Development
Plugin
navigator
Finish What You Start Sessions that last. AI that learns. Features that ship.
Plugin Signal77/100Solid
maintained86
capable82
documented75
adopted49
Install
$ npx -y skills add alekspetrov/navigator --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Stats
196
Stars
11
Forks
Active
Maintenance
Python
Language
26d ago
Last commit
10mo ago
Created
Repo: alekspetrov/navigator
In this plugin
- skills
- backend-endpoint
- backend-test
- database-migration
- frontend-component
- frontend-test
- nav-brief
- nav-compact
- nav-diagnose
- nav-features
- nav-graph
- nav-init
- nav-install-multi-claude
- nav-loop
- nav-marker
- nav-multi
- nav-onboard
- nav-pilot
- nav-profile
- nav-release
- nav-simplify
- nav-skill-creator
- nav-sop
- nav-start
- nav-stats
- nav-sync-claude
- nav-task
- nav-upgrade
- nav-workflow
- plugin-slash-command
- product-design
- visual-regression
- agents
What's inside
Skills
31/backend-endpointCreate REST/GraphQL API endpoint with validation, error handling, and tests. Auto-invoke when user says "add endpoint", "create API", "new route", or "add route"./backend-testGenerate backend tests (unit, integration, mocks) for existing code. Auto-invoke when user says "write test for", "add test", "test this", or "create test"./database-migrationCreate database migration with schema changes and rollback. Auto-invoke when user says "create migration", "add table", "modify schema", or "change database"./frontend-componentCreate React/Vue component with TypeScript, tests, and styles. Auto-invoke when user says "create component", "add component", "new component", or "build component"./frontend-testGenerate frontend component tests (React Testing Library, Vue Test Utils, snapshot) for existing components. Auto-invoke when user says "test this component", "write component test", or "add component test"./nav-briefRender a one-screen intent brief (Goal/Scope/Approach/Limits/Verify/Won't-do) before implementing ambiguous task-shaped prompts, triggered by the nav_brief.py UserPromptSubmit hook. Confirms scope with max 2 open questions before touching files; detects brief drift mid-task.
Show all 31 skillsShow fewer
/nav-compactClear conversation context while preserving knowledge via context marker. Use when user says "clear context", "start fresh", "done with this task", or when approaching token limits./nav-diagnoseDetect quality drops in AI output and prompt re-anchoring. Auto-triggers after repeated corrections, context confusion, or when user says "something seems off", "you're not getting this"./nav-featuresShow and toggle Navigator features. Auto-invoke when user says "show features", "enable/disable feature", "my navigator settings", or "configure navigator"./nav-graphQuery project knowledge graph. Search across tasks, SOPs, memories, and concepts. Use when user asks "what do we know about X?", "show everything related to X", or "remember this pattern/pitfall/decision"./nav-initInitialize Navigator documentation structure in a project. Auto-invokes when user says "Initialize Navigator", "Set up Navigator", "Create Navigator structure", or "Bootstrap Navigator"./nav-install-multi-claudeDEPRECATED. The multi-Claude orchestration scripts are deprecated in favor of native Claude Code Workflows; no installation is needed. Auto-invokes on "install multi-Claude workflows", "set up multi-Claude", "enable parallel execution" to explain the deprecation./nav-loopRun tasks until complete with structured completion signals. Auto-invoke when user says "run until done", "keep going until complete", "iterate until finished", "loop mode", "autonomous mode"./nav-markerCreate context save points to preserve conversation state before breaks, risky changes, or compaction. Use when user says "save my progress", "create checkpoint", "mark this point", or before clearing context./nav-multiDEPRECATED. Multi-Claude shell orchestration is superseded by native Claude Code Workflows. Auto-invokes on "run multi-agent workflow", "parallel agents for", "multi-claude for", "spawn agents for" to redirect the user to the native Workflow and Agent tools./nav-onboardInteractive onboarding for Navigator - learn by doing. Auto-invoke when user says "onboard me", "teach me Navigator", "how do I use Navigator", "Navigator tutorial", "learn Navigator", "new to Navigator", or "what skills should I use"./nav-pilotDispatch a Navigator task doc to Pilot as a labeled GitHub issue. Use when user says "dispatch TASK-XX to Pilot", "hand off to Pilot", "send to Pilot", or "queue for Pilot". One-way handoff (Navigator authors the spec, Pilot executes autonomously)./nav-profileManage user preferences and corrections for bilateral modeling. Auto-learns from session corrections. Use when user says "save my preferences", "remember I like...", or auto-triggers after corrections./nav-releaseValidate and release Navigator plugin to marketplace. Auto-invoke when user says "release plugin", "publish navigator", "create release", or "deploy new version"./nav-simplifySimplify and refine code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code. Auto-invoke after implementation skills or on-demand./nav-skill-creatorAnalyze codebase patterns and create custom skills for repetitive workflows. Use when project needs automation or pattern enforcement. Auto-invoke when user says "create a skill for...", "automate this workflow", or "we keep doing X manually"./nav-sopCreate Standard Operating Procedures after solving novel issues, establishing patterns, or documenting workflows. Use when user says "document this solution", "save this for next time", "create SOP"./nav-startLoad Navigator documentation navigator when starting development session, resuming work, or beginning new feature. Use when user mentions starting work, beginning session, resuming after break, or checking project status./nav-statsDisplay session efficiency report showing token savings, cache performance, and optimization recommendations. Use when user asks "show my stats", "how efficient am I?", "show session metrics", or wants to see Navigator's impact./nav-sync-claudeSync project CLAUDE.md to the installed Navigator version, preserving customizations. Use when user says "sync CLAUDE.md", "update CLAUDE.md", or when detecting outdated Navigator configuration./nav-taskManage Navigator task documentation - create implementation plans, archive completed tasks, update task index. Use when user starts new feature, completes work, or says "document this feature"./nav-upgradeAutomates Navigator plugin updates. Detects current version, updates plugin, verifies installation, updates project CLAUDE.md, and validates new features. Auto-invoke when user mentions upgrading Navigator or getting new features./nav-workflowUnified workflow orchestration for substantial tasks. Auto-detects complexity, defers to matching skills, or provides phase-based execution. Solves workflow conflicts between skills, loop mode, and CLAUDE.md./plugin-slash-commandGenerate new Navigator slash commands following project conventions. Use when user says "add slash command", "create command", "new /nav command", or "add /nav:[name] command"./product-designAutomates design review, token extraction, component mapping, and implementation planning. Reduces design handoff from 6-10 hours to 5 minutes via direct Figma MCP integration. Auto-invoke when user mentions design review, Figma mockup, or design handoff./visual-regressionSetup visual regression testing with Storybook stories, configuration, and CI/CD workflows. Supports Chromatic, Percy, BackstopJS. Auto-invoke when user says "set up visual regression", "add Chromatic tests", "add screenshot testing", or "set up Percy".
Agents
2navigator-researchSpecialized codebase exploration and architecture discovery. Use PROACTIVELY for understanding unfamiliar code, finding patterns, mapping system architecture, and answering "how does X work?" questions. Use the generic Explore agent for one-off lookups; use me for architecturetask-plannerImplementation planning and task breakdown specialist. Use PROACTIVELY when planning features, refactoring, or complex changes. Creates detailed implementation plans with effort estimates.
Hooks
16nav_brief.pyHook script.nav_post_compact.pyHook script.nav_pre_compact.pyHook script.nav_profile_sync.pyHook script.nav_read_guard.pyHook script.nav_session_start.pyHook script.
Show all 16 hooksShow fewer
nav_task_graph_sync.pyHook script.nav_workflow_state.pyHook script.test_compact_roundtrip.pyHook script.test_hooks_smoke.pyHook script.test_nav_brief.pyHook script.test_nav_pre_compact.pyHook script.test_nav_read_guard.pyHook script.test_nav_session_start.pyHook script.test_workflow_enforcer.pyHook script.workflow_enforcer.pyHook script.
README
1Navigator
Finish What You Start
Sessions that last. AI that learns. Features that ship.
What is Navigator?
Navigator is a Claude Code plugin that implements context engineering for AI-assisted development.
Instead of loading all your documentation upfront (and crashing at exchange 7), Navigator loads what you need, when you need it—keeping 94% of your context window available for actual work.
For developers using Claude Code who want sessions that finish features instead of crash mid-way.
The Loop You're Stuck In
You know the pattern:
Exchange 5: Claude forgets your recent changes
Exchange 7: Hallucinations start ("that function doesn't exist")
Exchange 8: "Context limit reached"
Restart. Reload. Re-explain everything. Repeat.
You loaded 150k tokens of documentation "just in case."
You used 8k.
The rest? Noise drowning out signal.
Break The Loop
Navigator implements context engineering—load what you need, when you need it.
| Metric | Without Navigator | With Navigator |
|---|---|---|
| Tokens loaded | 150,000 | 12,000 |
| Session length | 5-7 exchanges | 20+ exchanges |
| Context at end | 95% (crashed) | 35% (comfortable) |
| Token savings | — | 92% |
Result: Sessions that actually finish what they start.
And Your AI Gets Smarter
Navigator v5.0 adds Theory of Mind—Claude learns you.
nav-profile: Remembers your preferences across sessions
"Remember I prefer concise explanations"
→ Applied in future sessions
→ Auto-learns from corrections
nav-diagnose: Catches collaboration drift
Same correction twice → Quality check triggered
"You're not getting this" → Re-anchoring prompt
Loop Mode (v5.1): Run until done
"Run until done: add user authentication"
→ Structured completion with progress tracking
→ Dual-condition exit (heuristics + explicit signal)
→ Stagnation detection prevents infinite loops
Knowledge Graph (v6.0): Project memory that persists
"What do we know about auth?"
→ Unified search across tasks, SOPs, system docs
→ Experiential memory: patterns, pitfalls, decisions
→ Auto-surfaces relevant context on session start
Same Workflows. More Capabilities.
Navigator is a superset. Everything you'd expect, plus context engineering.
| Feature | Navigator | Others |
|---|---|---|
| Structured workflows | ✅ Full skill suite | ✅ |
| Component generation | ✅ | ✅ |
| Test generation | ✅ | ✅ |
| Session longevity | 20+ exchanges | 5-7 exchanges |
| Token savings | 92% verified | None |
| Code simplification | ✅ | ❌ |
| Task Mode | ✅ | ❌ |
| Theory of Mind | ✅ | ❌ |
| Knowledge Graph | ✅ | ❌ |
| Loop mode | ✅ | ❌ |
| OpenTelemetry metrics | ✅ | ❌ |
| Figma MCP integration | ✅ | ❌ |
Same foundation. Superior context management.
Proof, Not Promises
Not estimates. Verified via OpenTelemetry.
╔══════════════════════════════════════════════════════╗
║ NAVIGATOR EFFICIENCY REPORT ║
╚══════════════════════════════════════════════════════╝
📊 TOKEN USAGE
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Your project documentation: 150,000 tokens
Loaded this session: 12,000 tokens
Tokens saved: 138,000 tokens (92% ↓)
📈 SESSION METRICS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Context usage: 35% (excellent)
Efficiency score: 94/100 (excellent)
Check yours: Run /nav:stats after installing.
Quick Start
Install
# Claude Code plugin marketplace
/plugin marketplace add alekspetrov/navigator
/plugin install navigator
# Restart Claude Code
Initialize
"Initialize Navigator in this project"
Start Every Session
"Start my Navigator session"
That's it. Navigator handles the rest.
What You Get
Skills that auto-invoke on natural language:
"Start my Navigator session" → Session with 92% savings
"Create a React component for profile" → Component + tests + styles
"Add an API endpoint for posts" → Endpoint + validation + tests
"Create context marker: checkpoint" → 97% context compression
"Run until done: add dark mode" → Loop mode completion
No commands to memorize. Skills detect intent and execute.
Stop Restarting. Start Shipping.
Your sessions crash because context management is broken by default.
Navigator fixes this with context engineering—the same principles Anthropic recommends.
92% token savings. 20+ exchange sessions. Verified metrics.
/plugin marketplace add alekspetrov/navigator
/plugin install navigator
Finish what you start.
Troubleshooting
Skill loads but prints docs instead of executing
/plugin update navigator
Then retry. Outdated plugin version.
Links
License
MIT License - See LICENSE
File tree
524alekspetrov/navigatorView on GitHub
.agent/
.nav-config.json
design-system/
figma-mcp-integration-report.md
implementation-summary.md
mcp-sdk-summary.md
DEVELOPMENT-README.md
examples/
5-MIN-DESIGN-REVIEW.md
FEATURE-IN-3-STEPS.md
ZERO-CONTEXT-RESTART.md
grafana/
dashboard-screenshot.jpg
docker-compose.yml
grafana-dashboards.yml
grafana-datasource.yml
navigator-dashboard.json
prometheus.yml
README.md
knowledge/
concepts/
.gitkeep
graph.json
memories/
decisions/
.gitkeep
mem-002.md
mem-007.md
mem-023.md
mem-025.md
mem-039.md
mem-040.md
mem-041.md
mem-042.md
mem-043.md
resolved/
mem-038.md
mem-044.md
mem-045.md
mem-046.md
mem-047.md
mem-048.md
mem-049.md
learnings/
.gitkeep
mem-008.md
mem-010.md
mem-029.md
mem-031.md
patterns/
.gitkeep
mem-006.md
mem-017.md
mem-021.md
mem-022.md
mem-024.md
mem-026.md
mem-027.md
mem-028.md
mem-030.md
pitfalls/
.gitkeep
mem-001.md
mem-003.md
mem-004.md
mem-005.md
mem-009.md
mem-011.md
mem-012.md
mem-013.md
mem-014.md
mem-015.md
mem-016.md
mem-018.md
mem-019.md
mem-020.md
mem-032.md
mem-033.md
mem-034.md
mem-035.md
mem-036.md
mem-037.md
learning/
CONTEXT-BUDGETS.md
examples/
TRY-THIS-AGENT-SEARCH.md
TRY-THIS-LAZY-LOADING.md
TRY-THIS-MARKERS.md
frameworks/
AGENT-VS-MANUAL.md
PREPROCESSING-DECISION-TREE.md
WHEN-TO-COMPACT.md
PREPROCESSING-VS-LLM.md
PROGRESSIVE-REFINEMENT.md
TOKEN-OPTIMIZATION.md
markers/
2025-01-20-grafana-dashboard-fixes.md
onboarding/
.completed
.progress-data.json
MY-WORKFLOW.md
PROGRESS.md
philosophy/
ANTI-PATTERNS.md
CONTEXT-EFFICIENCY.md
NEXTJS-PATTERNS.md
PATTERNS.md
sops/
debugging/
.gitkeep
grafana-dashboard-empty-data.md
knowledge-graph-memory-corruption.md
test-failures.md
deployment/
.gitkeep
plugin-release.md
development/
.gitkeep
autonomous-completion.md
multi-claude-orchestration.md
multi-claude-troubleshooting.md
release-workflow.md
integrations/
.gitkeep
opentelemetry-setup.md
pilot-handoff.md
testing/
visual-regression-setup.md
system/
plugin-patterns.md
project-architecture.md
tasks/
.gitkeep
archive/
TASK-01-session-start-pm-integration.md
TASK-02-readme-markers-v1.4.0.md
TASK-03-markers-management-auto-resume.md
TASK-04-version-sync-release-process.md
TASK-05-autonomous-completion.md
TASK-06-session-statistics.md
TASK-07-skills-migration.md
TASK-08-skills-enhancements-v2.1.md
TASK-09-migration-system.md
TASK-10-project-skills-v2.2.md
TASK-11-project-skills-generation-v2.3.md
TASK-12-v3.0-skills-only.md
TASK-13-otel-session-statistics.md
TASK-14-claude-md-updater.md
TASK-14-documentation-consolidation.md
TASK-16-product-design-skill.md
TASK-17-visual-regression-skill.md
TASK-18-CORRECTIONS.md
TASK-18-PITCH.md
TASK-18-principle-to-product-v3.5.md
TASK-18-README.md
TASK-18-VERIFICATION.md
TASK-18-VISUAL-SUMMARY.md
TASK-19-multi-claude-agentic-workflow.md
TASK-19-multi-claude-workflow-learnings.md
task-22-simple-console-logger-1761948433-plan.md
task-22-simple-console-logger-1761948433-review-report.md
TASK-22-simple-console-logger.md
TASK-26-plugin-optimization-roadmap.md
TASK-27-interactive-onboarding.md
TASK-29-tom-v5-release.md
TASK-30-task-verification-enhancement.md
TASK-31-code-simplification-integration.md
TASK-32-auto-update-project-sync.md
TASK-33-workflow-enforcement.md
TASK-34-evaluate-native-task-integration.md
TASK-36-multi-agent-production.md
TASK-38-hook-migration-roadmap-v6.11.md
TASK-40-phase-3-hook-migration-v6.12.md
TASK-41-hook-silent-fail-postmortem-v6.15.1.md
poc-1769186747-evaluation-report.md
poc-1769186747-plan.md
poc-1769187675-plan.md
poc-1769187675-review-report.md
poc-1769187675-tests.py
TASK-05-landing-page-content.md
TASK-13-web-documentation-site.md
TASK-15-marketing-community-adoption.md
TASK-25-fix-multi-claude-reliability.md
TASK-35-project-memory.md
TASK-37-nav-simplify-complexity-cost-scoring.md
TASK-39-nextjs-workshop-prep.md
TASK-42-audit-remediation-roadmap.md
TASK-43-ci-gate.md
TASK-44-version-tooling.md
TASK-45-hook-tests.md
TASK-46-hook-safety.md
TASK-47-kg-integrity.md
TASK-48-detection-precision.md
TASK-49-plugin-paths.md
TASK-50-skill-templates.md
TASK-51-python-misc.md
TASK-52-docs-config.md
TASK-53-claude-plugin-root-env-var.md
TASK-54-nav-pilot-dispatch-skill.md
TASK-55-landing-docs-site.md
TASK-56-nav-brief.md
TASK-57-v7-hook-channel-spike.md
TASK-58-harness-conformance-suite.md
TASK-59-nav-hook-lib.md
TASK-60-nav-dispatch-runtime.md
TASK-61-port-hooks-to-ops.md
TASK-62-v7-new-capabilities.md
TASK-63-v7-config-docs-migration.md
TASK-64-v7-release-gate.md
TASK-example.md
tickets/
TASK-18.1-philosophy-documentation.md
TASK-18.2-narrative-rewrite.md
TASK-18.3-metrics-enhancement.md
VIDEO-PRODUCTION-PLAN.md
.claude/
.claude-plugin/
marketplace.json
plugin.json
README.md
settings.json
skills/
test-marker.md
.github/
workflows/
release.yml
test.yml
.gitignore
agents/
navigator-research.md
task-planner.md
CHANGELOG.md
CLAUDE.md
CONTRIBUTING.md
docs/
ARCHITECTURE-DIAGRAMS.md
ARCHITECTURE.md
CONFIGURATION.md
DEPLOYMENT.md
GRAFANA-DASHBOARD.md
landing-page-draft.md
MIGRATION.md
PERFORMANCE.md
PITCH.md
QUICK-START.md
upgrades/
UPGRADE-GUIDE-v3.3.0.md
UPGRADE-v3.4.0.md
UPGRADE-v4.0.0.md
VERSION-CHECK.md
examples/
nextjs-saas/
.agent/
.nav-config.json
DEVELOPMENT-README.md
sops/
development/
adding-protected-routes.md
integrations/
stripe-webhooks.md
system/
project-architecture.md
tasks/
TASK-01-auth-setup.md
TASK-04-stripe-integration.md
.gitignore
CLAUDE.md
README.md
stack-choices.md
SUMMARY.md
version-note.md
hooks/
nav_brief.py
nav_post_compact.py
nav_pre_compact.py
nav_profile_sync.py
nav_read_guard.py
nav_session_start.py
nav_task_graph_sync.py
nav_workflow_state.py
test_compact_roundtrip.py
test_hooks_smoke.py
test_nav_brief.py
test_nav_pre_compact.py
test_nav_read_guard.py
test_nav_session_start.py
test_workflow_enforcer.py
workflow_enforcer.py
jest.config.js
Makefile
README.md
releases/
RELEASE-NOTES-v3.1.0.md
RELEASE-NOTES-v3.2.0.md
RELEASE-NOTES-v3.3.0.md
RELEASE-NOTES-v3.3.1.md
RELEASE-NOTES-v3.4.0.md
RELEASE-NOTES-v4.0.0.md
RELEASE-NOTES-v4.3.0.md
RELEASE-NOTES-v4.3.1.md
RELEASE-NOTES-v4.5.0.md
RELEASE-NOTES-v4.6.0.md
RELEASE-NOTES-v4.7.0.md
RELEASE-NOTES-v5.1.0.md
RELEASE-NOTES-v5.2.0.md
RELEASE-NOTES-v5.3.0.md
RELEASE-NOTES-v5.4.0.md
RELEASE-NOTES-v5.5.0.md
RELEASE-NOTES-v5.6.0.md
RELEASE-NOTES-v5.7.0.md
RELEASE-NOTES-v6.1.0.md
RELEASE-NOTES-v6.10.0.md
RELEASE-NOTES-v6.10.1.md
RELEASE-NOTES-v6.10.2.md
RELEASE-NOTES-v6.10.3.md
RELEASE-NOTES-v6.11.0.md
RELEASE-NOTES-v6.11.1.md
RELEASE-NOTES-v6.11.2.md
RELEASE-NOTES-v6.12.0.md
RELEASE-NOTES-v6.12.1.md
RELEASE-NOTES-v6.13.0.md
RELEASE-NOTES-v6.14.0.md
RELEASE-NOTES-v6.15.0.md
RELEASE-NOTES-v6.15.1.md
RELEASE-NOTES-v6.15.2.md
RELEASE-NOTES-v6.15.3.md
RELEASE-NOTES-v6.15.4.md
RELEASE-NOTES-v6.15.5.md
RELEASE-NOTES-v6.15.6.md
RELEASE-NOTES-v6.15.7.md
RELEASE-NOTES-v6.16.0.md
RELEASE-NOTES-v6.17.0.md
RELEASE-NOTES-v6.17.1.md
RELEASE-NOTES-v6.18.0.md
RELEASE-NOTES-v6.18.1.md
RELEASE-NOTES-v6.3.0.md
RELEASE-NOTES-v6.4.0.md
RELEASE-NOTES-v6.5.0.md
RELEASE-NOTES-v6.6.0.md
RELEASE-NOTES-v6.7.0.md
RELEASE-NOTES-v6.8.0.md
RELEASE-NOTES-v6.9.0.md
UPDATE-NOTES-v4.7.0.md
UPDATE-NOTES-v5.0.0.md
scripts/
bump-version.sh
check-version.sh
install-multi-claude.sh
migrate-config.sh
multi-claude-dashboard.sh
navigator-multi-claude-poc.sh
navigator-multi-claude.sh
POC-LEARNINGS.md
post-install.sh
resume-workflow.sh
session-stats.sh
simple-poc.sh
sub-claude-monitor.sh
test-json.sh
SECURITY.md
skills/
skills-local/
social-media-post/
functions/
post_analyzer.py
SKILL.md
backend-endpoint/
examples/
users-get.ts
users-post.ts
functions/
endpoint_generator.py
route_validator.py
validation_generator.py
SKILL.md
templates/
endpoint-test-template.spec.ts
express-route-template.ts
nextjs-route-dynamic-template.ts
nextjs-route-template.ts
backend-test/
SKILL.md
database-migration/
SKILL.md
frontend-component/
examples/
Button.tsx
SearchBar.tsx
functions/
component_generator.py
file_generator.py
name_validator.py
props_interface_generator.py
style_generator.py
SKILL.md
templates/
component-simple-template.tsx
nextjs-client-component-template.tsx
nextjs-layout-template.tsx
nextjs-page-template.tsx
... 260 moreFAQ
navigator is a Claude Code plugin with 31 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes backend-endpoint, backend-test, database-migration. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is navigator?
- Finish What You Start Sessions that last. AI that learns. Features that ship.
- How do I install navigator?
- Run these in Claude Code: npx -y skills add alekspetrov/navigator --agent claude-code. Then prompt normally.
- Does navigator auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is navigator free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.