mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-31 19:16:29 +00:00
fix(skills): sync bundled + misc CLI skills to current upstream
Nine bundled and optional skills had stale flags, install URLs, packages, and paths. Verified each against upstream and corrected: - vllm: removed bogus --enable-metrics/--metrics-port (metrics at /metrics on API port); --speculative-model -> --speculative-config; canonical HF model IDs - lm-evaluation-harness: --tasks list -> lm-eval ls tasks; --allow_code_execution -> --confirm_run_unsafe_code - weights-and-biases: wandb.keras import removed -> wandb.integration.keras (WandbMetricsLogger); log_uniform -> log_uniform_values for raw values - huggingface-hub: upload-large-folder now deprecated; hf papers list -> ls - openhue: Linux install 404 -> openhue_Linux_x86_64.tar.gz tarball (release repo openhue/openhue-cli, v0.24) - apple-notes: memo notes -a is a bare flag, no positional title - excalidraw: upload.py path skills/diagramming/... -> skills/creative/... - searxng-search: removed Method 3 (searxng-data pip package is a PyPI 404) - sketch: noted get-shit-done upstream is archived/unmaintained
This commit is contained in:
teknium1
Teknium
parent
cae5c81956
commit
55ef425d0c
9 changed files with 60 additions and 63 deletions
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: searxng-search
|
||||
description: Free keyless meta-search aggregating 70+ engines.
|
||||
version: 1.0.0
|
||||
version: 1.0.1
|
||||
author: hermes-agent
|
||||
license: MIT
|
||||
platforms: [linux, macos]
|
||||
|
|
@ -124,23 +124,6 @@ for r in data.get("results", []):
|
|||
print()
|
||||
```
|
||||
|
||||
## Method 3: searxng-data Python Package
|
||||
|
||||
For more structured access, install the `searxng-data` package:
|
||||
|
||||
```bash
|
||||
pip install searxng-data
|
||||
```
|
||||
|
||||
```python
|
||||
from searxng_data import engines
|
||||
|
||||
# List available engines
|
||||
print(engines.list_engines())
|
||||
```
|
||||
|
||||
Note: This package only provides engine metadata, not the search API itself.
|
||||
|
||||
## Self-Hosting SearXNG
|
||||
|
||||
To run your own SearXNG instance:
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: apple-notes
|
||||
description: "Manage Apple Notes via memo CLI: create, search, edit."
|
||||
version: 1.0.0
|
||||
version: 1.0.1
|
||||
author: Hermes Agent
|
||||
license: MIT
|
||||
platforms: [macos]
|
||||
|
|
@ -49,10 +49,14 @@ memo notes -s "query" # Search notes (fuzzy)
|
|||
### Create Notes
|
||||
|
||||
```bash
|
||||
memo notes -a # Interactive editor
|
||||
memo notes -a "Note Title" # Quick add with title
|
||||
memo notes -a # Add a note (opens your $EDITOR)
|
||||
memo notes -a -f "Folder Name" # Add a note into a specific folder
|
||||
```
|
||||
|
||||
`-a`/`--add` is a bare flag — it opens your `$EDITOR` to compose the note; it does
|
||||
not take a title argument. Use `-f/--folder` to target a folder. Set `$EDITOR`
|
||||
first (e.g. `export EDITOR=vim`).
|
||||
|
||||
### Edit Notes
|
||||
|
||||
```bash
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: excalidraw
|
||||
description: "Hand-drawn Excalidraw JSON diagrams (arch, flow, seq)."
|
||||
version: 1.0.0
|
||||
version: 1.0.1
|
||||
author: Hermes Agent
|
||||
license: MIT
|
||||
dependencies: []
|
||||
|
|
@ -51,7 +51,7 @@ Save to any path, e.g. `~/diagrams/my_diagram.excalidraw`.
|
|||
Run the upload script (located in this skill's `scripts/` directory) via terminal:
|
||||
|
||||
```bash
|
||||
python skills/diagramming/excalidraw/scripts/upload.py ~/diagrams/my_diagram.excalidraw
|
||||
python skills/creative/excalidraw/scripts/upload.py ~/diagrams/my_diagram.excalidraw
|
||||
```
|
||||
|
||||
This uploads to excalidraw.com (no account needed) and prints a shareable URL. Requires the `cryptography` pip package (`pip install cryptography`).
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: sketch
|
||||
description: "Throwaway HTML mockups: 2-3 design variants to compare."
|
||||
version: 1.0.0
|
||||
version: 1.0.1
|
||||
author: Hermes Agent (adapted from gsd-build/get-shit-done)
|
||||
license: MIT
|
||||
platforms: [linux, macos, windows]
|
||||
|
|
@ -26,7 +26,9 @@ Load this when the user says things like "sketch this screen", "show me what X c
|
|||
|
||||
## If the user has the full GSD system installed
|
||||
|
||||
If `gsd-sketch` shows up as a sibling skill (installed via `npx get-shit-done-cc --hermes`), prefer **`gsd-sketch`** for the full workflow: persistent `.planning/sketches/` with MANIFEST, frontier mode analysis, consistency audits across past sketches, and integration with the rest of GSD. This skill is the lightweight standalone version — one-off sketching without the state machinery.
|
||||
If `gsd-sketch` shows up as a sibling skill (installed via `npx get-shit-done-cc --hermes`), you can use **`gsd-sketch`** for the fuller workflow: persistent `.planning/sketches/` with MANIFEST, frontier mode analysis, consistency audits across past sketches, and integration with the rest of GSD. This skill is the lightweight standalone version — one-off sketching without the state machinery.
|
||||
|
||||
> **Note:** The upstream GSD project ([gsd-build/get-shit-done](https://github.com/gsd-build/get-shit-done)) is **archived / no longer maintained** on GitHub. The npm package (`get-shit-done-cc`) still installs, but treat it as an archived community project — this standalone `sketch` skill is the maintained path and needs nothing extra.
|
||||
|
||||
## Core method
|
||||
|
||||
|
|
@ -215,4 +217,4 @@ Repeat for each variant, then present the comparison table.
|
|||
|
||||
## Attribution
|
||||
|
||||
Adapted from the GSD (Get Shit Done) project's `/gsd-sketch` workflow — MIT © 2025 Lex Christopherson ([gsd-build/get-shit-done](https://github.com/gsd-build/get-shit-done)). The full GSD system ships persistent sketch state, theme/variant pattern references, and consistency-audit workflows; install with `npx get-shit-done-cc --hermes --global`.
|
||||
Adapted from the GSD (Get Shit Done) project's `/gsd-sketch` workflow — MIT © 2025 Lex Christopherson ([gsd-build/get-shit-done](https://github.com/gsd-build/get-shit-done)). The upstream GSD repo is now **archived/unmaintained** on GitHub; the `get-shit-done-cc` npm package still installs (`npx get-shit-done-cc --hermes --global`) and ships persistent sketch state, theme/variant pattern references, and consistency-audit workflows, but treat it as an archived community project.
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: evaluating-llms-harness
|
||||
description: "lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.)."
|
||||
version: 1.0.0
|
||||
version: 1.0.1
|
||||
author: Orchestra Research
|
||||
license: MIT
|
||||
dependencies: [lm-eval, transformers, vllm]
|
||||
|
|
@ -38,7 +38,7 @@ lm_eval --model hf \
|
|||
|
||||
**View available tasks**:
|
||||
```bash
|
||||
lm_eval --tasks list
|
||||
lm-eval ls tasks
|
||||
```
|
||||
|
||||
## Common workflows
|
||||
|
|
@ -451,19 +451,19 @@ Verify model and tokenizer match:
|
|||
|
||||
**Issue: HumanEval not executing code**
|
||||
|
||||
Install execution dependencies:
|
||||
```bash
|
||||
pip install human-eval
|
||||
```
|
||||
Code-executing tasks (HumanEval, MBPP, etc.) are gated behind an explicit
|
||||
confirmation flag — you must pass `--confirm_run_unsafe_code` to run them:
|
||||
|
||||
Enable code execution:
|
||||
```bash
|
||||
lm_eval --model hf \
|
||||
--model_args pretrained=model-name \
|
||||
--tasks humaneval \
|
||||
--allow_code_execution # Required for HumanEval
|
||||
--confirm_run_unsafe_code # Required to run tasks that execute generated code
|
||||
```
|
||||
|
||||
Without this flag lm-eval refuses to run the task rather than silently skipping
|
||||
code execution.
|
||||
|
||||
## Advanced topics
|
||||
|
||||
**Benchmark descriptions**: See [references/benchmark-guide.md](references/benchmark-guide.md) for detailed description of all 60+ tasks, what they measure, and interpretation.
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: weights-and-biases
|
||||
description: "W&B: log ML experiments, sweeps, model registry, dashboards."
|
||||
version: 1.0.0
|
||||
version: 1.0.1
|
||||
author: Orchestra Research
|
||||
license: MIT
|
||||
dependencies: [wandb]
|
||||
|
|
@ -238,7 +238,7 @@ sweep_config = {
|
|||
},
|
||||
'parameters': {
|
||||
'learning_rate': {
|
||||
'distribution': 'log_uniform',
|
||||
'distribution': 'log_uniform_values',
|
||||
'min': 1e-5,
|
||||
'max': 1e-1
|
||||
},
|
||||
|
|
@ -317,7 +317,7 @@ sweep_config = {
|
|||
'method': 'bayes',
|
||||
'metric': {'name': 'val/loss', 'goal': 'minimize'},
|
||||
'parameters': {
|
||||
'lr': {'distribution': 'log_uniform', 'min': 1e-5, 'max': 1e-1}
|
||||
'lr': {'distribution': 'log_uniform_values', 'min': 1e-5, 'max': 1e-1}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
|
@ -433,17 +433,21 @@ trainer.fit(model, datamodule=dm)
|
|||
|
||||
```python
|
||||
import wandb
|
||||
from wandb.keras import WandbCallback
|
||||
from wandb.integration.keras import WandbMetricsLogger, WandbModelCheckpoint
|
||||
|
||||
# Initialize
|
||||
wandb.init(project="keras-demo")
|
||||
|
||||
# Add callback
|
||||
# Add callbacks (the monolithic WandbCallback was removed;
|
||||
# use the dedicated callbacks from wandb.integration.keras instead)
|
||||
model.fit(
|
||||
x_train, y_train,
|
||||
validation_data=(x_val, y_val),
|
||||
epochs=10,
|
||||
callbacks=[WandbCallback()] # Auto-logs metrics
|
||||
callbacks=[
|
||||
WandbMetricsLogger(), # Auto-logs metrics
|
||||
WandbModelCheckpoint("models/model-{epoch}") # Saves checkpoints
|
||||
]
|
||||
)
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: huggingface-hub
|
||||
description: "HuggingFace hf CLI: search/download/upload models, datasets."
|
||||
version: 1.0.0
|
||||
version: 1.0.1
|
||||
author: Hugging Face
|
||||
license: MIT
|
||||
tags: [huggingface, hf, models, datasets, hub, mlops]
|
||||
|
|
@ -25,8 +25,8 @@ The `hf` command is the modern command-line interface for interacting with the H
|
|||
|
||||
### General Operations
|
||||
* `hf download REPO_ID`: Download files from the Hub.
|
||||
* `hf upload REPO_ID`: Upload files/folders (recommended for single-commit).
|
||||
* `hf upload-large-folder REPO_ID LOCAL_PATH`: Recommended for resumable uploads of large directories.
|
||||
* `hf upload REPO_ID`: Upload files/folders (recommended for single-commit; also handles resumable uploads of large directories).
|
||||
* `hf upload-large-folder REPO_ID LOCAL_PATH`: **[Deprecated]** — use `hf upload` instead.
|
||||
* `hf sync`: Sync files between a local directory and a bucket.
|
||||
* `hf env` / `hf version`: View environment and version details.
|
||||
|
||||
|
|
@ -50,7 +50,7 @@ The `hf` command is the modern command-line interface for interacting with the H
|
|||
* **Datasets:** `hf datasets list`, `info`, and `parquet` (list parquet URLs).
|
||||
* **SQL Queries:** `hf datasets sql SQL` — Execute raw SQL via DuckDB against dataset parquet URLs.
|
||||
* **Models:** `hf models list` and `info`.
|
||||
* **Papers:** `hf papers list` — View daily papers.
|
||||
* **Papers:** `hf papers ls` — View daily papers.
|
||||
|
||||
### Discussions & Pull Requests (`hf discussions`)
|
||||
* Manage the lifecycle of Hub contributions: `list`, `create`, `info`, `comment`, `close`, `reopen`, and `rename`.
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: serving-llms-vllm
|
||||
description: "vLLM: high-throughput LLM serving, OpenAI API, quantization."
|
||||
version: 1.0.0
|
||||
version: 1.0.1
|
||||
author: Orchestra Research
|
||||
license: MIT
|
||||
dependencies: [vllm, torch, transformers]
|
||||
|
|
@ -31,7 +31,7 @@ pip install vllm
|
|||
```python
|
||||
from vllm import LLM, SamplingParams
|
||||
|
||||
llm = LLM(model="meta-llama/Llama-3-8B-Instruct")
|
||||
llm = LLM(model="meta-llama/Meta-Llama-3-8B-Instruct")
|
||||
sampling = SamplingParams(temperature=0.7, max_tokens=256)
|
||||
|
||||
outputs = llm.generate(["Explain quantum computing"], sampling)
|
||||
|
|
@ -40,14 +40,14 @@ print(outputs[0].outputs[0].text)
|
|||
|
||||
**OpenAI-compatible server**:
|
||||
```bash
|
||||
vllm serve meta-llama/Llama-3-8B-Instruct
|
||||
vllm serve meta-llama/Meta-Llama-3-8B-Instruct
|
||||
|
||||
# Query with OpenAI SDK
|
||||
python -c "
|
||||
from openai import OpenAI
|
||||
client = OpenAI(base_url='http://localhost:8000/v1', api_key='EMPTY')
|
||||
print(client.chat.completions.create(
|
||||
model='meta-llama/Llama-3-8B-Instruct',
|
||||
model='meta-llama/Meta-Llama-3-8B-Instruct',
|
||||
messages=[{'role': 'user', 'content': 'Hello!'}]
|
||||
).choices[0].message.content)
|
||||
"
|
||||
|
|
@ -74,24 +74,23 @@ Choose configuration based on your model size:
|
|||
|
||||
```bash
|
||||
# For 7B-13B models on single GPU
|
||||
vllm serve meta-llama/Llama-3-8B-Instruct \
|
||||
vllm serve meta-llama/Meta-Llama-3-8B-Instruct \
|
||||
--gpu-memory-utilization 0.9 \
|
||||
--max-model-len 8192 \
|
||||
--port 8000
|
||||
|
||||
# For 30B-70B models with tensor parallelism
|
||||
vllm serve meta-llama/Llama-2-70b-hf \
|
||||
vllm serve meta-llama/Meta-Llama-3-70B-Instruct \
|
||||
--tensor-parallel-size 4 \
|
||||
--gpu-memory-utilization 0.9 \
|
||||
--quantization awq \
|
||||
--port 8000
|
||||
|
||||
# For production with caching and metrics
|
||||
vllm serve meta-llama/Llama-3-8B-Instruct \
|
||||
# For production with caching (Prometheus metrics are exposed
|
||||
# automatically at /metrics on the API port)
|
||||
vllm serve meta-llama/Meta-Llama-3-8B-Instruct \
|
||||
--gpu-memory-utilization 0.9 \
|
||||
--enable-prefix-caching \
|
||||
--enable-metrics \
|
||||
--metrics-port 9090 \
|
||||
--port 8000 \
|
||||
--host 0.0.0.0
|
||||
```
|
||||
|
|
@ -112,10 +111,10 @@ Verify TTFT (time to first token) < 500ms and throughput > 100 req/sec.
|
|||
|
||||
**Step 3: Enable monitoring**
|
||||
|
||||
vLLM exposes Prometheus metrics on port 9090:
|
||||
vLLM exposes Prometheus metrics at `/metrics` on the API port (default 8000):
|
||||
|
||||
```bash
|
||||
curl http://localhost:9090/metrics | grep vllm
|
||||
curl http://localhost:8000/metrics | grep vllm
|
||||
```
|
||||
|
||||
Key metrics to monitor:
|
||||
|
|
@ -131,7 +130,7 @@ Use Docker for consistent deployment:
|
|||
# Run vLLM in Docker
|
||||
docker run --gpus all -p 8000:8000 \
|
||||
vllm/vllm-openai:latest \
|
||||
--model meta-llama/Llama-3-8B-Instruct \
|
||||
--model meta-llama/Meta-Llama-3-8B-Instruct \
|
||||
--gpu-memory-utilization 0.9 \
|
||||
--enable-prefix-caching
|
||||
```
|
||||
|
|
@ -175,7 +174,7 @@ print(f"Loaded {len(prompts)} prompts")
|
|||
from vllm import LLM, SamplingParams
|
||||
|
||||
llm = LLM(
|
||||
model="meta-llama/Llama-3-8B-Instruct",
|
||||
model="meta-llama/Meta-Llama-3-8B-Instruct",
|
||||
tensor_parallel_size=2, # Use 2 GPUs
|
||||
gpu_memory_utilization=0.9,
|
||||
max_model_len=4096
|
||||
|
|
@ -338,9 +337,11 @@ Verify tensor parallelism uses power of 2 GPUs:
|
|||
vllm serve MODEL --tensor-parallel-size 4 # Not 3
|
||||
```
|
||||
|
||||
Enable speculative decoding for faster generation:
|
||||
Enable speculative decoding for faster generation (pass config as JSON;
|
||||
`--speculative-model` was removed in favor of `--speculative-config`):
|
||||
```bash
|
||||
vllm serve MODEL --speculative-model DRAFT_MODEL
|
||||
vllm serve MODEL \
|
||||
--speculative-config '{"model": "DRAFT_MODEL", "num_speculative_tokens": 5, "method": "draft_model"}'
|
||||
```
|
||||
|
||||
## Advanced topics
|
||||
|
|
|
|||
|
|
@ -1,7 +1,7 @@
|
|||
---
|
||||
name: openhue
|
||||
description: "Control Philips Hue lights, scenes, rooms via OpenHue CLI."
|
||||
version: 1.0.0
|
||||
version: 1.0.1
|
||||
author: community
|
||||
license: MIT
|
||||
platforms: [linux, macos, windows]
|
||||
|
|
@ -20,8 +20,11 @@ Control Philips Hue lights and scenes via a Hue Bridge from the terminal.
|
|||
## Prerequisites
|
||||
|
||||
```bash
|
||||
# Linux (pre-built binary)
|
||||
curl -sL https://github.com/openhue/openhue-cli/releases/latest/download/openhue-linux-amd64 -o ~/.local/bin/openhue && chmod +x ~/.local/bin/openhue
|
||||
# Linux (pre-built binary — releases ship tarballs, not bare binaries)
|
||||
curl -sL "https://github.com/openhue/openhue-cli/releases/latest/download/openhue_Linux_x86_64.tar.gz" \
|
||||
| tar -xz -C /tmp openhue \
|
||||
&& install -m 0755 /tmp/openhue ~/.local/bin/openhue
|
||||
# (use openhue_Linux_arm64.tar.gz on ARM64)
|
||||
|
||||
# macOS
|
||||
brew install openhue/cli/openhue-cli
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue