Skip to main content

rf-agentskills

Cross-agent installer for Robot Framework agent skills. Ships the plugins/rf-agentskills/ bundle (12 skills, 4 subagents, hooks, helper scripts) and writes it into the install paths of seven coding agents:

Agent Status
Claude Code (CLI) full native — skills, agents, hooks
GitHub Copilot (VS Code 1.108+) full native (preview flags req'd)
OpenAI Codex skills native; subagents transformed; hooks experimental
Cursor 2.4+ skills native, hooks adapted
OpenCode skills + subagents native; hooks deferred
Project Goose skills (~/.agents/skills) + persona text
Claude Desktop one upload ZIP per skill (Customize → Skills → Upload a skill)

Install

Zero-install one-liner (no prior pip install needed):

uvx rf-agentskills install        # or: pipx run rf-agentskills install

Bare install is interactive in a terminal — it shows a multi-select of known agents with the ones detected on your machine pre-checked, then writes into the current project. Prefer a persistent install? pipx install rf-agentskills first.

Non-interactive (CI / scripts)

Fully scriptable — no prompt when you pass an explicit selection, --yes, or when stdin isn't a TTY:

rf-agentskills install --agents claude-code,cursor   # explicit list
rf-agentskills install --agents all                  # every known agent
rf-agentskills install --agents detected --yes       # only detected, no prompt
rf-agentskills install --agent claude-code           # single (back-compat)

--agents none is a no-op. With nothing detected and no selection in a non-interactive context, the command exits non-zero and lists the valid agents.

Scope: project (default) vs user

Installs default to project scope, writing into the current directory (e.g. ./.claude/) — reviewable per-repo, and uninstall from the same directory needs no arguments. Use --scope user for a global install under your home directory:

rf-agentskills install --agents all                  # → ./<agent dirs> (project)
rf-agentskills install --agents all --scope user      # → ~/<agent dirs> (global)

The uninstall manifest follows scope: project installs record it in <project>/.rf-agentskills/, user installs in the global data dir — so two projects never collide.

Upgrading: re-run rf-agentskills install with the same agent and scope. Files the previous install wrote that the new bundle no longer ships (for example retired skills) are removed — only when their hash still matches, and only for the categories being installed; user-modified files are kept and reported. --dry-run lists them as remove rows first.

Installing a pre-release

Pre-releases (e.g. 0.5.0rc2) need an opt-in: pipx install --pip-args=--pre rf-agentskills, or with uv uv tool install --prerelease allow rf-agentskills / an exact pin rf-agentskills==0.5.0rc2.

Troubleshooting — "no version of rf-agentskills==": if uv add/uv pip/pip reports it can't find a pre-release you know was just published, your index cache is stale (common the same day a release lands). Refresh it:

uv cache clean rf-agentskills      # or: uv add --refresh …
pip install --no-cache-dir --pre rf-agentskills

To make pre-release intent self-documenting in a project, add [tool.uv]\nprerelease = "allow" to its pyproject.toml.

Subcommands

rf-agentskills install   [--agents all|none|detected|<csv> | --agent <name> | --all]
                         [--scope project|user] [--project DIR] [--prefix DIR]
                         [--what skills,agents,hooks] [--yes] [--no-input]
                         [--dry-run] [--force]
rf-agentskills uninstall --agent <name> [--scope project|user] [--project DIR]
rf-agentskills list                # what's installed where, per the manifest
rf-agentskills targets             # which agents are detected on this machine
rf-agentskills doctor              # what works, what doesn't, what needs user action
rf-agentskills version

See docs/installer/proposal.md (in the parent repo) for the full design, compatibility matrix, and per-agent install recipes.

Metadata

Release files for rf-agentskills 0.7.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for rf-agentskills 0.7.0
File Size Uploaded
rf_agentskills-0.7.0.tar.gz 259.9 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for rf-agentskills 0.7.0
File Interpreter ABI Platform
rf_agentskills-0.7.0-py3-none-any.whl Python 3 none any Details

Total release size: 623.4 kB

Release files / rf_agentskills-0.7.0.tar.gz

Download URL rf_agentskills-0.7.0.tar.gz
Size 259.9 kB
Tags Source
SHA-256 checksum
How to use checksums
af8cabbc0299c654c47d4c7632f8729d01172c07f45e6ee0bb5360472e8a18f3
BLAKE2b-256 checksum
How to use checksums
5f098fe3563c3640e5b968643c4141fbbcdd17f965d155d5398d2afcabfb75a9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.9.26 {"installer":{"name":"uv","version":"0.9.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

Release files / rf_agentskills-0.7.0-py3-none-any.whl

Download URL rf_agentskills-0.7.0-py3-none-any.whl
Size 363.5 kB
Tags Python 3
SHA-256 checksum
How to use checksums
cef86a4f868fb5ec755aab426ed53a712ff2460cdd520f0b0b8f97770da03b5b
BLAKE2b-256 checksum
How to use checksums
fdc47a899026696f302815617b403d8f9ec322a83bef827c8f63064f6a0c13e9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via uv/0.9.26 {"installer":{"name":"uv","version":"0.9.26","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page