rylaispirit Bundle

Convert documentation websites, GitHub repositories, PDFs, and reference sets into portable Agent Skills with source traceability and validation.

cadugevaerd Bundle

Especialista LangSmith-first para projetar, implementar, executar e auditar evals de chatbots, RAG, agentes, nodes e grafos; criar datasets/evaluators/experiments/backtests; comparar modelos e aplicar gates de promocao com evidencia. Use em qualquer mudanca de modelo, prompt, tool, retrieval, LangGraph ou comportamento agentico que precise de qualidade mensuravel.

cadugevaerd Skill

Decide quando usar RAG, KAG, GraphRAG ou arquitetura híbrida para sistemas LLM com conhecimento externo.

cadugevaerd Bundle

Entrevista técnica (estilo grill-me) para decidir primeiro se LangGraph é justificado e, somente quando for, desenhar o fluxo LangGraph com diagrama, State CRUE e tabela de nodes. Use quando o usuário quiser desenhar agentes/workflows, avaliar se LangGraph é excesso de engenharia, decidir agent-as-node vs nodes explícitos, ou separar um hot path determinístico de uma consulta/agente adaptativo.

cadugevaerd Skill

Entrevista curta para transformar uma ideia de agente em um system prompt pronto para copiar e colar. Use quando o usuário pedir um agente "prompt-only", system prompt ou instruções de sistema para um agente sem ferramentas, código, memória externa, RAG ou automações.

cadugevaerd Bundle

Seleciona até 5 candidatos OpenRouter para Model Engineering Eval com inteligência Artificial Analysis >35 via OpenRouter Benchmarks, reasoning controlável, throughput hard >=60 t/s e latência p50 <2min/p99 <3min.

irahardianto Bundle

Structured code review protocol: inspect against full rule set. Use for audit workflows, code reviews, or when user requests review. Produces findings document with severity tags.

fused-gaming Skill

mcp-builder

fused-gaming Skill

Coordinate complex project work using SyncPulse's workspace-scoped swarm architecture. Use when a request should be decomposed across planning, design, architecture, implementation, testing, review, remediation, release, or capability-management workspaces; when model cost should be minimized; or when agent/tool/skill capability gaps must be identified.

fused-gaming Skill

Discover, evaluate, and install verified @h4shed skills, tools, and agents from the live npm ecosystem and the Fused-Gaming-Skill-MCP registry into this project, so the plugin's tool/skill/agent set can grow without hand-editing config. Use when the operator asks to add a capability, when the capability-scout records a gap, or when asked to sync/update the installed ecosystem.

aethrox Bundle

Hand off in-progress work, an on-call shift, or an open incident to another person or agent using a fixed four-part structure, so nothing load-bearing is lost between one owner and the next. Use when work needs to change hands mid-flight, an on-call rotation is ending, or an open incident is passing to a new owner. Not for compacting a conversation so a fresh session can resume, which is a session-continuity concern.

aethrox Bundle

Investigate a technical question against primary sources and capture the findings, with citations, as a file in the repo. Use when the user wants a topic researched, docs or API facts gathered, a claim verified before it's relied on, or reading legwork delegated to a background agent.

aethrox Bundle

Build a throwaway spike solution to answer one design or technical question before committing to an approach. Use when the user wants to sanity-check whether a state model, logic, or UI direction feels right, is unsure an approach will work, or wants to explore options before writing production code.