skill-installer
Skill installer
Usage
Use this skill when the user asks to install, update, or migrate a skill so that it is discoverable by a specific agent harness.
Typical requests:
- "Install this skill from a URL"
- "Add this skill to my machine"
- "Add this skill to this repo"
- "Update this skill from this URL"
Requirements
- File system access to the destination directories
- Network access if installing from a URL
gitif installing from a git repository URL- A tool for fetching URLs (
curl,wget, or a built-in web fetch tool)
What it does
This skill helps you do three things safely:
- Decide whether a skill is repo-specific or machine-specific.
- Install the full skill folder into one or more harness-specific locations.
- Update an existing installed skill while keeping a backup.
How it works
Clarify scope and targets
Ask these questions if the user has not already specified the answers:
-
Is this skill repo-specific or machine-specific?
-
Which harnesses should be able to discover it?
-
What is the source of truth?
- local folder path
- git repo URL
- zip URL
- raw
SKILL.mdURL
If the user is unsure about repo versus machine scope, use this heuristic:
- Repo-specific: only useful in one repo, depends on that repo’s structure or conventions.
- Machine-specific: reusable across many repos.
Choose destinations
Use references/harness-locations.md to map harness and scope to install paths.
Install
- Confirm the skill directory name matches
namein frontmatter. - Confirm
SKILL.mdcontains valid frontmatter (name,description). - Copy the entire skill folder into each destination.
Update
When updating an already installed skill:
- Create a timestamped backup of the existing installed folder.
- Replace the installed folder with the new version.
- Confirm the harness can discover the updated skill.
Do not delete user files unless they explicitly ask.
Notes on distribution
Some ecosystems distribute a packaged .skill file, which is a zip container. Treat that as a distribution artifact, not the canonical source.
More from ericmjl/skills
html-presentations
Create single-file HTML slide presentations with vanilla JS/CSS. Themed (terminal.css, catppuccin, nord), keyboard-navigable, with inline SVG diagrams and animations. Use when the user asks for an HTML presentation, slide deck, or single-file slides without a framework.
29agents-md-improver
Proposes updates to AGENTS.md so repo-local coding-agent instructions stay accurate, non-contradictory, and consolidated. Use when the user corrects the agent (e.g. do not do X, always do Y, from now on, remember this), asks to edit or sync AGENTS.md, CLAUDE.md, .claude/CLAUDE.md, or GEMINI.md, wants one canonical instruction file or to deduplicate agent docs, or flags conflicting or outdated repository agent rules.
22scientific-eda
Defensive exploratory data analysis for scientific data (CSV, FASTA, etc.). Context-first, human-guided; one plot at a time, ask why before executing, append-only journal per session, scripts with PEP723 and uv run, WebP plots. Use when opening data files for EDA or when the user wants guided scientific data exploration.
20skill-creator
Guide for authoring Agent Skills with strong YAML `description` triggers, progressive disclosure, and bundled resources. Use when creating or updating a skill, running init_skill.py or package_skill.py, or improving a bland skill description so agents load the skill on the right user tasks.
18ml-experimentation
Conduct machine learning experiments from planning through evaluation and report writing. Use when running ML experiments, testing hypotheses, training models, or writing up results. Covers single-hypothesis scoping, fast iteration loops, targeted logging, JOURNAL.md protocol, data-backed diagnostic plots, and scientific report writing.
16gh-cli
Use GitHub CLI (gh) for common operations like creating PRs, viewing GitHub Actions logs, managing issues, reviewing PRs, and more. Use this when you need to interact with GitHub repositories directly from the command line.
14