xskillaber Skills
This directory contains built-in skills that extend xskillaber's capabilities.
## Skill Format
Each skill is a directory containing a `SKILL.md` file with:
- YAML frontmatter (name, description, metadata)
- Markdown instructions for the agent
## Attribution
These skills are adapted from [OpenClaw](https://github.com/openclaw/openclaw)'s skill system.
The skill format and metadata structure follow OpenClaw's conventions to maintain compatibility.
## Available Skills
| Skill | Description |
|-------|-------------|
| `cron` | Schedule reminders and recurring tasks. |
| `dalphin` | Multi-agent DevOps utilities for environment management and project discovery. |
| `git` | Interact with Git repositories using the `git` CLI. |
| `glain` | Knowledge base with semantic RAG, hybrid search, entity extraction. |
| `memory` | Two-layer memory system with grep-based recall. |
| `mindot` | Advanced decision making engine using multi-criteria analysis. |
| `summarize` | Summarize or extract text/transcripts from URLs, podcasts, and files. |
| `taskaxn` | Structured task and action management. |
| `terminal` | Shell command execution and management. |
| `upskiller` | Create or update AgentSkills. |
| `wiggum` | Specialized code development loop (Red-Green-Refactor). |
## Installing Skills into Hermes Agent
xskillaber skills are useful on their own (via `xskillaber skill list` /
`xskillaber skill index`), but most users also want them available to
**Hermes Agent** so the agent can load the skill knowledge into its
context. Hermes discovers skills at `~/.hermes/skills/<name>/SKILL.md`.
Two ways to install:
### Option A — local install script (recommended, no network)
`scripts/install_skill.py` copies a skill from this repo's source tree
into `~/.hermes/skills/`. Local-only; no public registry, no clawhub.
```bash
# From the xskillaber repo root:
python -m scripts.install_skill glain memory
# or every shipped skill:
python -m scripts.install_skill --all
# or override HERMES_HOME for a per-profile install:
python -m scripts.install_skill glain --hermes-home ~/.hermes-profiles/work
```
The script is idempotent: re-running without `--force` skips existing
files (preserves manual edits); with `--force`, it overwrites.
The companion `scripts/list_xskills.py` shows which shipped skills are
absent, installed, or outdated relative to a given `HERMES_HOME`.
### Option B — manual copy
If you prefer not to run the script:
```bash
cp -r xskillaber/skills/glain ~/.hermes/skills/
```
### Why no public registry?
xskillaber intentionally does NOT publish to clawhub, PyPI, or any
public skill index. Skill installation is a file-copy operation the
user runs themselves against the local source tree they already have.
This keeps the trust boundary clear: only skills you've explicitly
checked out land in your Hermes home.
## SKILL.md Frontmatter
```yaml
---
name: skill-name # required, matches directory name
description: one liner # required, used in skill pickers
always: true # optional, load on every agent session
version: 0.1.0 # optional
---
```
`always: true` should be reserved for skills the agent needs on every
turn (e.g. `glain`, `memory`). Default-off skills are only loaded when
the agent's task matches their description.
Metadata
Release files for xskillaber 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| xskillaber-0.0.1-cp312-cp312-manylinux_2_39_x86_64.whl | CPython 3.12 | CPython 3.12 | Linux glibc 2.39+ x86-64 | Details for xskillaber-0.0.1-cp312-cp312-manylinux_2_39_x86_64.whl |
Release files / xskillaber-0.0.1-cp312-cp312-manylinux_2_39_x86_64.whl
| Download URL | xskillaber-0.0.1-cp312-cp312-manylinux_2_39_x86_64.whl |
|---|---|
| Size | 237.8 kB |
| Tags | CPython 3.12 Linux glibc 2.39+ x86-64 |
|
SHA-256 checksum How to use checksums |
69a68d9d1557fcdc56e01294e78e41b270b0ed09c5ef3ed8ade16c3669c4e627
|
|
BLAKE2b-256 checksum How to use checksums |
a67569ab3692327ad1b0b47f1810f2030c3a86872b7e1e509ef88e9723c6693e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.3
|
Security for xskillaber 0.0.1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.