ouyangbo/hermes-agent
1
0
Fork 0
Code Issues Pull Requests Actions 9 Packages Projects Releases Wiki Activity

chore(skills): standards sweep — bring 42 bundled/optional skills up to hardline

Browse Source 
Audited all 191 in-repo skills (77 bundled, 114 optional) against the
authoring standards (AGENTS.md hardline + PR #80800). Fixed 42:

- 8 overlong descriptions rewritten to <= 60 chars, one sentence, period
  (one-three-one-rule 525ch, drug-discovery 405ch, web-pentest 358ch,
  fitness-nutrition 352ch, neuroskill-bci 332ch, oss-forensics 320ch,
  computer-use 307ch, memento-flashcards 252ch)
- 24 skills with missing frontmatter fields: author (credited from git
  history: f-trycua, SHL0MS, teyrebaz33, haileymarshall, FurkanL0,
  teknium1), license, version, platforms, tags
- 7 machine-local paths scrubbed (/home/bb, /home/user, /home/ubuntu ->
  portable placeholders)
- 11 marketing-word intros reworded (Comprehensive/state-of-the-art)
- docs catalogs + per-skill pages regenerated, scope-disciplined

Deferred (not in this PR):
- 14 frontmatter/dir name mismatches — open PR #42788 already proposes
  the dir-rename approach for 4 of them; resolve there as one class
- 2 skills over 100k chars (pytorch-fsdp 159k, research-paper-writing
  103k) — need content splits into references/, separate PRs
- comfyui dangling related_skill resolves after the name-mismatch class
This commit is contained in:
teknium1
2026-08-08 14:28:17 -07:00
committed by Teknium
parent fe42097865
commit 1c9433897c
87 changed files with 444 additions and 154 deletions
Download Patch File Download Diff File Expand all files Collapse all files
optional-skills/communication/one-three-one-rule/SKILL.md
+1 -8
View File
@@ -1,13 +1,6 @@
---
name: one-three-one-rule
description: >
Structured decision-making framework for technical proposals and trade-off analysis.
When the user faces a choice between multiple approaches (architecture decisions,
tool selection, refactoring strategies, migration paths), this skill produces a
1-3-1 format: one clear problem statement, three distinct options with pros/cons,
and one concrete recommendation with definition of done and implementation plan.
Use when the user asks for a "1-3-1", says "give me options", or needs help
choosing between competing approaches.
description: "1-3-1 decision briefs: problem, three options, one pick."
platforms: [linux, macos, windows]
version: 1.0.0
author: Willard Moore
optional-skills/creative/audiocraft-audio-generation/SKILL.md
+1 -1
View File
@@ -15,7 +15,7 @@ metadata:
# AudioCraft: Audio Generation
Comprehensive guide to using Meta's AudioCraft for text-to-music and text-to-audio generation with MusicGen, AudioGen, and EnCodec.
Guide to using Meta's AudioCraft for text-to-music and text-to-audio generation with MusicGen, AudioGen, and EnCodec.
## When to use AudioCraft
optional-skills/creative/blender-mcp/SKILL.md
+1
View File
@@ -4,6 +4,7 @@ description: Drive Blender via the catalog blender MCP, with bpy recipes.
version: 2.1.0
requires: Blender 3.0+ desktop instance (headless via xvfb-run)
author: alireza78a + kshitijk4poor + Hermes Agent
license: MIT
tags: [blender, 3d, animation, modeling, bpy, mcp]
platforms: [linux, macos, windows]
---
optional-skills/creative/heartmula/SKILL.md
+2
View File
@@ -2,6 +2,8 @@
name: heartmula
description: "HeartMuLa: Suno-like song generation from lyrics + tags."
version: 1.0.0
author: Teknium (teknium1), Hermes Agent
license: MIT
platforms: [linux, macos, windows]
metadata:
hermes:
optional-skills/devops/actual-setup/SKILL.md
+1
View File
@@ -4,6 +4,7 @@ description: Set up Actual Computer (actual.inc) inference in Hermes.
version: 2.0.0
author: shl0ms + Hermes Agent
license: MIT
platforms: [linux, macos, windows]
metadata:
hermes:
tags: [actual, actual-inc, provider, local-inference, relay, gguf, setup]
optional-skills/email/agentmail/SKILL.md
+2
View File
@@ -2,6 +2,8 @@
name: agentmail
description: "Give the agent its own inbox: send and receive email."
version: 1.0.0
author: teyrebaz33, Hermes Agent
license: MIT
platforms: [linux, macos, windows]
metadata:
hermes:
optional-skills/finance/polymarket/SKILL.md
+1
View File
@@ -3,6 +3,7 @@ name: polymarket
description: "Query Polymarket: markets, prices, orderbooks, history."
version: 1.0.0
author: Hermes Agent + Teknium
license: MIT
tags: [polymarket, prediction-markets, market-data, trading]
platforms: [linux, macos, windows]
---
optional-skills/gaming/minecraft-modpack-server/SKILL.md
+3
View File
@@ -1,6 +1,9 @@
---
name: minecraft-modpack-server
description: "Host modded Minecraft servers (CurseForge, Modrinth)."
version: 1.0.0
author: Teknium (teknium1), Hermes Agent
license: MIT
tags: [minecraft, gaming, server, neoforge, forge, modpack]
platforms: [linux, macos]
---
optional-skills/gaming/pokemon-player/SKILL.md
+3
View File
@@ -1,6 +1,9 @@
---
name: pokemon-player
description: "Play Pokemon via headless emulator + RAM reads."
version: 1.0.0
author: Teknium (teknium1), Hermes Agent
license: MIT
tags: [gaming, pokemon, emulator, pyboy, gameplay, gameboy]
platforms: [linux, macos, windows]
---
optional-skills/health/fitness-nutrition/SKILL.md
+2 -6
View File
@@ -1,13 +1,9 @@
---
name: fitness-nutrition
description: >
Gym workout planner and nutrition tracker. Search 690+ exercises by muscle,
equipment, or category via wger. Look up macros and calories for 380,000+
foods via USDA FoodData Central. Compute BMI, TDEE, one-rep max, macro
splits, and body fat — pure Python, no pip installs. Built for anyone
chasing gains, cutting weight, or just trying to eat better.
description: "Workout planning, macros, and body metrics via wger/USDA."
platforms: [linux, macos, windows]
version: 1.0.0
author: Hailey Marshall (haileymarshall), Hermes Agent
authors:
- haileymarshall
license: MIT
optional-skills/health/neuroskill-bci/SKILL.md
+1 -6
View File
@@ -1,11 +1,6 @@
---
name: neuroskill-bci
description: >
Connect to a running NeuroSkill instance and incorporate the user's real-time
cognitive and emotional state (focus, relaxation, mood, cognitive load, drowsiness,
heart rate, HRV, sleep staging, and 40+ derived EXG scores) into responses.
Requires a BCI wearable (Muse 2/S or OpenBCI) and the NeuroSkill desktop app
running locally.
description: "Use live BCI cognitive and mood state from NeuroSkill."
platforms: [linux, macos, windows]
version: 1.0.0
author: Hermes Agent + Nous Research
optional-skills/mlops/lambda-labs/SKILL.md
+2 -2
View File
@@ -14,7 +14,7 @@ metadata:
# Lambda Labs GPU Cloud
Comprehensive guide to running ML workloads on Lambda Labs GPU cloud with on-demand instances and 1-Click Clusters.
Guide to running ML workloads on Lambda Labs GPU cloud with on-demand instances and 1-Click Clusters.
## When to use Lambda Labs
@@ -286,7 +286,7 @@ Filesystems must be attached at instance launch time:
└── outputs/
# Local SSD (faster, ephemeral)
/home/ubuntu/
~/ (instance home)
└── working/ # Temporary files
```
optional-skills/mlops/modal/SKILL.md
+1 -1
View File
@@ -14,7 +14,7 @@ metadata:
# Modal Serverless GPU
Comprehensive guide to running ML workloads on Modal's serverless GPU cloud platform.
Guide to running ML workloads on Modal's serverless GPU cloud platform.
## When to use Modal
optional-skills/mlops/models/segment-anything-model/SKILL.md
+1 -1
View File
@@ -14,7 +14,7 @@ metadata:
# Segment Anything Model (SAM)
Comprehensive guide to using Meta AI's Segment Anything Model for zero-shot image segmentation.
Guide to using Meta AI's Segment Anything Model for zero-shot image segmentation.
## When to use SAM
optional-skills/mlops/pytorch-fsdp/SKILL.md
+1 -1
View File
@@ -14,7 +14,7 @@ metadata:
# Pytorch-Fsdp Skill
Comprehensive assistance with pytorch-fsdp development, generated from official documentation.
Assistance with pytorch-fsdp development, generated from official documentation.
## When to Use This Skill
optional-skills/mlops/stable-diffusion/SKILL.md
+1 -1
View File
@@ -14,7 +14,7 @@ metadata:
# Stable Diffusion Image Generation
Comprehensive guide to generating images with Stable Diffusion using the HuggingFace Diffusers library.
Guide to generating images with Stable Diffusion using the HuggingFace Diffusers library.
## When to use Stable Diffusion
optional-skills/mlops/tensorrt-llm/SKILL.md
+1 -1
View File
@@ -14,7 +14,7 @@ metadata:
# TensorRT-LLM
NVIDIA's open-source library for optimizing LLM inference with state-of-the-art performance on NVIDIA GPUs.
NVIDIA's open-source library for optimizing LLM inference with high performance on NVIDIA GPUs.
## When to use TensorRT-LLM
optional-skills/mlops/training/axolotl/SKILL.md
+1 -1
View File
@@ -18,7 +18,7 @@ metadata:
Expert guidance for fine-tuning LLMs with Axolotl — YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support.
Comprehensive assistance with axolotl development, generated from official documentation.
Assistance with axolotl development, generated from official documentation.
## When to Use This Skill
optional-skills/mlops/training/unsloth/SKILL.md
+2 -2
View File
@@ -14,7 +14,7 @@ metadata:
# Unsloth Skill
Comprehensive assistance with unsloth development, generated from official documentation.
Assistance with unsloth development, generated from official documentation.
## When to Use This Skill
@@ -33,7 +33,7 @@ This skill should be triggered when:
## Reference Files
This skill includes comprehensive documentation in `references/`:
This skill includes full documentation in `references/`:
- **llms-txt.md** - Llms-Txt documentation
optional-skills/productivity/memento-flashcards/SKILL.md
+1 -5
View File
@@ -1,10 +1,6 @@
---
name: memento-flashcards
description: >-
Spaced-repetition flashcard system. Create cards from facts or text,
chat with flashcards using free-text answers graded by the agent,
generate quizzes from YouTube transcripts, review due cards with
adaptive scheduling, and export/import decks as CSV.
description: "Spaced-repetition flashcards: create, review, quiz, export."
version: 1.0.0
author: Memento AI
license: MIT
optional-skills/research/bioinformatics/SKILL.md
+2
View File
@@ -2,6 +2,8 @@
name: bioinformatics
description: Gateway to 400+ genomics and computational biology skills.
version: 1.0.0
author: Teknium (teknium1), Hermes Agent
license: MIT
platforms: [linux, macos]
metadata:
hermes:
optional-skills/research/domain-intel/SKILL.md
+7
View File
@@ -1,7 +1,14 @@
---
name: domain-intel
description: Passive recon of subdomains, SSL certs, WHOIS, and DNS.
version: 1.0.0
author: FurkanL0, Hermes Agent
license: MIT
platforms: [linux, macos, windows]
metadata:
hermes:
tags: [Domains, OSINT, DNS, Research]
related_skills: []
---
# Domain Intelligence — Passive OSINT
optional-skills/research/drug-discovery/SKILL.md
+1 -7
View File
@@ -1,12 +1,6 @@
---
name: drug-discovery
description: >
Pharmaceutical research assistant for drug discovery workflows. Search
bioactive compounds on ChEMBL, calculate drug-likeness (Lipinski Ro5, QED,
TPSA, synthetic accessibility), look up drug-drug interactions via
OpenFDA, interpret ADMET profiles, and assist with lead optimization.
Use for medicinal chemistry questions, molecule property analysis, clinical
pharmacology, and open-science drug research.
description: "Drug discovery: ChEMBL search, drug-likeness, interactions."
platforms: [linux, macos, windows]
version: 1.0.0
author: bennytimz
optional-skills/research/osint-investigation/SKILL.md
+1
View File
@@ -4,6 +4,7 @@ description: Follow the money via public records and sanctions data.
version: 0.1.0
platforms: [linux, macos, windows]
author: Hermes Agent (adapted from ShinMegamiBoson/OpenPlanter, MIT)
license: MIT
metadata:
hermes:
tags: [osint, investigation, public-records, sec, sanctions, corporate-registry, property, courts, due-diligence, journalism]
optional-skills/security/oss-forensics/SKILL.md
+8 -5
View File
@@ -1,10 +1,9 @@
---
name: oss-forensics
description: |
Supply chain investigation, evidence recovery, and forensic analysis for GitHub repositories.
Covers deleted commit recovery, force-push detection, IOC extraction, multi-source evidence
collection, hypothesis formation/validation, and structured forensic reporting.
Inspired by RAPTOR's 1800+ line OSS Forensics system.
description: "GitHub supply-chain forensics: recovery, IOCs, reporting."
version: 1.0.0
author: Teknium (teknium1), Hermes Agent
license: MIT
platforms: [linux, macos, windows]
category: security
triggers:
@@ -23,6 +22,10 @@ toolsets:
- web
- file
- delegation
metadata:
hermes:
tags: [Security, Forensics, GitHub, Supply-Chain]
related_skills: []
---
# OSS Security Forensics Skill
optional-skills/security/web-pentest/SKILL.md
+8 -6
View File
@@ -1,11 +1,9 @@
---
name: web-pentest
description: |
Authorized web application penetration testing — reconnaissance, vulnerability
analysis, proof-based exploitation, and professional reporting. Adapts
Shannon's "No Exploit, No Report" methodology with hard guardrails for
scope, authorization, and aux-client leakage. Active testing against running
applications you own or have written authorization to test.
description: "Authorized web pentest: recon, proof-based exploits, report."
version: 1.0.0
author: Teknium (teknium1), Hermes Agent
license: MIT
platforms: [linux, macos]
category: security
triggers:
@@ -22,6 +20,10 @@ toolsets:
- browser
- file
- delegation
metadata:
hermes:
tags: [Security, Pentest, Web, Recon]
related_skills: []
---
# Web Application Penetration Testing
optional-skills/software-development/code-wiki/SKILL.md
+1 -1
View File
@@ -13,7 +13,7 @@ metadata:
# Code Wiki Skill
Generate a comprehensive wiki for any codebase — overview, architecture, per-module deep-dives, Mermaid class and sequence diagrams. Inspired by Google CodeWiki, but works on local repos, private repos, and any language. Uses only existing Hermes tools (`terminal`, `read_file`, `search_files`, `write_file`); no Docker, no external services, no extra dependencies.
Generate a full wiki for any codebase — overview, architecture, per-module deep-dives, Mermaid class and sequence diagrams. Inspired by Google CodeWiki, but works on local repos, private repos, and any language. Uses only existing Hermes tools (`terminal`, `read_file`, `search_files`, `write_file`); no Docker, no external services, no extra dependencies.
This skill produces **reference documentation** (what/how). It does not produce strategic narrative (why — that's a different skill).
optional-skills/software-development/rest-graphql-debug/SKILL.md
+1
View File
@@ -4,6 +4,7 @@ description: "Debug REST/GraphQL APIs: status codes, auth, schemas, repro."
version: 1.2.0
author: eren-karakus0
license: MIT
platforms: [linux, macos, windows]
metadata:
hermes:
tags: [api, rest, graphql, http, debugging, testing, curl, integration]
optional-skills/yuanbao/SKILL.md
+2
View File
@@ -2,6 +2,8 @@
name: yuanbao
description: "Yuanbao (元宝) groups: @mention users, query info/members."
version: 1.0.0
author: Teknium (teknium1), Hermes Agent
license: MIT
platforms: [linux, macos, windows]
metadata:
hermes: