Trigger with "run self-audit", "test the analyzer", "regression test the plugin analyzer", "audit the agent-scaffolders", or "verify the analyzer works correctly".
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…
Reviews a completed os-eval-runner lab run and backports approved changes to master plugin sources. Trigger with "backport the eval results", "review the lab run", "apply eval…
Trigger with "mine plugins", "analyze plugin collection", "run the full analysis pipeline", "inventory and analyze all plugins", "mine patterns from this directory", or when you…
Updates model catalogs and cheapest-model references for all CLI backends (copilot, agy, claude, codex, llama).
Maintains a persistent, folder-based log of all agentic-os experiment runs. Each run writes one dated file to context/experiment-log/ and updates index.md.
Trigger with "evaluate autoresearch fit", "score this skill for karpathy loop", "is this a good autoresearch candidate", "assess autoresearch viability for", "which skills are…
Trigger with "mine this skill", "analyze this skill", "run targeted skill analysis", "extract patterns from this skill", or when you want focused analysis on a single Agent Skill…
Detect and prevent computational bugs in the DCF / scenario valuation engine that produce nonsensical target prices.
Converts conversational input and images from the user into structured parameters. Handles missing or ambiguous data by defining defaults or returning flags for required…
Agent-powered RLM cache distillation. Replaces the slow local Ollama distiller with the agent's own summarization capability for both rlm_summary_cache.json and…
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…
Poll SEC EDGAR for 13F-HR institutional filings from a target fund, download and parse holdings into structured JSON, and generate quarter-over-quarter diffs.
Interactively select and uninstall agent plugins and skills from the local .agents/ environment.
Activate when the user wants to install, deploy, test, or materialize an APM package into runtime directories such as .agents/, .github/, .claude/, .cursor/, .gemini/, .codex/,…
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,…
Progressive-disclosure query against the Obsidian LLM wiki. Returns RLM summary first, expands to bullets, then full wiki node on demand.
Master synchronization and garbage collection skill. Synchronizes the local plugins against the vendor inventory.
Living Chronicle journaling agent. Auto-invoked when creating project event entries, searching history, or reviewing past sessions.
Initialize and onboard a new project repository as an Obsidian Vault. Covers prerequisite installation, vault configuration, exclusion filters, and validation.
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation. — from richfrem/Project_Sanctuary
Create an isolated workspace (worktree) for implementing a specific work package.
Programmatically create and manipulate Obsidian Canvas (.canvas) files using JSON Canvas Spec 1.0. Enables agents to generate visual flowcharts, architecture diagrams, and…
Prepares a standalone adversarial review bundle of the investment thesis, DCF projections, and proposed weights for paste into an external LLM (Grok, ChatGPT, Gemini).
SME-facing orchestrator for the Business Exploration Loop. Supports 4 session types (greenfield, brownfield, discovery-only, spike) with adaptive phase selection.
Interactive RLM cache initialization. Use when: setting up a new project's semantic cache for the first time, or adding a new cache profile.
Synchronizes local plugins from the vendor inventory, safely cleaning up deleted vendor plugins while preserving project-specific customizations.
Copilot CLI sub-agent system for persona-based analysis. Use when piping large contexts to GitHub Copilot models for security audits, architecture reviews, QA analysis, or any…
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.
Generates architectural SVG drawings and updates the composite dependency manifest.
The master self-evolving workflow for authoring, research, and managing custom Pine Script v6 indicators.
Fetches, analyzes, and lists active TradingView price alerts, saving the snapshot to the backend data folder for offline caching and verification.
Synchronizes portfolio holdings and researched tickers from projections / watchlist.json to TradingView watchlists.
Activate when the user wants to create a new APM-native package from scratch for reusable agent skills, agents, commands, hooks, MCP configuration, prompts, or governance-managed…
Acts as a seasoned Technical Analyst and Pine Script expert. Navigates TradingView to the requested ticker and timeframe, builds the optimal indicator view (reading existing…
Session manager for RSVP speed reading. Orchestrates reading sessions with pause, resume, speed adjustment, and comprehension check-ins.
Translate .mmd diagram files into PNG images with configurable resolution (retina/HQ/scale), supporting rasterization (raster, rasterize, rasterization).
Audits analysis coverage across all portfolio holdings and watchlist tickers. Identifies unanalyzed tickers ($0.00 price, missing DCF projections, missing TA levels), ranks them…
Provides sandboxing validation, HMAC key rotation, and budget verification to manage security boundaries under Agentic Group Theory (AGT).
Provides validation, setup guidance, and a local test harness simulator to run skills within the Microsoft Agent Framework (MAF).
Initialize HuggingFace integration - validates .env variables, tests API connectivity, and ensures the dataset repository structure exists.
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…
Convert raw plugin analysis results into actionable improvement recommendations for agent-scaffolders and agent-scaffolders.
Builds an executable safety net of characterization tests by integrating browser flow recording, API payload snapshotting, DOM state captures, network traces, and mock fixture…
Adversarial red-team reviewer for Technical Analysis theses. Acts as a Senior Risk Manager and Skeptical Proprietary Trader who challenges TA logic, validates price levels against…
Change the active TradingView chart symbol. Clicks the symbol button in the chart header, types the ticker, and confirms with Enter.
Session manager for RSVP speed reading. Orchestrates reading sessions with pause, resume, speed adjustment, and comprehension check-ins.
Project Sanctuary-specific skill for Spec-Driven Development. Knows the project's constitution, safety rules, AUGMENTED.md best practices, and how the spec-kitty-plugin should be…
Audit a file for TODO comments, pending work items, or technical debt markers. Useful for checking code readiness before a commit or reviewing task status.
Captures a TradingView chart screenshot and performs visual technical analysis. Reads the live chart image (with whatever indicators the user has configured) and produces…
Create or update the feature specification from a natural language feature description. — from richfrem/Project_Sanctuary
Synchronizes the agent environments. Looks at the inventory (plugin-sources.json) and reinstalls all skills and plugins from the sources indicated.
Summarize podcast episodes from audio metadata. Extracts ID3 tags, chapter markers, and show notes.
Converts Markdown files to one MS Word document per file using plugin-local scripts. V2 includes L5 Delegated Constraint Verification for strict binary artifact linting.
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…
Progressively migrates legacy prototype routes and features to a clean architecture layer slice-by-slice, verifying them against characterization tests, running purity/drift…
(Industry standard: Parallel Agent) Primary Use Case: Work that can be partitioned into independent sub-tasks running concurrently across multiple agents.
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 Quality Assurance Operator for documentation link integrity and scans. Automatically handles automated link validation, auditing, fixing, and repairing broken…
End-to-end pipeline that transforms an undocumented vibe-coded prototype into a Spec Kit-compatible specification package and a Superpowers-ready implementation handoff, including…