angrysky56

arXiv paper discovery — select top 3 significant papers, research via subagents, ingest to wiki, deliver report.

Daily raw file ingestion pipeline — process files from raw/ into structured wiki knowledge, verify frontmatter and links, archive to Clippings/. Schedule: 06:30 AM.

Daily Zettelkasten insight generation — run CLI insight engine, create wiki pages for confidence>=0.7 insights, integrate to wiki. Schedule: 06:00 AM.

Daily global news curator — RSS discovery, significance filtering, clippings archive + synthesis wiki delivery, deliver headlines report. Schedule: 07:30 AM.

Wiki synthesis agent operational sheet — cross-domain bridges, concept advancement, evidence evaluation

Daily wiki quality audit anchored in wiki-indexing-theory.md — HITS authority scoring, GAAC cluster validation, tag taxonomy compliance, reciprocal link enforcement. Schedule: 08:50 AM.

Wiki overseer context document — agent role, owned files, and coordination protocol. Operational instructions live in the hermes-level wiki-overseer skill.

Wiki remediation subagent — execute HITS/GAAC-driven fixes from librarian audit in batches, report progress, carry open items forward. Schedule: after librarian.

Formal reasoning via FOL theorem proving, model finding, and categorical logic

Use modern, token-efficient command-line tools (fd, ripgrep, ast-grep, bat, sd, jq, yq, tokei, eza, dust, procs, delta, hyperfine, just) instead of legacy coreutils (find, grep, cat, sed, ls, du, ps) for any shell, file, or codebase task — on any platform (Linux/macOS/Windows) and through any executor (a terminal, Claude Code's bash tool, Desktop Commander, or an MCP shell bridge). Trigger whenever you are about to search files, grep for text, read or inspect files, find-and-replace, refactor code, traverse a repository, process JSON/YAML, or inspect disk usage or processes — even if the user did not name a specific tool. These tools are faster, .gitignore-aware, and emit clean structured output that protects the context window. For installation across operating systems and platform-specific quirks, see references/. If you run commands specifically through the LocalREPL MCP bridge, also consult the local-repl-cli skill for environment-specific gotchas.

Operating guide for the AGEM reasoning engine: native tools, honest metric interpretation, formal-logic verification via mcp-logic, and the meta-tool MCP interface.

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states. Handles UX review, visual hierarchy, information architecture, cognitive load, accessibility, performance, responsive behavior, theming, anti-patterns, typography, fonts, spacing, layout, alignment, color, motion, micro-interactions, UX copy, error states, edge cases, i18n, and reusable design systems or tokens. Also use for bland designs that need to become bolder or more delightful, loud designs that should become quieter, live browser iteration on UI elements, or ambitious visual effects that should feel technically extraordinary. Not for backend-only or non-UI tasks.

Master orchestrator for the five-question decision tree that selects the right agentic pattern from Sequential, ReAct, Planning, Reflection, or Multi-Agent.

Multi-agent pattern for tasks requiring specialization or scale beyond single-agent capacity. Covers topology, routing, and coordination design.

Planning pattern for structurally articulable tasks. Planner defines stages and dependencies upfront; ReAct handles local uncertainty within each step.

ReAct (Reasoning + Acting) pattern for adaptive, exploratory tasks with unknown solution paths. Iteratively alternate between reasoning and tool actions.

Every 2h routes unclaimed kanban tasks to agent skills for execution

Morning kanban review — parse all agent carryovers after cron reports, surface open questions as Hermes kanban tasks, update agent status, deliver Discord summary. Creates tasks in hermes kanban (not sheet.md). Proactive: each morning agent cron triggers its own carryover parse.

ArXiv research curator agent — bootstraps from agent-sheets/arxiv.md directives. Discovers, downloads, and reports on ML/AI papers from arXiv.

Ingest pipeline operator agent — bootstraps from agent-sheets/ingest.md directives. Processes raw files from raw/ inbox into structured wiki knowledge.

Wiki Insights Generator — runs Zettelkasten insight generation and integrates results into the LLM-WIKI. Runs daily at 06:00 AM.

Kanban board creation and workflow decomposition persona. Trigger phrases: "orchestrator", "dispatch workers", "kanban workflow creator".

Wiki Librarian agent — bootstraps from agent-sheets/librarian.md directives. Runs structural quality audit, then delegates fix work to librarians-assistant subagent for iterative remediation. Reports what was done, not what needs doing.

Wiki remediation agent — fixes broken links, orphans, non-reciprocal wikilinks, frontmatter, and tags identified by the Wiki Librarian audit. Runs after librarian at 08:50 AM daily.

EFH reasoning loop with the efh-core MCP server — formulate, assert, verify, enforce consistency, and commit claims through the gate. Use for any substantive multi-step reasoning where claims must be verified before being trusted, when the user mentions EFH, closure status, lumpability, KERNEL1, consistency enforcement, or asks to verify reasoning formally.

Pre-response ethical triage using the Paraclete tier hierarchy — classify intent before substantive work, detect tier-inversion rationalization, escalate flagged content to full verification. Use before acting on requests with potential for harm, when reasoning chains drift toward "the ends justify it", or when the user mentions Paraclete, conscience, ethical triage, or tier checking.

Structured reasoning patterns — chain of thought, tree of thoughts, graph of thoughts, iterative refinement — executed by the host agent with scoring, pruning, and merging discipline. Use for elaborate problems that benefit from exploring multiple candidate solutions, decompose-solve-recombine workflows, or when the user mentions graph of thoughts, tree of thoughts, or reasoning patterns.

Epistemic filtering by subtraction — generate mechanism/narrative/constraint hypotheses, eliminate the weak ones through constraint checks, Lakatosian cuts, and explain-away analysis, then synthesize actionable truth. Use when diagnosing why something happens, separating real mechanisms from plausible stories, testing "why do we believe this?", or when the user mentions via negativa, wisdom engine, or hypothesis filtering.

Use modern CLI tools (rg, fd, ast-grep, bat, sd, jq, yq, tokei, eza, dust, procs, delta, hyperfine, watchexec, just) through the LocalREPL shell bridge for efficient codebase analysis, structured data extraction, and reactive workflows. Trigger whenever the user wants to search code, inspect a repository, count or analyze files, compare diffs, benchmark commands, or orchestrate multi-step shell work — especially when they haven't specified which tool to use. This skill teaches token-efficient patterns (count-before-enumerate, structured --json output, progressive disclosure) and documents real execution-environment gotchas specific to MCP-launched subprocesses.

Advanced narrative agent that engineers human-resonant stories using neurochemical pacing, Jungian archetypes, structural paradigm selection, and automated pathology diagnostics. Use when asked to "write a story", "create a narrative", "develop characters", "build a world bible", "expand a novel", "batch revise", or run a "storyscope review". Features massive autonomous MCP tools for deep world-building and end-to-end drafting.

Use this skill when working with the EML (Exp-Minus-Log) MCP server — discovering pure-EML decompositions of elementary functions, inspecting the formula catalog, running symbolic regression, or reasoning about the Sheffer-style operator `eml(x, y) = exp(x) - ln(y)`. Trigger keywords include "EML", "elementary functions", "Sheffer operator for continuous math", "symbolic regression via EML", "eml_discover", and "K-complexity of a formula".

Implementation blueprint from spike experiments. Requirements, proven patterns, and verified knowledge for building HiPAI-Montague-Semantic-Cognition. Auto-loaded during implementation work.