Agentsop Vllm
Decision SOP for serving LLMs with vLLM. Covers PagedAttention mental model, quantization/parallelism/batching tradeoffs, OOM triage, and when NOT to use vLLM. Activates when a coder-agent is choosing or tuning an inference engine, debugging vLLM throughput/latency/OOM, or comparing vLLM against TGI/SGLang/TensorRT-LLM/llama.cpp.
LEAP
|
Lens
|
SkillAlchemy
|
Agentsop Repo Map
>-
Agentsop Multiscale Chunking
>-
Agentsop Agent Topology Selection
>-
Agentsop Langgraph
|
Agentsop Query Routing
>-
Agentsop State Reducer
|
Agentsop Bio Fraud Forensics
>-
Agentsop Llm Tool Idempotency
>-
Agentsop Structured Output Picker
>-
Agentsop Metric Design
>-
Agentsop Aider
>-
Agentsop Streaming Output
|
Agentsop Dspy
|
Agentsop Tool Scoping
>-
Agentsop Idempotent Ingestion
|
Agentsop Module Shape Selection
>-
Agentsop Http Tool Wrapping
|
Agentsop Per Model Artifacts
>-
Agentsop Bounded Loop
>-
Career Role Finder
>-
Agentsop Framework Selection
|
Agentsop Regression Gate
Build a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is a code change — gate it with a test suite (eval set + metric + threshold). Cross-framework SOP not surfaced by any single base skill.
Agentsop Repo State Gating
>-
Agentsop Output Format By Model
>-
Agentsop Map Reduce Fanout
|
Agentsop Observability Setup
|
Career Resume Tailor
>-
Agentsop Session State Hygiene
|
Agentsop Llm Artifact Versioning
>-
Agentsop Signature Design
>-
Agentsop Llm Engine Selection
Cross-engine decision rubric for self-hosting or recommending an LLM serving stack. Picks among vLLM, SGLang, TensorRT-LLM, TGI, llama.cpp, Ollama, and MLX as a function of (hardware × workload × constraint), not "which is fastest". Activates whenever a coder-agent must choose, defend, or migrate a serving runtime.
Agentsop Selfhost Decision
>-
Agentsop Cost Tiered Models
>-
Agentsop Llamaindex
|
Career Bullet Builder
>-
Career Experience Mapper
>-
Agentsop Reranker Stage
>-
Agentsop Crewai
SOP for building multi-agent systems with CrewAI — role-based collaboration, sequential/hierarchical processes, Flows, memory, delegation. Use when modeling agent teams with clear roles and task pipelines.
Agentsop Test Fix Loop
|
Career Gap Planner
>-
Career Jd Analyzer
>-
Agentsop Conventions Pinning
SOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md / .cursor/rules / .clinerules / AGENTS.md) so that a coder-agent reliably respects your codebase's style choices every session. Tool-agnostic; covers the four load mechanics (read-only attachment, ancestor-walk auto-load, glob-scoped rules, agent backstory) and the conflict resolution between pinned…
Agentsop Hybrid Retrieval
|
Agentsop Prompt History Inspect
|
Agentsop Multi Tenant Rag
|
Agentsop Domain Eval Set
Build and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic. Distinct from public benchmarks (MMLU/HumanEval/GSM8K via lm-evaluation-harness) which measure GENERAL capability. Only a held-out domain set predicts whether THIS system works on YOUR data. Collect real examples, label, hold out (never train/prompt on it), size 50-200, version it, refresh on drift.
Agentsop Context Scope Discipline
>-
Agentsop Dify
SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. Use when shipping LLM apps fast with a "no-code to pro-code" gradient, especially when non-engineers need to co-author the flow.
Agentsop Code Execution Decision
>-
Agentsop Prompt Compilation
The compile-readiness gate for prompt auto-optimization. Decide whether you have earned the right to run an optimizer (DSPy MIPROv2 / GEPA / BootstrapFewShot) before spending compute. Two preconditions only — a real metric, and enough examples for the optimizer you picked. Garbage metric in, garbage prompt out. Pick the optimizer by data scale; GEPA inverts the scale assumption (~10 examples + te…