What it can do: magic-powers

Plugin bundle · kienbui1995

What magic-powers declares, asks for and runs, according to the marketplaces we read. Installs into the AI tool as a plugin bundle; what it starts is listed below. None of the marketplaces we read publishes its tools or the settings it asks for. As of our marketplace pass on 2026-10-12.

This is not a security audit. We list what the marketplaces publish about this plugin: what it declares, what it asks for and what it runs. We do not run or inspect its code, and a verified mark is the marketplace's statement, not ours.

Where it runs

Installs into the AI tool as a plugin bundle; what it starts is listed below.As declared on: Claude Code: claude-plugins-community.

What it declares

None of the marketplaces we read publishes a list of tools for it.

Prompts and resources: the marketplaces we read do not publish them.

What it asks for

None of the marketplaces we read lists environment variables for it.

Names only: we keep no values, examples or descriptions of these variables. OAuth scopes and install-time settings are not published by the marketplaces we read.

What it runs besides MCP

Skills: 155 As declared on: Claude Code: claude-plugins-community.

accessibility-audit
accessibility-compliance
ado-api-cli
ado-artifacts
ado-container-deployments
ado-organization
ado-pipeline-design
ado-pipeline-optimization
ado-pipeline-security
ado-pipelines-ops
ado-release-management
ado-security-policies

Show the remaining 143

ado-work-tracking
adr-writing
agentic-ai-patterns
agentic-eval
agentic-memory
agentic-reliability
agentic-security
ai-data-moat
ai-harness
ai-product-design
ai-product-monetization
ai-product-positioning
ai-product-retention
ai-product-validation
ai-safety-guardrails
analytics-reporting
api-contract-testing
api-design
authentication-patterns
blockchain-audit
brainstorming
brand-voice
caching-strategy
capacity-planning
chaos-engineering
ci-cd-pipeline
claude-hooks
claude-mcp-setup
claude-md-authoring
claude-memory
claude-project-settings
cloud-cost-review
competitive-analysis
content-strategy
cost-aware-routing
data-modeling
data-pipeline-design
data-quality
database-optimization
deal-strategy
dependency-management
design-handoff
design-system-audit
design-with-pencil
design-with-stitch
developer-advocacy
discovery-call
dispatching-parallel-agents
docker-containerization
email-marketing
environment-setup
executing-plans
experiment-tracking
feature-engineering
feedback-synthesis
financial-modeling
finishing-a-development-branch
game-audio
game-design-doc
growth-hacking
hr-people-ops
incident-postmortem
incident-response
infrastructure-review
knowledge-transfer
launch-planning
legal-compliance
level-design
llm-cost-optimization
llm-evaluation
llm-observability
ml-experiment-tracking
mlops-deployment
model-evaluation
model-monitoring
model-routing
model-selection-guide
mvp-rapid-development
narrative-design
on-call-runbook
open-source-project
performance-benchmarking
performance-optimization
performance-testing
pipeline-management
pr-workflow
product-metrics
product-strategy
prompt-engineering
proposal-writing
qa-audit
qa-process-design
qa-risk-management
qc-automation
qc-defect-management
qc-metrics
qc-mobile-testing
qc-security-testing
qc-test-data
qc-test-design
qc-uat-facilitation
quality-gates
rag-architecture
receiving-code-review
refactoring
requesting-code-review
roadmap-planning
sales-coaching
security-review
seo-optimization
session-lifecycle
slo-sli-design
social-media-planning
solo-founder-gtm
solutions-architecture
spatial-ux
spec-driven-development
sprint-planning
sprint-retrospective
stakeholder-communication
subagent-driven-development
support-playbook
systematic-debugging
team-onboarding
tech-debt-triage
technical-art
technical-documentation
technical-writing
test-driven-development
test-strategy
training-pipeline
user-research
user-story-writing
using-git-worktrees
using-magic-powers
ux-audit
verification-before-completion
vibe-coding
visionos-patterns
workflow-templates
writing-plans
writing-skills
xr-interface-design

Commands: 15 As declared on: Claude Code: claude-plugins-community.

brainstorming
db-review
debug
deploy
install-skills
plan
pr
refactor
review
security-scan
session-end
session-start

Show the remaining 3

setup
tdd
workflow

Agents: 16 As declared on: Claude Code: claude-plugins-community.

ado-cicd-engineer
architect
azure-devops-admin
copywriter
database-optimizer
debugger
git-workflow
product-strategist
qa-engineer
qc-engineer
reviewer
security-reviewer

Show the remaining 4

solo-ai-builder
sre
technical-writer
ui-designer

Hooks: 1 As declared on: Claude Code: claude-plugins-community.

SessionStart

Who answers for it

kienbui1995

No marketplace we read marks it or its publisher as verified.
License: MIT.
The repository github.com/kienbui1995/magic-powers belongs to the account the publisher is listed under on Claude Code: claude-plugins-community.

How it has changed

Its tools, settings, hooks and composition have not changed since we started watching it.

In context

Median number of secrets a plugin bundle asks for on the marketplaces we read: 0.0. This one asks for: 0.
Share of plugin bundles that run on a remote server: 17%.

Where it is published and how its figures have moved

Compare it side by side with similar plugins

Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Figures come from our own regular passes over the marketplaces, last read on 2026-10-12. We publish no contact details for plugin publishers.