Metadata-Version: 2.4
Name: xskillaber
Version: 0.0.1
Summary: Tool call layer for LadyOL agent harness
Author: Maintainers, nanobot contributors
Author-email: solubrew@solutionsbrewer.com
License: MIT
Platform: Linux
Requires-Python: >=3.11
Requires-Dist: pytest>=9.0.0,<10.0.0 ; extra == "dev"
Requires-Dist: pytest-asyncio>=1.3.0,<2.0.0 ; extra == "dev"
Requires-Dist: ruff>=0.1.0 ; extra == "dev"
Provides-Extra: dev
Description: # 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.
Description-Content-Type: text/markdown
