Automated summary
Installs a skill from the library into the current project by resolving it from already-active skills, the cache, the local library, or the remote registry, then validating it before activation.
Strengths
- Cascading resolution (already active → cache → local library → registry) that avoids unnecessary network calls.
- Validates each fetched skill (SKILL.md present, file count and expected file list) before copying, so a broken skill is never activated.
- Handles network failures explicitly: reports which cached version is being used and when it was fetched, or states the skill is unavailable offline.
- Idempotent: a skill that is already active is silently skipped.
Limitations
- Depends on internal files (_index.json, _registry.json, _cache) whose format is not documented in the skill itself.
- Clones with --depth 50 against a pinned commit SHA, which can fail if the revision is more than 50 commits behind.
- No update, removal, or skill-authoring command is described.
Use it when you want to activate an additional skill from the library inside the current project.
Avoid it for updating, removing, or authoring a skill, or when the requested skill is not present in the registry.
Security analysis
CautionThe skill acts as a package installer, cloning remote repositories and copying files into the active skills directory. While it does not directly execute fetched code or exfiltrate data, it enables the installation of untrusted third-party skills with limited validation, which could lead to malicious behavior downstream.
- •Fetches and copies third-party skill files from remote repositories using git clone without strong integrity verification (only file count and presence checks).
- •Uses bash commands for network operations and file copying, though no allowed-tools are declared.
- •Installed skills may later be executed by the AI agent, so a compromised registry or repository could introduce malicious instructions.
Examples
/claude-gen-add-skill/claude-gen-add-skill golang-pro/claude-gen-add-skill python-pro — I have no network, use the cached copy if you have one.name: claude-gen-add-skill description: Add a skill from the library to this project. Usage: /claude-gen-add-skill [skill-name] or /claude-gen-add-skill to see available list.
Steps
-
No argument given → read
_index.json, list available skills not yet active:Available skills for your stack ({profile}): golang-pro — Go 1.22+ goroutines, GORM [cached] python-pro — Python 3.12+ async, typing [cached] ... Already active: debugging, docker, git-advanced -
Argument given → find {skill}:
- Check
.claude/skills/{skill}/→ already active? Skip. - Check
.claude/skills/_library/_cache/{skill}/→ cached? Copy to active. - Check
.claude/skills/_library/{skill}/→ local skill? Copy to active. - Not found locally? Check
_registry.json→ fetch from source.
- Check
-
Fetching from registry (when not in cache):
# Read _registry.json for source repo + ref (commit SHA) # SHA cannot use --branch, so clone then checkout: git clone --depth 50 {repo} /tmp/skill-fetch cd /tmp/skill-fetch && git checkout {ref} # Copy the skill directory from {path} to cache -
Validate after fetch:
- SKILL.md exists
- Count files matches
file_countin_registry.json - All files listed in
filesarray are present - If validation fails → report error, do NOT copy broken skill
-
On network failure:
- Report: "Cannot fetch {skill} — network unavailable."
- If skill exists in
_cache/: "Using cached version from {fetched date}." - If not cached: "Skill not available offline. Try again when connected."
-
Copy to active:
.claude/skills/_library/_cache/{skill}/ → .claude/skills/{skill}/ -
Report: "Added: {name} — {description}"
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/add-skill-from-library-mrwake9x/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/add-skill-from-library-mrwake9x' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/add-skill-from-library-mrwake9x/download' --output '.skill-downloads/add-skill-from-library-mrwake9x/SKILL.md.part' && mv '.skill-downloads/add-skill-from-library-mrwake9x/SKILL.md.part' '.skill-downloads/add-skill-from-library-mrwake9x/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/add-skill-from-library-mrwake9x/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
React Hook Form Best Practices
Development
Master React Hook Form: avoid anti-patterns, manage subscriptions, and handle reset, dirty state, and controlled inputs correctly.
Emotion to Mantine Migration
Development
Migrate Emotion styled-components to Mantine components with style props and CSS modules. Use when converting .styled.tsx files or removing @emotion imports.
Scope Creep Detector
Development
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad PRs, and oversized changes, then suggests keep, split, or justify actions.