AI & ML

felvieira Skill

Audita o peso de contexto carregado na sessão — CLAUDE.md, agents, MCP descriptions, rules ativas, skills invocadas e histórico acumulado. Estima tokens por componente, reporta headroom disponível e emite alertas de overflow. Distinto do cost-tracker (skill 30) que rastreia tokens gastos em completions runtime. Trigger em: "contexto inchado", "context overflow", "quanto contexto estou usando", "peso do contexto", "context budget", "tokens carregados", "sessao lenta", "respostas degradadas", "headroom de contexto", "custo fixo de contexto", "overhead de rules", "overhead dos agents", "impacto do MCP no contexto", "espaco no context window", "quanto cabe no context window"

ax-llm Skill

Use when writing Java code with `dev.axllm:ax` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.

ax-llm Skill

Use when writing Java code with `dev.axllm:ax` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

ax-llm Skill

Use when writing Python code with `axllm` for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed responses, and direct-respond executor skipping.

ax-llm Skill

Use when writing Python code with `axllm` for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.

ax-llm Skill

Use when writing Rust code with `axllm` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.

ax-llm Skill

Use when writing Rust code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

ax-llm Skill

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

ax-llm Skill

Use when writing Python code with `axllm` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.

ax-llm Skill

Use when writing C++ code with `axllm` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.

ax-llm Skill

Use when writing C++ code with `axllm` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

ax-llm Skill

Use when writing Python code with `axllm` for the playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook into a program.

ax-llm Skill

Use when writing Java code with `dev.axllm:ax` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.

ax-llm Skill

Use when writing Python code with `axllm` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.

ax-llm Skill

Use when writing Python code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

ax-llm Skill

Use when writing Rust code with `axllm` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.

ax-llm Skill

Use when writing Java code with `dev.axllm:ax` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

ax-llm Skill

Use when writing Rust code with `axllm` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

ax-llm Skill

Use when writing Go code with `github.com/ax-llm/ax/packages/go` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.

ax-llm Skill

Use when writing C++ code with `axllm` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.

ax-llm Skill

Use when writing Python code with `axllm` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.

ax-llm Skill

Use when writing Python code with `axllm` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.

ax-llm Skill

Use when writing Java code with `dev.axllm:ax` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.

ax-llm Skill

Use when writing Rust code with `axllm` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.

ax-llm Skill

Use when writing Python code with `axllm` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.

lyndonkl Bundle

Verify and debug equivariance in an implemented model.

plurigrid Skill

Agreement protocol in multi-agent systems

plurigrid Bundle

P-adic ultrametric skill embeddings with MLX Snowflake Arctic, DuckDB

plurigrid Bundle

SKILL: MCP Tripartite Integration

plurigrid Skill

System 2 attention mechanisms for deliberate, slow reasoning in transformer architectures.

iapro-community Bundle

Converter screenshots, prints, mockups e imagens de interfaces web/mobile em melhorias precisas de UX/UI, prompts de programação ou implementação solicitada. Usar automaticamente, sem menção à skill, quando houver referência visual de interface no pedido ou contexto acessível e intenção de melhorar a tela, deixar igual à referência, modernizar layout, comparar telas ou gerar prompt para Codex/Claude. Não usar só pela presença de imagem, para retocar fotos, criar artes promocionais, transcrever texto ou diagnosticar erros de terminal.

iapro-community Skill

Use for server-side AI orchestration in SaaS products, including OpenAI, Gemini, Claude, ElevenLabs, streaming, transcription, structured extraction, prompt contracts, token budgets, model routing, queues, retries, observability, consent, validation, and safe API key handling.

bkjohn2018 Skill

SOP Writing

bkjohn2018 Skill

Reviews conceptual, logical, and physical data models using Data Model Scorecard categories to produce structured findings, scores, and remediation plans. Use when users request model quality validation, review readiness checks, or formal data model QA.

bkjohn2018 Skill

Analyzes actual-vs-plan and period-over-period financial variances against predefined dimensions (entity, account, product, region) using standard volume/rate/mix decomposition, with business interpretation. Use when finance teams need variance narratives and action-focused insights explained against known categories. Use `predictive-model-development` instead when the explanatory grouping itself is unknown and must be discovered (e.g., clustering or segmentation to find which vendors, invoice types, or processors are driving a pattern).

bkjohn2018 Skill

Predictive Model Development