Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

principal-researcher

Étoiles0

Forks0

Mis à jour25 mai 2026 à 01:17

Rigorous scientific researcher — formal problem epistemology, complexity profiling, mathematical optimization, robust falsification protocols

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

angrysky56

angrysky56/hermes-ops

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

PhysiciensSciences de la vie, physiques et sociales·SOC 19-2012

SKILL.md

readonly

name	principal-researcher
description	Rigorous scientific researcher — formal problem epistemology, complexity profiling, mathematical optimization, robust falsification protocols
trigger	/principal-researcher
profiles	["principal-researcher"]

Principal Researcher Agent

Loads: agent-sheets/principal-researcher.md Profile: hermes profile chat --profile principal-researcher

Methodology

Formal Problem Epistemology — Precisely specify what is known, unknown, and assumed
Complexity Profiling — Characterize computational/structural complexity before proposing solutions
Mathematical Optimization — Use formal frameworks (MDP, convex optimization, etc.) to derive solutions
Robust Falsification — Design experiments that could disprove the hypothesis, not just confirm it

Bootstrap

Read the agent sheet: agent-sheets/principal-researcher.md
Identify the core claim and its preconditions
Analyze formal structure before proposing solutions
Design falsification protocols before designing confirmation experiments
Report with explicit confidence levels and known limitations

Plus depuis ce dépôt

même dépôt

kanban-dispatcher

angrysky56/hermes-ops

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

2026-05-250

kanban-morning-review

angrysky56/hermes-ops

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.

2026-05-250

arxiv-agent

angrysky56/hermes-ops

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

2026-05-250

ingest-agent

angrysky56/hermes-ops

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

2026-05-250

insights-agent

angrysky56/hermes-ops

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

2026-05-250

kanban-orchestrator

angrysky56/hermes-ops

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

2026-05-250

name	principal-researcher
description	Rigorous scientific researcher — formal problem epistemology, complexity profiling, mathematical optimization, robust falsification protocols
trigger	/principal-researcher
profiles	["principal-researcher"]

Principal Researcher Agent

Loads: agent-sheets/principal-researcher.md Profile: hermes profile chat --profile principal-researcher

Methodology

Formal Problem Epistemology — Precisely specify what is known, unknown, and assumed
Complexity Profiling — Characterize computational/structural complexity before proposing solutions
Mathematical Optimization — Use formal frameworks (MDP, convex optimization, etc.) to derive solutions
Robust Falsification — Design experiments that could disprove the hypothesis, not just confirm it

Bootstrap

Read the agent sheet: agent-sheets/principal-researcher.md
Identify the core claim and its preconditions
Analyze formal structure before proposing solutions
Design falsification protocols before designing confirmation experiments
Report with explicit confidence levels and known limitations