Skip to main content
commandsSource-backedReview first Safety Privacy

Agent Skills Installer for Claude Code

Install and manage Claude Code Agent Skills - specialized knowledge packages that extend Claude's capabilities with domain expertise and progressive disclosure

by JSONbored·added 2025-10-25·
HarnessClaude Code
Invocation:/skills-installer [action] [skill-name]
Review first review before installing

Open the source and read safety notes before installing.

Citation facts

Source-backed facts for citing this resource, derived directly from the registry — also available as plain text for AI assistants.

Source URLs
https://code.claude.com/docs/en/skills, https://github.com/JSONbored/awesome-claude/blob/main/content/commands/skills-installer.mdx
Safety notes
Review generated changes and commands before applying them; slash commands can ask the agent to read, write, edit, or run tools in the current project., Limit scope to the intended files and run in a trusted checkout when the command analyzes code, tests, security findings, or generated output.
Privacy notes
Prompts, source files, logs, errors, dependency metadata, and generated reports may be sent to the configured AI model during command execution., Redact secrets, customer data, private repository details, and proprietary code before sharing command output outside the workspace.
Author
JSONbored
Claim status
unclaimed
Last verified
2025-10-25

Decision playbook

Review trust signals before you adopt

Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.

Compare context
Selected

0

Current score

78

Baseline

Delta

No baseline selected

No major trust-signal divergence detected in the current selection.

Source and provenance checks

Complete

Confirm ownership and provenance before trusting install instructions.

  • Source link availableRequired

    Open the canonical repository and verify ownership.

    Done
  • Source provenance statusRequired

    Marked as source-backed.

    Done
  • Metadata reviewed

    Registry metadata indicates a reviewed listing.

    Done

Safety and privacy checks

Complete

Validate risk disclosures before installation or API wiring.

  • Safety notes presentRequired

    Review the listed safety guidance before running commands.

    Done
  • Privacy notes presentRequired

    Review data handling notes before connecting accounts or secrets.

    Done
  • Trust level risk gateRequired

    Trust level does not block evaluation.

    Done

Package and install checks

Needs review

Check package metadata and artifact integrity signals.

  • Install payload available

    Install or copy payload is available for review.

    Done
  • Package verification flag

    No package verification flag provided.

    Pending
  • Checksum metadata

    No checksum provided for downloaded artifact.

    Pending

Compare-driven decision checks

Needs review

Use compare context to validate trade-offs before adoption.

  • Compare tray has multiple entries

    Add at least one more entry to compare trust differences.

    Pending
  • Baseline comparison available

    No baseline peer selected yet.

    Pending
  • Diverging trust signals identified

    No major trust-signal divergence found.

    Pending

Setup at a glance

CLI install

Copy-ready — paste the snippet to get started.

Install command

Provided

Config snippet

Not provided

Copy snippet

Provided

Prerequisites

None

Platforms

1 listed

Difficulty

100/100

Adoption plan

Balanced adoption plan

Current risk score 16/100. Use staged verification before broader rollout.

Risk 16

Pre-adoption checks

Validate source and review signals before any execution.

  • Confirm source provenanceRequired

    Source URL/provenance metadata is present.

    Done
  • Confirm metadata review state

    Listing has review metadata.

    Done
  • Verify install payload

    Install/config payload exists and can be inspected.

    Done

Security checks

Confirm safety, privacy, and package integrity signals.

  • Review safety notesRequired

    Safety notes are present.

    Done
  • Review privacy notesRequired

    Privacy notes are present.

    Done
  • Verify package integrity metadata

    No package verification/checksum metadata.

    Pending

Rollout

Adopt in controlled steps based on the selected plan.

  • Run in isolated sandbox firstRequired

    Use a constrained sandbox and observe behavior across multiple tasks.

    Pending
  • Roll out graduallyRequired

    Roll out to a small cohort before wider usage.

    Pending
  • Set monitoring and fallback

    Define rollback path and monitor errors after adoption.

    Pending

Evidence readiness

Evidence readiness matrix · balanced

Required evidence gates are covered (5/6 signals complete).

Risk 15

Source provenance

Present

Source repository/provenance is listed.

Required in this preset

Metadata review

Present

Review metadata is present.

Required in this preset

Safety notes

Present

Safety notes are present.

Required in this preset

Privacy notes

Present

Privacy notes are present.

Optional in this preset

Package integrity

Missing

Package integrity metadata is missing.

Optional in this preset

Install payload

Present

Install payload is available.

Required in this preset

Required evidence gates are covered for this preset.

Decision timeline

Decision timeline · balanced

5/6 steps complete with no blocking gaps for this preset.

Risk 14

triage

Confirm source provenanceRequired

Source/provenance metadata is available.

Done

triage

Check metadata review statusRequired

Review metadata is available.

Done

verify

Review safety notesRequired

Safety notes are available.

Done

verify

Review privacy notes

Privacy notes are available.

Done

verify

Validate package integrity metadata

Package integrity metadata is missing.

Pending

rollout

Verify install payload and commandsRequired

Install payload is available.

Done

No required blockers for this timeline preset.

Safety & privacy surface

Safety & privacy surface

2 safety and 2 privacy notes across 4 risk areas. Review closely: credentials & tokens, permissions & scopes, third-party handling.

4 areas
  • SafetyExecution & processesReview generated changes and commands before applying them; slash commands can ask the agent to read, write, edit, or run tools in the current project.
  • SafetyPermissions & scopesLimit scope to the intended files and run in a trusted checkout when the command analyzes code, tests, security findings, or generated output.
  • PrivacyThird-party handlingPrompts, source files, logs, errors, dependency metadata, and generated reports may be sent to the configured AI model during command execution.
  • PrivacyCredentials & tokensRedact secrets, customer data, private repository details, and proprietary code before sharing command output outside the workspace.

Safety notes

  • Review generated changes and commands before applying them; slash commands can ask the agent to read, write, edit, or run tools in the current project.
  • Limit scope to the intended files and run in a trusted checkout when the command analyzes code, tests, security findings, or generated output.

Privacy notes

  • Prompts, source files, logs, errors, dependency metadata, and generated reports may be sent to the configured AI model during command execution.
  • Redact secrets, customer data, private repository details, and proprietary code before sharing command output outside the workspace.

Schema details

Install type
cli
Reading time
8 min
Difficulty score
100
Troubleshooting
Yes
Breaking changes
No
Runtime and command metadata
Command syntax
/skills-installer [action] [skill-name]
Full copyable content
/skills-installer [action] [skill-name]

About this resource

The /skills-installer command installs Agent Skills - model-controlled configuration packages that extend Claude's capabilities with specialized domain knowledge.

Features

  • 47 Specialized Skills: Domain-specific expertise packages
  • Progressive Disclosure: Skills activate only when relevant to task
  • Plugin System: Modular knowledge packages
  • Auto-Activation: Claude automatically selects appropriate skills
  • Skill Discovery: Browse available skills by category
  • Version Management: Update skills as they evolve
  • Dependency Resolution: Auto-install required dependencies
  • Team Sharing: Commit skills config to git

Usage

/skills-installer [action] [skill-name]

Actions

  • --install - Install skill by name
  • --list - List available skills
  • --installed - Show installed skills
  • --uninstall - Remove skill
  • --update - Update installed skills
  • --search - Search skills by keyword

Categories

  • --development - Programming and development skills
  • --devops - Infrastructure and deployment
  • --data - Data science and analytics
  • --security - Security and compliance
  • --frontend - UI/UX and frontend
  • --backend - Server-side and APIs

What Are Agent Skills?

Agent Skills are model-controlled configurations that give Claude specialized knowledge:

  • Files, scripts, resources for specific domains
  • Activated automatically when relevant
  • Extend capabilities without manual prompting
  • Similar to VS Code extensions but for AI

Examples

Install React 19 Skill

Command:

/skills-installer --install react-19-expert

Installation:

[Installing Skill: React 19 Expert]

✓ Downloaded skill package
✓ Installed dependencies
✓ Configured activation triggers

Skill Capabilities:
- React 19.1 features (use hook, Server Actions)
- React Compiler optimization
- Server Components best practices
- Concurrent rendering patterns
- New hooks (useOptimistic, useFormStatus)

Activation Triggers:
- React file detected (*.tsx, *.jsx)
- package.json contains "react": "^19"
- Prompts mentioning React/components

✓ Skill installed successfully

Auto-Activation:

User: "Create a form with optimistic updates"

[Agent Skill: React 19 Expert - Activated]

Claude: "I'll use React 19's useOptimistic hook for this..."

// Generated code uses React 19 patterns
import { useOptimistic } from 'react';

export function TodoForm({ addTodo }: Props) {
  const [optimisticTodos, addOptimisticTodo] = useOptimistic(
    todos,
    (state, newTodo) => [...state, newTodo]
  );

  // ...
}

Install TypeScript Strict Mode Skill

Command:

/skills-installer --install typescript-strict

Skill Details:

[TypeScript Strict Mode Expert]

Capabilities:
- Enforce strict mode conventions
- No `any` type - suggest `unknown` instead
- Proper type guards
- Discriminated unions
- Advanced type inference

Configuration:
  "compilerOptions": {
    "strict": true,
    "noUncheckedIndexedAccess": true,
    "noImplicitReturns": true
  }

✓ Installed

Effect:

// Before skill:
function getData(id: any) {
  // Claude might use 'any'
  return data[id];
}

// After skill activated:
function getData(id: string): User | undefined {
  // Strict types
  const user = data[id]; // Could be undefined
  if (!user) {
    throw new Error(`User ${id} not found`);
  }
  return user;
}

Install Multiple Skills

Command:

/skills-installer --install next-15-expert prisma-advanced tdd-workflow

Batch Installation:

[Installing 3 Skills]

1/3 Next.js 15 Expert
  ✓ Installed
  - App Router patterns
  - Server Components
  - Partial Prerendering
  - React 19 integration

2/3 Prisma Advanced
  ✓ Installed
  - Query optimization
  - N+1 prevention
  - Migration strategies
  - Type safety patterns

3/3 TDD Workflow
  ✓ Installed
  - Test-first development
  - Red-green-refactor
  - Coverage enforcement
  - Mock strategies

✓ All skills installed

List Available Skills

Command:

/skills-installer --list --category=development

Output:

[Available Development Skills]

## Frontend
- react-19-expert - React 19.1 features and patterns
- next-15-expert - Next.js 15 App Router mastery
- tailwind-v4 - TailwindCSS v4 modern patterns
- svelte-5-runes - Svelte 5 with runes system

## Backend
- node-20-performance - Node.js 20 performance patterns
- fastify-optimization - Fastify web framework expert
- graphql-federation - GraphQL Federation v2
- prisma-advanced - Advanced Prisma ORM patterns

## Testing
- vitest-advanced - Vitest testing mastery
- playwright-e2e - Playwright E2E testing
- tdd-workflow - Test-driven development expert

## Language Expertise
- typescript-strict - TypeScript strict mode expert
- python-type-hints - Python typing and mypy
- go-idioms - Go language idioms
- rust-ownership - Rust ownership patterns

Total: 47 skills available
Installed: 0

View Installed Skills

Command:

/skills-installer --installed

Output:

[Installed Skills]

✓ react-19-expert (v1.2.0)
  Last used: 2 hours ago
  Activations: 45 times

✓ typescript-strict (v2.1.0)
  Last used: Active now
  Activations: 120 times

✓ next-15-expert (v1.0.5)
  Last used: Yesterday
  Activations: 30 times

3 skills installed
Storage: 2.4 MB

Search Skills

Command:

/skills-installer --search "database optimization"

Results:

[Search Results: database optimization]

1. prisma-advanced
   Description: Advanced Prisma patterns with query optimization
   Tags: database, orm, optimization, performance

2. postgres-performance
   Description: PostgreSQL query optimization and indexing
   Tags: database, postgresql, performance, sql

3. mongodb-aggregation
   Description: MongoDB aggregation pipeline mastery
   Tags: database, mongodb, nosql, performance

Found 3 matching skills

Skill Categories

Frontend Skills

  • react-19-expert - React 19 features
  • next-15-expert - Next.js 15 patterns
  • vue-3-composition - Vue 3 Composition API
  • svelte-5-runes - Svelte 5 runes
  • tailwind-v4 - TailwindCSS v4
  • framer-motion-advanced - Animation patterns

Backend Skills

  • node-20-performance - Node.js optimization
  • fastapi-async - FastAPI async patterns
  • nestjs-microservices - NestJS architecture
  • express-security - Express.js security
  • graphql-federation - GraphQL Federation

Database Skills

  • prisma-advanced - Prisma ORM mastery
  • postgres-performance - PostgreSQL optimization
  • mongodb-aggregation - MongoDB pipelines
  • redis-caching - Redis caching strategies
  • drizzle-orm - Drizzle ORM patterns

DevOps Skills

  • docker-optimization - Docker best practices
  • kubernetes-deployment - K8s deployments
  • github-actions-ci - GitHub Actions CI/CD
  • terraform-iac - Infrastructure as Code
  • vercel-edge - Vercel Edge Functions

Testing Skills

  • vitest-advanced - Vitest mastery
  • playwright-e2e - Playwright E2E
  • cypress-component - Cypress testing
  • tdd-workflow - Test-driven development
  • jest-migration - Jest to Vitest migration

Security Skills

  • owasp-top-10 - OWASP security patterns
  • auth-best-practices - Authentication/authorization
  • input-validation - Input sanitization
  • secrets-management - Secret handling
  • csrf-protection - CSRF prevention

Progressive Disclosure

How Skills Activate

User: "Fix the login component"

[Skill Selection Process]
1. Detect context: React component
2. Check installed skills
3. Activate: react-19-expert
4. Load knowledge: React 19 patterns
5. Apply to task

Claude: *Uses React 19 patterns automatically*

Multiple Skills Simultaneously

User: "Optimize the database queries in the API"

[Skills Activated]
✓ prisma-advanced (database queries)
✓ node-20-performance (API optimization)
✓ typescript-strict (type safety)

Claude: *Combines knowledge from all 3 skills*

Skill Configuration

Where Skills Are Stored

# Project skills (team-shared)
.claude/
  skills/
    react-19-expert/
      config.json
      patterns.md
      examples/
    typescript-strict/
      config.json
      rules.md

# User skills (personal)
~/.claude/
  skills/
    personal-shortcuts/

Skill Configuration File

// .claude/skills/react-19-expert/config.json
{
  "name": "react-19-expert",
  "version": "1.2.0",
  "description": "React 19 expert with latest features",
  "activationTriggers": [
    { "filePattern": "**/*.{tsx,jsx}" },
    { "keyword": "react" },
    { "packageJson": "react" }
  ],
  "capabilities": [
    "React 19.1 features",
    "Server Components",
    "React Compiler",
    "New hooks"
  ],
  "dependencies": ["typescript-strict"]
}

Updating Skills

Command:

/skills-installer --update

Update Process:

[Checking for Updates]

✓ react-19-expert: v1.2.0 → v1.3.0 available
  - Added Server Actions patterns
  - Improved useOptimistic examples

✓ typescript-strict: Up to date (v2.1.0)

✓ next-15-expert: v1.0.5 → v1.1.0 available
  - Partial Prerendering patterns
  - Updated caching strategies

Update all? (y/n): y

[Updating 2 skills]
✓ react-19-expert updated
✓ next-15-expert updated

All skills up to date

Best Practices

Install Relevant Skills Only

# ✅ Good: Install skills you actually use
/skills-installer --install react-19-expert typescript-strict

# ❌ Bad: Install everything
/skills-installer --install * # Don't do this

Team Collaboration

# Commit skills config to git
git add .claude/skills/
git commit -m "Add React 19 and TypeScript skills"

# Team members get same skills automatically
git pull
# Skills auto-install on first use

Skill Priority

// More specific skills override general skills
{
  "skills": [
    { "name": "typescript-strict", "priority": 10 },
    { "name": "react-19-expert", "priority": 20 }, // Higher priority
    { "name": "next-15-expert", "priority": 30 } // Highest priority
  ]
}

Troubleshooting

Skill Not Activating

# Check skill installation
/skills-installer --installed

# Verify activation triggers
# Edit .claude/skills/[skill]/config.json

# Manually activate for testing
"Use the React 19 expert skill for this task"

Conflicting Skills

# Some skills may conflict
# Example: jest-expert + vitest-expert

# Solution: Uninstall conflicting skill
/skills-installer --uninstall jest-expert

Skill Updates Breaking

# Rollback to previous version
/skills-installer --rollback react-19-expert

# Or pin specific version
/skills-installer --install react-19-expert@1.2.0

Source citations

Add this badge to your README

Show that Agent Skills Installer for Claude Code is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.

Listed on HeyClaude
[![Listed on HeyClaude](https://heyclau.de/badge/commands/skills-installer.svg)](https://heyclau.de/entry/commands/skills-installer)

How it compares

Agent Skills Installer for Claude Code side by side with its closest alternative on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.

Field

Install and manage Claude Code Agent Skills - specialized knowledge packages that extend Claude's capabilities with domain expertise and progressive disclosure

Open dossier

User-created Claude Code custom slash command recipe for planning deeper tests around a file or function, including edge cases, property-style invariants, regression cases, and mutation-score gaps where the project already supports those tools.

Open dossier
Next steps
Trust
Review statusReviewedMaintainer reviewedReviewedMaintainer reviewed
Package trustPackage not verifiedPackage not verified
Source provenanceSource-backedSource-backed
Submitter
Install riskReview firstReview first
Notes Safety Privacy Safety Privacy
Brand
Categorycommandscommands
Sourcesource-backedsource-backed
AuthorJSONboredJSONbored
Added2025-10-252025-09-16
Platforms
Claude Code
Claude Code
Source repo
Safety notesReview generated changes and commands before applying them; slash commands can ask the agent to read, write, edit, or run tools in the current project. Limit scope to the intended files and run in a trusted checkout when the command analyzes code, tests, security findings, or generated output.This recipe asks Claude to inspect and draft tests against local project code; review generated tests before committing them. Run the narrowest relevant test command yourself and verify failures before broadening the suite or changing production code. If you add allowed-tools or dynamic shell injection to the command file, scope those permissions narrowly because the command can run local tools.
Privacy notesPrompts, source files, logs, errors, dependency metadata, and generated reports may be sent to the configured AI model during command execution. Redact secrets, customer data, private repository details, and proprietary code before sharing command output outside the workspace.The target source file, nearby tests, failures, logs, and command arguments may be sent into the model context. Use synthetic fixtures and redacted logs; do not paste production data, credentials, customer records, or private incident details into generated tests.
Prerequisites— none listed— none listed
Install
/skills-installer [action] [skill-name]
/test-advanced src/utils/parser.ts
Config
Citations
ClaimUnclaimedUnclaimed
Open in the interactive comparison tool

Related guides

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.