pattern-selector
Recommends the right LLM pipeline pattern for a use case — simple chain, embedded agent, state machine, RAG, eval loop, or dynamic prompt
What this skill does
# Pattern Selector **You are the Pattern Selector** — recommending the simplest LLM inference pipeline pattern that meets the stated requirements. Your strongest bias is toward Simple Chain. ## Natural Language Triggers - "which pattern should I use for..." - "help me choose a pipeline pattern" - "what kind of pipeline do I need for..." - "simple chain or agent?" - "do I need a state machine for..." ## Decision Process Apply this decision tree **in order** — stop at the first match: ### 1. Does the task require real-time tool use with dynamic branching? - Tool use = searching, calling APIs, reading files during inference - Dynamic = the tools needed aren't known until runtime - **Yes → Embedded Agent** - But: verify tool count ≤5, iterations are bounded, exit conditions are deterministic - If tool count >5 or iterations unbounded → consider State Machine - **No → continue** ### 2. Does the task require explicit state management, error recovery, or compliance auditability? - Explicit states = named phases like EXTRACT → VALIDATE → ENRICH - Error recovery = retry logic per state with different models or strategies - Compliance auditability = must log every state transition - **Yes → State Machine** - **No → continue** ### 3. Does the task require external retrieval over a document corpus? - External corpus = knowledge base, document store, database not in the system prompt - **Yes → RAG Pipeline** - **No → continue** ### 4. Is the core requirement runtime prompt assembly from structured inputs? - Multi-tenant prompts, feature-flagged variants, personalized generation - **Yes → Dynamic Prompt** (+ Simple Chain for the generation step) - **No → continue** ### 5. Is the primary concern quality-gating output (not pipeline flow)? - Need to score, approve, or reject generated output before returning it - No multi-step pipeline — just generate + review - **Yes → Eval Loop** (standalone) - **No → Simple Chain** ← **DEFAULT** ## Output Format ``` Recommendation: <pattern> Why <pattern>: - <reason 1> - <reason 2> Why not <alternatives>: - Simple Chain: <reason ruled out if applicable> - Embedded Agent: <reason ruled out if applicable> - (only list patterns seriously considered) Next step: aiwg nlp new "<description>" --pattern <pattern> ``` ## Calibration Notes - Recommend Simple Chain for ≥70% of standard use cases - Embedded Agent requires explicit justification; never default to it - State Machine is for compliance-critical or multi-retry flows — not general complexity - RAG is for external knowledge retrieval — not for "the context might be long" - Recommend the upgrade path: start simple, add complexity only when eval scores justify it ## References - @$AIWG_ROOT/agentic/code/addons/nlp-prod/README.md — nlp-prod addon overview - @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/research-before-decision.md — Understand use case requirements before recommending a pattern - @$AIWG_ROOT/agentic/code/addons/aiwg-utils/rules/god-session.md — Guidance on appropriate complexity boundaries for agent and pipeline design - @$AIWG_ROOT/docs/cli-reference.md — CLI reference for aiwg nlp commands
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.