moonlight-lupin/agent-skills

A collection of AI agent skills for Hermes Agent — research, creative, productivity, devops, and more. Each skill is self-contained and tested.

57Stars on the repository
32Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

hermes-onboarding

01

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Use when onboarding a new customer — configure gateway, dashboard, memory, services for production.

not rated 57 +19 changed today B SkillSpector: warn 23 tokens original MIT

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Use when context window is filling up too fast or input token cost is too high. Audits overhead sources.

not rated 57 +19 yesterday A SkillSpector: warn 27 tokens original MIT

log-analyzer

03

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Parse agent log files to identify error patterns, rate limit hits, timeout clusters, tool failures, and component-level error counts. Produces a structured anomaly report. Cron-compatible — silent if no issues, alert digest if anomalies found. Also computes per-tool failure rates from a Hermes profile state.db…

not rated 57 +19 changed today A SkillSpector: pass 69 tokens original MIT

skill-maintainer

04

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Track upstream drift and sync adapted skill libraries.

not rated 57 +19 yesterday A SkillSpector: warn 12 tokens original MIT

clips-studio

05

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Use when the user wants to "make a video/clip", "generate a video from text", "animate this image/photo", "create a marketing reel / social video / teaser", "do a 3D / parallax move", "pan/zoom/orbit a shot", or mentions fal.ai, Kling, Veo or Seedance for video. Staged fal.ai workflow — brainstorm, draft cheaply…

not rated 57 +19 yesterday A SkillSpector: warn 146 tokens original MIT

image-studio

06

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Generate, edit and upscale AI images via fal.ai through a three-stage studio workflow — brainstorm a strong prompt with the user, prototype cheaply and iterate on feedback, then produce a finalised image. Use when the user wants image generation or editing through the local fal.ai helper workflow, including requests…

not rated 57 +19 yesterday A SkillSpector: warn 214 tokens original MIT

pexels-stock-photos

07

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Search and download free real-world stock photos from the Pexels API. Use when the user wants a REAL photo — "find a photo of X", "search for pictures of Y", "stock image of Z", "I need a photo for this slide/article/presentation". Searches the Pexels library (millions of photos) and downloads images in the chosen…

not rated 57 +19 yesterday A SkillSpector: warn 173 tokens original MIT

disk-cleanup

08

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Use when df says disk is above 80% full or the user wants to reclaim storage space on a VM.

not rated 57 +19 changed 2d ago C 27 tokens original MIT

model-compare

09

moonlight-lupin/agent-skills

Skill Codex

Blind side-by-side multi-model comparison. Send one prompt to 2-4 models simultaneously, present responses anonymously (Model A / B / C / D), let the user pick a winner, then reveal identities and show which model won. Supports custom evaluation criteria, synthesis of responses, and vote history logging. Trigger when…

not rated 57 +19 yesterday C 145 tokens original MIT

skill-retrieval

10

moonlight-lupin/agent-skills

Skill Claude Code

BM25-based skill retrieval plugin for Hermes Agent. Replaces the full skill list in the system prompt with a names-only compact view (2K tokens) and injects top-K relevant skill descriptions per turn via BM25 retrieval (300 tokens). Saves 9K tokens/turn. Use when system prompt token overhead from skills is a concern…

not rated 57 +19 changed today A SkillSpector: pass 81 tokens original MIT

decision-log

11

moonlight-lupin/agent-skills

Skill Claude CodeCodex needs its repo

ADR-style decision journal for agents and teams. Create numbered decision records, track superseding chains, schedule periodic reviews, and search past decisions to avoid re-litigating settled questions.

not rated 57 +19 yesterday A SkillSpector: warn 39 tokens original MIT

document-converter

12

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Convert between document formats: Markdown↔HTML, CSV↔JSON, YAML↔TOML, JSON↔YAML, CSV↔Markdown table, HTML→plain text, JSON→CSV (flattening nested objects), Excel→CSV, Markdown→PDF. Requires pandoc for PDF and openpyxl for Excel.

not rated 57 +19 yesterday A SkillSpector: pass 72 tokens original MIT

file-organizer

13

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Use when the user wants to organize, tidy, or restructure a messy directory (Downloads, Desktop, documents folder). LLM-powered file organizer that scans content, proposes a structure, and executes moves in chunks with a mandatory user confirmation gate.

not rated 57 +19 changed today A SkillSpector: pass 52 tokens original MIT

fill-template

14

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Bulk-fill ONE master template — a Word (.docx) letter/form or an Excel (.xlsx) form — from a data table, producing one filled file per row (mail-merge). Use whenever the user wants to "fill in this letter for each person", "mail merge", "generate letters for this list", "run this template over a spreadsheet", or hands…

not rated 57 +19 yesterday A SkillSpector: pass 215 tokens original MIT

scheduled-summary

15

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Cron-driven cross-session digest. Aggregates session activity, cron job outputs, memory changes, and tool usage stats into a compact summary for delivery via messaging platforms. Surfaces outstanding tasks and cross-session context that's invisible on chat platforms.

not rated 57 +19 yesterday A SkillSpector: pass 49 tokens original MIT

task-brief

16

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Compile a task brief BEFORE starting substantial work — pin down the goal (what "done" looks like), the context (everything known that bears on the task), the constraints (guardrails, with the organisation's standing rules included automatically) and the tooling (which installed skill or tool will do the work) …

not rated 57 +19 yesterday A SkillSpector: warn 209 tokens original MIT

travel-itinerary

17

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Create, update, sanitize, route, and export structured business-trip itineraries from booking confirmations, emails, tickets, PDFs, screenshots, calendar invites, or notes. Use for day-by-day itinerary generation, privacy-safe sharing, route links, and Markdown/PDF/DOCX/Google Doc/ICS exports.

not rated 57 +19 yesterday A SkillSpector: pass 66 tokens original MIT

deep-research

18

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Autonomous multi-step deep research engine implementing an iterative Think → Search → Extract → Synthesize → Stop loop. The LLM drives every decision: what to search, what's relevant, what's missing, and when to stop. Produces a cited, magazine-quality report with inline citations, category- specific formatting, and…

not rated 57 +19 yesterday A SkillSpector: pass 147 tokens original MIT

endpoint-probe

19

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Use when you need to discover an API's surface — poke a base URL to find its type (REST, GraphQL, SOAP, JSON-RPC), auth scheme, available endpoints, rate limits, and CORS policy. Also probes MCP servers (HTTP and stdio) to discover tools, resources, and prompts with full input schemas. Runs a Python probe script that…

not rated 57 +19 yesterday C 159 tokens original MIT

entity-research

20

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Deep background research on an entity — a company OR a person — into a cited dossier: identity & background, ownership & key management, adverse / negative media, public sanctions-list name-match signals, PEP indications from public research, and litigation / regulatory history. Use when the user says "research this…

not rated 57 +19 yesterday A SkillSpector: pass 190 tokens original MIT

fact-checker

21

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Targeted claim verification pipeline. Given a factual assertion, search multiple independent sources, cross-check for agreement or contradiction, rate confidence (verified / likely true / disputed / unverified / outdated), and produce a cited verification report.

not rated 57 +19 yesterday A SkillSpector: pass 49 tokens original MIT

library-rag

22

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Semantic search over a personal library using Nemotron-3-Embed-1B embeddings + sqlite-vec. Index books, documents, any text corpus; query by meaning. Includes EPUB→Markdown conversion and MCP server for auto-available search tools.

not rated 57 +19 yesterday A SkillSpector: warn 54 tokens original MIT

media-analyzer

23

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Technique-focused media analysis. Detects rhetorical tools (loaded language, cherry-picking, source selection bias, framing, omission, emotional appeals, false balance) in articles and produces a structured analysis report. Identifies specific techniques and bias-signal intensity without labeling political positions.

not rated 57 +19 yesterday A SkillSpector: pass 58 tokens original MIT

news-monitoring

24

moonlight-lupin/agent-skills

Skill Claude CodeCodex

Recurring topic/news monitoring with web search, multi-language sources, digest formatting, and automated delivery via Hermes cron jobs. Covers search strategy, source selection, Chinese-language platforms, and digest templates.

not rated 57 +19 yesterday A SkillSpector: warn 42 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: