with one click
LLM-WIKI
LLM-WIKI contains 32 collected skills from angrysky56, with repository-level occupation coverage and site-owned skill detail pages.
Skills in this repository
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.
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.
State-Scout — builds custom state-tracking harnesses for difficult task classes, runs competence-frontier probes, writes findings to wiki. Triggered by overseer or stuck-task signals.
Daily OrCAID multi-agent delegation — run commit0/self_improve/paperbench tasks, evaluate output, deliver results. Schedule: 09:00 AM.
Meta-advancement tracking framework — per-agent state, advancement formula, scrutiny/improvement cycles. Used by overseer to track agent progress and coordinate tasking.
Expert system skill for the AGEM engine with full EFHF MCP server integration. Covers native tools, meta-tool MCP access, sheaf consistency enforcement, ethical evaluation, formal logic, advanced reasoning, and multi-server orchestration strategies.
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.
Reflection pattern for quality-critical outputs using generate-critique-refine cycles. Requires clear evaluation criteria and acceptable latency.
Sequential workflow pattern for deterministic, fixed-path tasks. Use when solution steps are known upfront and follow a stable repeatable sequence.
ArXiv research curator agent — bootstraps from agent-sheets/arxiv.md directives. Discovers, downloads, and reports on ML/AI papers from arXiv.
Hierarchical supervisor pattern: Multi-level supervisor chains.
Wiki Librarian agent — audits vault structural quality, delegates fix work to librarians-assistant subagent for iterative remediation. Reports what was done, not what needs doing.
News curator agent — bootstraps from agent-sheets/news.md directives. Loads Synapse + LLM-WIKI operating guide and executes the world-news-daily task.
OrCAID multi-agent execution engine — correct entry (orcaid.cli), local path support, auto-build Docker, three task types (commit0/self_improve/paperbench)
Paper2Code-Enhanced — multi-agent paper-to-code pipeline (planning → analyzing → coding) using PaperCoder. Generates working implementations from ML papers. ~$0.50–0.70 per run, ~1 hour per run.
Parallel execution pattern: Multiple agents work simultaneously on independent sub-tasks.
Wiki Researcher agent — bootstraps from agent-sheets/researcher.md directives. Loads Synapse + LLM-WIKI operating guide and executes the knowledge discovery task.
Single-agent pattern: One LLM handles all tasks without sub-agent delegation.
Supervisor delegation pattern: One supervisor LLM routes tasks to specialized sub-agents.
Supervisor-orchestrator pattern: Orchestrator controls task planning and delegation.
No description.
EFHF three-tier ethics framework with Omega1-4 axioms, Paraclete Protocol, and sheaf-based value-drift detection. Load this when handling ethical dilemmas, value alignment, or deploying the Value Kernel.