Before designing any cross-agent feature, protocol, or workflow: trace the receiving agent's end-to-end connectivity, auth, consumption, and permission path. This skill prevents the most expensive mistake in multi-agent systems โ assuming that because Messageโฆ
Skills in this repository
lukemcqueen/hermes-cortex - Page 3
SkillsMP has collected 311 skills from lukemcqueen/hermes-cortex. Open a skill to review its source and details.
lukemcqueen/hermes-cortexShowing 40 of 311 collected skills.
When you discover an issue mid-task, the correct response is begin_change โ not a question. Covers the litmus test, the failure pattern, and the concrete "never ask" guardrail. Triggers: 'should I fix', 'want me to', discovered anything wrong mid-task, userโฆ
Recurring governance introspection โ scrape brain sync snapshots for codepath patterns, compile weekly insights, and store verdicts in dream.json for retrospection. Runs as a sentinel after mycortex-update-sync, before daily police logs.
Maintain an installed Hermes Cortex instance โ update both the upstream Hermes Agent and the cortex repo layer, merge diverged histories, sync skills safely, and troubleshoot common issues. Covers the dual-update workflow (hermes update + cortex-update.sh),โฆ
Server migration, disaster recovery, and restoration workflows for Hermes Agent โ restoring from tar.gz archives, reconstructing from backup directories, and verifying all subsystems post-move.
TDD cycle scoring, self-improvement, and governance system for Hermes Cortex. Scores completeness/quality/progress per cycle with nomic embeddings, logs to SQLite, collects user feedback via CLI, auto-applies config patches with safety bounds, and integratesโฆ
Use for mycortex knowledge brain work or mycortex migration.
Postgres schemas with RLS, roles, or migrations.
psql from scripts โ error propagation, docker wrappers.
Systematic repo health review โ survey scripts, detect duplicates, check naming, find gaps, prune dead weight, and produce a structured report. Run before major refactors or when asked to audit the repo.
Handle false positives from the auto-remediation sensor pipeline. Covers the trace-before-create workflow for sensor-reported missing scripts and distinguishing stale sensor entries from genuine issues.
Comprehensive security audit and hardening for Linux servers running web services (nginx, Docker, fail2ban, UFW). Five-layer methodology: network inventory โ service config review โ firewall/iptables audit โ fail2ban/DDoS protection โ OS sysctl hardening โโฆ
After the weekly opportunity scan identifies issues, run auto-fix patterns โ git pull, branch cleanup, Docker restart, permission fixes, disk cleanup โ then verify each fix succeeded. Reduces manual intervention for known recurring problems.
Install, configure, and manage Ollama on Linux โ including sudo-free tarball install, user systemd service, model management, and health verification.
Auto-save a bug-fix lesson after resolving any non-trivial error. Builds a personal bug-fix memory that makes the agent smarter over time. Trigger: after fixing a bug, after resolving an error, after debugging. Run: offline_knowledge lesson create --titleโฆ
Daily bible reading cron pattern โ generates SOUL.md entries and brain pages for agent-wide scripture engagement.
Cron timestamps follow HERMES_TIMEZONE env, never hardcoded.
Know which files are yours to modify vs Hermes defaults. Covers the two-domain split (Hermes Agent vs hermes-cortex repo), what each domain owns, and how to check before editing.
Workflow router skill โ classifies the incoming request into one of 12 patterns and dispatches to the correct tooling, output format, and checklist.
Create, name, list, and maintain Hermes cron jobs โ no_agent watchdog scripts, naming conventions, and the user's preferred listing format.
Slim docs to byte targets (SOUL 10K, AGENTS gates) safely.
Use when a cron delivery is flagged or looks wrong.
Safe operational practices for Docker-based staging servers โ volume management, change verification, and database recovery patterns.
Read cron job definitions and execution history from filesystem when cronjob CLI is unavailable. Platform-agnostic fallback for cron mode, restricted approval, or limited shell contexts.
Query bus queues and archives reliably for fleet results.
Schedule LLM crons around provider peak/off-peak windows.
Cron tick budget kill: detached worker + result sweep.
Probe MCP server health; extend the governance watchdog.
Use when a command is flagged as a security issue.
Automated Agent Bus processing via MCP.
MCP inbox tools for cortex-bus messaging.
Build, test, and debug MCP servers for Hermes Agent โ logging, dependency checks, fix hints, and best practices.
Fix adversarial-verify.py findings with real handling.
Yuanbao (ๅ ๅฎ) groups: @mention users, query info/members.
Bus queue lifecycle โ inspecting stuck messages, archiving orphaned messages, navigating state constraints, and performing routine queue cleanup. Complements cortex-bus for the hands-on maintenance side.
Systematic system health survey run proactively when the user gives an open-ended directive to "find work" or "look for issues". 9-step sequential scan: inbox โ memory โ doctor โ crons โ git โ system โ analyze โ fix โ verify.
Multi-audience documentation scoping conventions for Hermes Cortex. Defines when and how to distinguish general (universal) content from deployment- specific content using scope banners and section tags. Keeps the public OSS repo usable by everyone whileโฆ
Tune and configure PostgreSQL running inside Docker containers โ custom configs, mounts, command overrides, and the listen_addresses pitfall.
Canonical repo organization for Hermes Cortex โ structure, naming, consolidation, symlinks, and audit procedures.
Deploy a custom web app (Flask, Python, Node) behind nginx โ upstream config, SSL, basic auth, rate limiting, launchd/systemd service, and multi-layer testing pattern.