skill-installer

Name: skill-installer
Author: vinhnx

AI Community

Repo stars 604
Author repo VTCode

Interpretation is structured for decision-making; original keeps the upstream SKILL.md unchanged.

Decide Fit First

Core job: Install VT Code skills into ~/.agents/skills from a curated list or a GitHub repo path. Use when a user asks to list installable…
Best fit: Use it when the task has reusable inputs, steps, and validation criteria rather than a one-off answer.
Avoid forcing it: If the source lacks commands, platform support, or external-service evidence, keep those fields unknown instead of guessing.

Design Intent

Structure: The skill is organized around “Communication”, “Scripts”, “List Curated Skills”, “Install from Curated List”, showing how the author expects the agent to judge fit, collect context, and produce verifiable output.
Trigger evidence: Prioritize the author’s wording around when to use it, what context to collect, and what output shape to produce.
Evidence boundary: Author text states facts, repository files prove commands and paths, and Fluxly only adds fit, limits, and usage judgment.

How To Use It

Inputs: Provide target material, scope, expected result, forbidden changes, and validation method.
Invocation: Name skill-installer directly; if the source includes slash commands, start with the command and then add task context.
Validation: Start small and check whether the result follows “Communication / Scripts / List Curated Skills” before expanding.

Boundaries And Review

Dependencies: Prepare GitHub API keys before running a full task.
Permissions: Declared permissions include read / env-read; ask the agent to state file, command, and rollback boundaries before acting.
Quality bar: A useful result names the deliverable, evidence, and next action. Generic prose means the task needs tighter context.

Skill Installer

Helps install skills. By default these are from https://github.com/openai/skills/tree/main/skills/.curated, but users can also provide other locations.

Use the helper scripts based on the task:

List curated skills when the user asks what is available, or if the user uses this skill without specifying what to do.
Install from the curated list when the user provides a skill name.
Install from another repo when the user provides a GitHub repo/path (including private repos).

Install skills with the helper scripts.

Communication

Start by confirming the task and running the appropriate command.
If something fails, report the exact error and ask what to do next.
Say only what is necessary.

Scripts

List Curated Skills

Show available skills from the curated list:

scripts/list-curated-skills.py

Optional: specify a different repo or path:

scripts/list-curated-skills.py --repo owner/repo --path skills/path --ref branch

Output formats:

Default: numbered list with installation status
JSON: --format json for programmatic use

Install from Curated List

Install a skill by name from the curated list:

scripts/install-skill-from-github.py <skill-name>

The skill will be installed to ~/.agents/skills/<skill-name>/.

Install from Any GitHub Repo

Install skills from any GitHub repository:

scripts/install-skill-from-github.py owner/repo path/to/skill

For private repos, ensure gh CLI is authenticated or GITHUB_TOKEN is set.

Install multiple skills from the same repo:

scripts/install-skill-from-github.py owner/repo path/to/skill1 path/to/skill2

Behavior and Options

Installation Location

Skills are installed to ~/.agents/skills/ by default.

Private Repositories

For private repositories:

Ensure GitHub CLI (gh) is installed and authenticated: gh auth login
Or set the GITHUB_TOKEN environment variable

Overwriting Existing Skills

If a skill with the same name already exists, the installer will:

Warn about the existing skill
Ask for confirmation before overwriting
Back up the existing skill before replacement

Validation

Before installing, the script validates:

SKILL.md exists and has valid frontmatter
Skill name follows naming conventions
No invalid or dangerous file patterns

Notes

Skills installed from GitHub are placed in the User scope.
After installation, the skill is immediately available in the current session.
Use /skills list to verify installation.
Use /skills load <skill-name> to activate the skill.

Fluxly profile Author and license come from source; runtime, permissions, and network are Fluxly detections or estimates

Fluxly category: AI
Author-declared agents: No explicit declaration found; this is not inferred or tested compatibility
Static check: 88 / 100 · heuristic scan, not runtime safety proof
Author / version / license: @vinhnx · no license declared
Fluxly token estimate: Lean
Fluxly setup estimate: Guided setup
External API key: Required · GitHub
Detected OS requirements: Unspecified
Runtime requirements: Unspecified
Detected file/system behavior: Read-only
Env read
Detected network behavior: External requests
Install commands: None (reference only)

Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.

Heads up: 未限定 allowed-tools，默认拥有全部工具权限。

Output preview skill-installer-vinhnx.preview

The current SKILL.md does not define a fixed output example.

SKILL.md SKILL.md

# Skill Installer

Helps install skills. By default these are from https://github.com/openai/skills/tree/main/skills/.curated, but users can also provide other locations.

Use the helper scripts based on the task:

-   List curated skills when the user asks what is available, or if the user uses this skill without specifying what to do.
-   Install from the curated list when the user provides a skill name.
-   Install from another repo when the user provides a GitHub repo/path (including private repos).

Install skills with the helper scripts.

## Communication

-   Start by confirming the task and running the appropriate command.
-   If something fails, report the exact error and ask what to do next.
-   Say only what is necessary.

## Scripts

### List Curated Skills

Show available skills from the curated list:

```bash
scripts/list-curated-skills.py
```

Optional: specify a different repo or path:

```bash
scripts/list-curated-skills.py --repo owner/repo --path skills/path --ref branch
```

Output formats:

-   Default: numbered list with installation status
-   JSON: `--format json` for programmatic use

### Install from Curated List

Install a skill by name from the curated list:

```bash
scripts/install-skill-from-github.py <skill-name>
```

The skill will be installed to `~/.agents/skills/<skill-name>/`.

### Install from Any GitHub Repo

Install skills from any GitHub repository:

```bash
scripts/install-skill-from-github.py owner/repo path/to/skill
```

For private repos, ensure `gh` CLI is authenticated or `GITHUB_TOKEN` is set.

Install multiple skills from the same repo:

```bash
scripts/install-skill-from-github.py owner/repo path/to/skill1 path/to/skill2
```

## Behavior and Options

### Installation Location

…

Evidence boundary and execution chain

Author text anchors workflow facts; Fluxly only indexes current sections, terms, files, and commands.

sections -> Communication → Scripts → List Curated Skills → Install from Curated List → Install from Any GitHub Repo → Behavior and Options
terms    -> Helps install skills. · - List curated skills when the user asks what is available, or if the user uses this skill without specifying what to do. · Install skills with the helper scripts. · - Start by confirming the task and running the appropriate command. · The skill will be installed to ~/.agents/skills/<skill-name>/. · For private repos, ensure gh CLI is authenticated or GITHUBTOKEN is set. · Skills are installed to ~/.agents/skills/ by default. · 1. Ensure GitHub CLI (gh) is installed and authenticated: gh auth login 2.
files/cmd -> --format json · ~/.agents/skills/<skill-name>/ · GITHUBTOKEN · ~/.agents/skills/ · gh auth login · /skills list · /skills load <skill-name>
body sha256 -> 952bad03bd6b