magnus919/agent-skills

Curated collection of AI agent skills for Hermes and other agent frameworks

This repository also configures its own agents. See what agent-skills tells them →

76Stars on the repository
174Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

litellm

73

magnus919/agent-skills

Skill Claude CodeCodex

Operate, configure, secure, and troubleshoot the LiteLLM AI gateway (proxy) and Python SDK: run the proxy (litellm --config), route to 100+ providers through one OpenAI-compatible API, configure model lists and routing/reliability, virtual keys, teams, budgets, rate limits, caching, guardrails, observability, and…

not rated 76 +6 yesterday A SkillSpector: warn 173 tokens original MIT

llama-cpp

74

magnus919/agent-skills

Skill Claude CodeCodex

Operate, configure, benchmark, and troubleshoot llama.cpp across CPU, Metal, CUDA, HIP/ROCm, Vulkan, SYCL, and hybrid or multi-GPU systems. Use when installing or building llama.cpp, selecting or inspecting GGUF models, running llama-cli, serving an OpenAI-compatible API with llama-server, tuning memory and…

not rated 76 +6 yesterday A SkillSpector: warn 122 tokens original MIT

llamaindex

75

magnus919/agent-skills

Skill Claude CodeCodex

Build LLM applications with the LlamaIndex framework. Use when working with LlamaIndex or comparing RAG and agent orchestration frameworks. Do not use this skill for unrelated requests; route to the nearest named specialist.

not rated 76 +6 yesterday A SkillSpector: pass 48 tokens original MIT

mermaid-diagrams

76

magnus919/agent-skills

Skill Claude CodeCodex

Author, render, troubleshoot, and review Mermaid diagrams for documentation, architecture, processes, and technical communication. Use when a versionable diagram must communicate a defined audience job across a real renderer, including narrative, hierarchy, labels, legends, accessibility fallback, and uncertainty. Do…

not rated 76 +6 yesterday A SkillSpector: warn 77 tokens original MIT

magnus919/agent-skills

Skill Claude CodeCodex

Capture MeshCore Companion packets via BLE, serial, or TCP. Do not use this skill for unrelated requests; route to the nearest named specialist.

not rated 76 +6 yesterday B SkillSpector: warn 36 tokens original MIT

magnus919/agent-skills

Skill Claude CodeCodex

Plan and execute safe cross-system migrations, including service extraction from monoliths. Use when moving data, schemas, interfaces, infrastructure, or service ownership through compatibility windows, dual-running, reconciliation, cutover, recovery, or deprecation. Do not use for deciding whether decomposition is…

not rated 76 +6 yesterday A SkillSpector: pass 83 tokens original MIT

ml-engineering

79

magnus919/agent-skills

Skill Claude CodeCodex

Plan and execute production ML engineering work — model training and fine-tuning (LoRA/QLoRA), evaluation and eval-set design, quantization decisions, inference deployment, and regression triage, grounded in practical engineering patterns for production ML systems. Do not use for statistical modeling and experimental…

not rated 76 +6 yesterday A SkillSpector: pass 91 tokens original MIT

mobile-development

80

magnus919/agent-skills

Skill Claude CodeCodex

Build, test, sign, and ship mobile apps across iOS, Android, Flutter, and React Native — project scaffolding, builds and code signing, device and emulator testing, store submission (App Store and Play Store), app lifecycle and backgrounding, offline and sync, and mobile-specific testing. Use when the task involves…

not rated 76 +6 yesterday A SkillSpector: warn 144 tokens original MIT

magnus919/agent-skills

Skill Claude CodeCodex

Design and review end-to-end multi-tenant SaaS architectures: tenant and subscription semantics, control and application planes, pooled or isolated tenancy, onboarding, entitlements, metering, billing handoffs, lifecycle, partitioning, and tenant-aware operations. Use when a subscription product needs a coherent…

not rated 76 +6 yesterday A SkillSpector: pass 121 tokens original MIT

neckbeard

82

magnus919/agent-skills

Skill Claude CodeCodex

Use when asked to fix, build, refactor, review, verify, or release software and the work is non-trivial — including delivering a change request through planning, gates, implementation, review, verified PR, and authorized release; continuing work started elsewhere with no packet via evidence-based position assessment…

not rated 76 +6 yesterday A SkillSpector: pass 184 tokens original MIT

notion

83

magnus919/agent-skills

Skill Claude CodeCodex

Operate Notion from a terminal or agent: retrieve pages, query databases, search pages and databases, and update page properties — with a bundled notion-cli script that is read-only by default and gates every create or update behind a --dry-run/--yes confirmation. Use when an agent needs to read Notion content, answer…

not rated 76 +6 yesterday A SkillSpector: pass 119 tokens original MIT

nous-branding

84

magnus919/agent-skills

Skill Claude CodeCodex

Generate images and content consistent with the Nous Research brand identity. Use when creating visuals in the Nous / Theia / Hermes ecosystem: a "cyber-classical" style blending neo-classical statuary, cyberpunk/industrial grunge, and retro anime illustration. Covers official brand color palette, typography…

not rated 76 +6 yesterday A SkillSpector: pass 130 tokens original MIT

magnus919/agent-skills

Skill Claude CodeCodex

Define knowledge bundles with Google's Open Knowledge Format (OKF) v0.1. Use when the user mentions OKF, Open Knowledge Format, Google's knowledge format, LLM wiki bundles, agent knowledge packs, creating OKF bundles, validating OKF documents, or converting knowledge into the OKF standard. Do not use this skill for…

not rated 76 +6 yesterday A SkillSpector: pass 82 tokens original MIT

openlibrary

86

magnus919/agent-skills

Skill Claude CodeCodex

Query the Open Library catalog from the terminal: search books and authors, look up works, editions, and ISBNs, enumerate every edition of a work, read community ratings, and resolve cover-image URLs. Fully keyless public API. Includes the OL…M/W/A key-graph reference, ISBN 302-redirect resolution, search query…

not rated 76 +6 yesterday A SkillSpector: pass 113 tokens original MIT

magnus919/agent-skills

Skill Claude CodeCodex

Make good open source contributions — check CONTRIBUTING.md first, follow project norms, be a good citizen. Covers bug reports, feature requests, and pull requests with a defensible default posture when the project hasn't documented expectations. Do not use this skill for unrelated requests; route to the nearest named…

not rated 76 +6 yesterday A 64 tokens copy · 91% MIT

operational-design

88

magnus919/agent-skills

Skill Claude CodeCodex

Design and improve operational processes, controls, metrics, vendors, and scaling models through bounded pilots and evidence. Do not use for engineering delivery, financial modeling, technology evaluation, or legal advice. design, operational metrics, compliance and audit, vendor management, and team topology. Covers…

not rated 76 +6 yesterday A 141 tokens copy · 89% MIT

org-design

89

magnus919/agent-skills

Skill Claude CodeCodex

Design organizational topology, talent, rewards, culture, and health decisions with explicit decision rights and validation. Do not use for legal advice, project delivery planning, financial modeling, or technology implementation. reporting structures), talent strategy (make-vs-buy, skill taxonomies, succession…

not rated 76 +6 yesterday A 108 tokens copy · 89% MIT

pace-plan

90

magnus919/agent-skills

Skill Claude CodeCodex

Build, coordinate, operate, troubleshoot, exercise, and improve an authorized Primary, Alternate, Contingency, and Emergency communications plan. Use for resilient emergency-communications paths and their ownership, triggers, check-ins, tests, and corrective actions. Do not use for generic incident status messaging…

not rated 76 +6 yesterday A SkillSpector: warn 75 tokens original MIT

peertube

91

magnus919/agent-skills

Skill Claude CodeCodex

Browse PeerTube federated video from the terminal — instance stats, latest videos, video detail, comment threads, channels, accounts, instance-local search, and OAuth2 login with per-instance token persistence. Set PEERTUBESERVER to any instance; point it at sepiasearch.org for fediverse-wide search. Use when the user…

not rated 76 +6 yesterday A SkillSpector: pass 115 tokens original MIT

magnus919/agent-skills

Skill Claude CodeCodex

Use this skill when building or operating internal developer platforms: infrastructure as code, CI/CD, container orchestration, service networking, secrets, and observability. Do not use it to define release process, promotion, rollout, or rollback policy; use release-engineering for that delivery model.

not rated 76 +6 yesterday A SkillSpector: pass 61 tokens original MIT

playwright

93

magnus919/agent-skills

Skill Claude CodeCodex

Operate Playwright for browser automation end to end: author and debug E2E test suites (robust locators, network interception and mocking, parallel workers, accessibility snapshot checks), wire them into CI, and drive headless browsing and scraping with an extract -> validate -> save loop. Use when writing, running…

not rated 76 +6 yesterday C 148 tokens original MIT

postgres

94

magnus919/agent-skills

Skill Claude CodeCodex

Operate PostgreSQL instances safely: configuration review, index and query-plan analysis, vacuum and bloat management, WAL archiving and point-in-time recovery, replication and failover, extensions, major-version upgrades, and evidence-based diagnostics with the bundled read-only pgdiag script. Use when running or…

not rated 76 +6 yesterday A SkillSpector: warn 107 tokens original MIT

privacy-engineering

95

magnus919/agent-skills

Skill Claude CodeCodex

Translate privacy principles and legal requirements into data-flow, lifecycle, acceptance, and verification artifacts. Map data classification, purpose, processing, access, retention, deletion, residency, and consent; define verifiable privacy acceptance criteria; and produce data-lifecycle records, retention/deletion…

not rated 76 +6 yesterday A SkillSpector: pass 98 tokens original MIT

product-adoption

96

magnus919/agent-skills

Skill Claude CodeCodex

Diagnose and design product adoption for onboarding, activation, behavior change, feature discovery, rollout, and sustained use after launch. Covers consumer, B2B, internal-tool, and public-service contexts with evidence-based decision points and cohort segmentation. Does not own acquisition campaigns or marketing…

not rated 76 +6 yesterday A SkillSpector: pass 114 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: