agent-plugins-skills

(Industry standard: Parallel Agent) Primary Use Case: Work that can be partitioned into independent sub-tasks running concurrently across multiple agents. Parallel multi-agent execution pattern. Use when: work can be partitioned into independent tasks that N agents can execute simultaneously across worktrees. Includes routing (sequential vs parallel), merge verification, and correction loops.

(Industry standard: Sequential Agent / Agent as a Tool) Primary Use Case: Delegating a well-defined task to a worker agent, verifying its execution, and repeating if necessary. Inner/outer agent delegation pattern. Use when: work needs to be delegated from a strategic controller (Outer Loop) to a tactical executor (Inner Loop) via strategy packets, with verification and correction loops.

(Industry standard: Loop Agent / Single Agent) Primary Use Case: Self-contained research, content generation, and exploration where no inner delegation is required. Self-directed research and knowledge capture loop. Use when: starting a session (Orientation), performing research (Synthesis), or closing a session (Seal, Persist, Retrospective). Ensures knowledge survives across isolated agent sessions.

(Industry standard: Routing Agent / Orchestrator Pattern) Primary Use Case: Analyzing an ambiguous trigger and routing it to one of the specific specialized implementations. Routes triggers to the appropriate agent-loop pattern. Use when: assessing a task, research need, or work assignment and deciding whether to run a simple learning loop, red team review, dual-loop delegation, or parallel swarm. Manages shared closure (seal, persist, retrospective, self-improvement).

(Industry standard: Review and Critique Pattern) Primary Use Case: Iterative generation paired with adversarial review, continuing until an 'Approved' verdict is reached. Orchestrated adversarial review loop. Use when: research, designs, architectures, or decisions need to be reviewed by red team agents (human, browser, or CLI). Iterates in rounds of research → bundle → review → feedback until approved.

(Industry standard: Meta-Learning System / Automated Autoresearch) Primary Use Case: Continuous, self-improving orchestration of an agentic system over multiple sessions. Use when: building a continuous improvement layer that autonomously identifies workflow friction, postulates hypotheses, and tests improved instructions/coding skills against an objective headless benchmark before merging and persisting.

Antigravity (`agy`) CLI sub-agent system for frontier Google Gemini models. Use when dispatching tasks to Gemini 3.5 Flash and above via the `agy` binary. For cheaper/older Gemini models (gemini-3-flash-preview, gemini-3.1-pro-preview), use gemini-cli-agent instead. Trigger with "use agy", "dispatch to antigravity", "run with agy", "use frontier gemini model", or "agy sub-agent".

Generate Mermaid flowcharts documenting business processes, state machines, and workflow logic from session captures. Use when you need to map multi-step processes, approval flows, user journeys, or decision trees during exploration. Trigger with "map this workflow", "create a process diagram", "flowchart the business process", "document this workflow", or "visualize the state machine".

Guides a Subject Matter Expert through a structured discovery session to create and approve a Discovery Plan before any building begins. This is the HARD-GATE brainstorming skill — no prototype can be built until the SME explicitly approves the plan. Trigger phrases: "start a discovery session", "let's plan this out", "help me figure out what we're building", "I have an idea I want to explore", "let's start from scratch"

Interactive co-authoring skill for the narrow end of the exploration funnel. Synthesizes session briefs, BRDs, story sets, and prototype notes into a structured handoff package targeted at the correct downstream consumer (e.g., formal software specs, strategic roadmaps, or process documentation).

Interactive co-authoring skill for the wide end of the exploration funnel. Captures and refines the core intent, whether the outcome is a software app, a business process improvement, research analysis, or strategic roadmap. Guides users through gathering context, iteratively drafting the brief, and testing for blind spots.

SME-facing orchestrator for the Business Exploration Loop. Supports 4 session types (greenfield, brownfield, discovery-only, spike) with adaptive phase selection. Manages state via exploration-dashboard.md, enforces phase gates, and routes to child skills in sequence. Phases can be skipped based on session type. Single canonical entry point — invoke at the start of any exploration session or to resume an in-progress session. Trigger phrases: "start an exploration", "let's explore this idea", "resume my exploration", "where did we leave off", "start discovery".

Orchestrates the full prototype build cycle for a Subject Matter Expert. Coordinates layout confirmation and component building — it does not build components directly. Acts as the single entry point for all prototype-related requests. Trigger phrases: "build a prototype", "create a working prototype", "show me a working version", "prototype to clarify scope", "build an exploratory prototype"

Builds a prototype component by component, self-reviewing each component against the Discovery Plan before moving to the next. Invoked by prototype-builder after the layout direction is confirmed. Trigger phrases: "build the prototype", "let's build it", "start building". Also invoked by prototype-builder-agent after visual-companion confirms layout.

Use when starting any conversation - establishes how to find and follow the business exploration workflow.

Presents layout options to the SME in plain language before any prototype construction begins. Invoked after the Discovery Plan is approved to confirm visual structure and direction. Trigger phrases: "what should it look like", "show me some layout options", "let me see the design options before we build". Also invoked by prototype-builder after plan approval.

Discovers and persists the user's available AI environments (Claude, Copilot CLI, Agy CLI, Cursor, etc.) to context/memory/environment.md. Run once after OS setup or whenever the environment changes. os-architect and os-evolution-planner read this file to select the right delegation backend and cheapest brainstorm model automatically. Invoked by os-architect on first run if environment.md is absent.

Bootstraps a skill evaluation lab repo for an autoresearch improvement run. Trigger with "set up an eval lab", "bootstrap the eval repo", "prepare the test repo for skill evaluation", "create an eval environment for this skill", "set up the lab space for this skill", or when starting a new skill optimization run that needs a standalone test environment.

Stateless evaluation engine that scores and gates skill improvement iterations using headless Python evaluation scripts. Use when the user says "evaluate this skill", "run autoresearch loop on", "optimize this skill", "run the eval loop", or when another agent proposes a change to an existing skill and needs empirical validation before applying it. Supports autonomous loop mode for iterative improvement and single-shot QA mode for validating one specific proposed change. Requires Python 3.8+ and a git repository.

Codifies the plan-and-delegate workflow for evolving plugins, skills, and agents. Given a target (plugin/skill/agent name) and an evolution goal, this skill first brainstorms 2-3 approach options using the cheapest available model, presents them for selection, then writes a structured task plan and Copilot CLI delegation prompt for the chosen approach. Called by os-architect for Path B (update) and Path C (create) executions. Can also be invoked standalone.

Verifies that os-architect actually causes evolution — not just words. Dispatches os-architect in single-shot simulation mode for a given test scenario, then checks for real artifact presence (new files, HANDOFF_BLOCK, plan files). Reports PASS / FAIL with grep evidence. Accumulates results into a test report. Use after any changes to os-architect, os-evolution-planner, or improvement-intake-agent.

Tiered memory system for cognitive continuity across agent sessions. Manages hot cache (session context loaded at boot) and deep storage (loaded on demand). Use when: (1) starting a session and loading context, (2) deciding what to remember vs forget, (3) promoting/demoting knowledge between tiers, (4) user says 'remember this' or asks about project history.

Removes stale and orphaned entries from the RLM Summary Ledger. Use after files are deleted, renamed, or moved to keep the ledger in sync with the filesystem. <example> user: "Clean up the RLM cache after I renamed some files" assistant: "I'll use rlm-cleanup-agent to remove stale entries from the ledger." </example> <example> user: "The RLM ledger has entries for files that no longer exist" assistant: "I'll run rlm-cleanup-agent to prune orphaned entries." </example>

Knowledge Curator agent skill for the RLM Factory. Auto-invoked when tasks involve distilling code summaries, querying the semantic ledger, auditing cache coverage, or maintaining RLM hygiene. Supports both Ollama-based batch distillation and agent-powered direct summarization. V2 enforces Concurrency Safety constraints.

Distills uncached files into the Recursive Language Model(RLM) Summary cache Ledger. You (the agent) ARE the distillation engine. Read each file deeply, write a high-quality 1-sentence summary, inject it via inject_summary.py. The purpose is if you read the full file once and produce a great summary once it will avoid the need to read the file every time you need to know what the script does or what the details of the file are. most cases the RLM summary should be sufficient. Use when files are missing from the ledger and need to be summarized. <example> user: "Summarize these new plugin files into the RLM ledger" assistant: "I'll use rlm-distill-agent to read and summarize each file into the cache." </example> <example> user: "The RLM ledger is missing 40 files -- fill the gaps" assistant: "I'll use rlm-distill-agent to process the missing files." </example>

Interactive RLM cache initialization. Use when: setting up a new project's semantic cache for the first time, or adding a new cache profile. Walks the user through folder selection, extension config, manifest creation, and first distillation pass.

3-Phase Knowledge Search strategy for the RLM Factory ecosystem. Auto-invoked when tasks involve finding code, documentation, or architecture context in the repository. Enforces the optimal search order: RLM Summary Scan (O(1)) -> Vector DB Semantic Search -> Grep/Exact Match. Never skip phases.

Interactively initializes the Vector DB plugin. Guided discovery asks which folders to index, confirms the manifest, then scaffolds vector_profiles.json for high-performance In-Process or Native Server connections. Mandatory first step before ingestion or search.

Semantic search skill for retrieving code and documentation from the ChromaDB vector store. Use when you need concept-based search across the repository (Phase 2 of the 3-phase search protocol). V2 includes L4/L5 retrieval constraints.

Top-level orchestration skill coordinating the entire 7-step surgical vibe-to-enterprise reengineering pipeline with automated safety and economic optimization controls.

Claude CLI sub-agent system for persona-based analysis. Use when piping large contexts to Anthropic models for security audits, architecture reviews, QA analysis, or any specialized analysis requiring a fresh model context.

Codex CLI sub-agent for dispatching tasks to OpenAI-compatible models via the `codex` binary. Use for code-focused tasks routed to GPT-5 Codex or any OpenAI-compatible endpoint. Part of the run_agent.py multi-LLM task router — cli=codex target.

Copilot CLI sub-agent system for dispatching tasks and persona-based analysis to GitHub Copilot models. Use for task delegation (agent reads/writes files directly), security audits, architecture reviews, or any work requiring a fresh model context.

Gemini CLI sub-agent system for cost-efficient analysis using the `gemini` binary. Use when piping large contexts to cheaper Google Gemini models (gemini-3-flash-preview, gemini-3.1-pro-preview) for security audits, architecture reviews, or QA analysis. For frontier models (Gemini 3.5 Flash and above), use agy-cli-agent instead.

Local Gemma 4 12B sub-agent. Routes bounded tasks directly to the optimized llama-server at localhost:8089 — no routing proxy, no cloud API, 2–5s typical response. Use for fast, private, cost-free subtask delegation from any cloud primary agent. Part of the run_agent.py multi-LLM task router — cli=llama target.

Cross-platform setup wizard for the local Gemma 4 12B inference stack. Automates llama-server installation (binary download or Metal/CUDA/Vulkan/ROCm compile), model download, routing proxy daemon install (launchd/systemd/NSSM), and Mode A/B validation. Covers Day 1 bootstrap and Day 2+ reconfiguration.

Distills wiki source files into the RLM summary layer (summary.md, bullets.md, deep.md) using the cheapest available LLM CLI. Routes to Copilot gpt-5-mini first, then Claude Haiku, then Gemini Flash. Never uses Ollama. Use when wiki nodes need RLM summaries generated or refreshed.

Runs a semantic health check over the Obsidian LLM wiki using the cheapest available LLM CLI. Finds inconsistencies, missing concepts, stale articles, connection candidates, and new article suggestions. Writes a structured report to meta/lint-report.md. Use when the wiki is large enough to have quality drift, or as a periodic maintenance step.

Coding conventions enforcement agent. Auto-invoked when writing new code, reviewing code quality, adding headers, or checking documentation compliance across Python, TypeScript/JavaScript, and C#/.NET.

Systematically analyze agent plugins and skills to extract design patterns, architectural decisions, and reusable techniques. Trigger with "analyze this plugin", "mine patterns from", "review plugin structure", "extract learnings from", "what patterns does this plugin use", "check if this plugin is well-structured", "validate plugin compliance", or when examining any plugin or skill collection to understand its design. Use this skill even when the user just says "look at this plugin" or "tell me how this is structured."