| What it does | Ontological knowledge graph that surfaces specification gaps, test coverage gaps, and unaddressed architecture standards before code ships
| AI skill manager that keeps your skills together across tools
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| US
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free CLI (MIT + Commons Clause licence, free for own projects including commercial software). Bootstrap Kit $149 one-time per repository (includes 12 months updates, unlimited team members, web visualiser, AI audit commands, architecture standards YAML, Docker setup, and Claude + Kimi Code CLI skill
| Free: £0/month with core features. Individual: £6.99/month (one person, 7-day trial). Team: £12.99/member/month (billed per active member).
|
|---|
| Key features | - Reduced AI orientation tokens (71% fewer on Formbricks codebase)
- Requirements traceability from user stories through use cases to features to tests
- Automated requirement quality checks using 13 QUS criteria and 6 traceability rules without AI API key
- V-model 4-tier test coverage mapping (component, integration, use case flow, end-to-end)
- AI test quality audit across 7 AS-TEST dimensions
- Code scanning for Go, TypeScript, Python, Java, C# with automatic symbol and test linking
- Web visualiser with drill-down graph navigation and entity editor
- Parallel session coordination with in-progress marking
- Docker Compose setup with one-command initialization
| - Unified library for importing and organizing skills from multiple sources
- Source tracking to monitor when skills change and decide whether to update
- Security review with Cisco Skill Scanner for prompt injection, exfiltration, and obfuscated code
- Selective skill delivery to specific projects and tools
- Skill capture to turn successful workflows into reusable skills
- Skillbox Trim to reduce command output noise from agent context
- Skillbox AI to draft and review skills with assistance
- Shared workspaces for team collaboration without forcing skills on individuals
- Team standards to require specific skills for workspace consistency
- Weekly workspace usage reports for team admins
|
|---|
| What makes it different | - Maps what a system is supposed to do and whether it's verified, not just what code contains or what chats remember
- Surfaces specification gaps that code review cannot detect because the requirement was never written down
- Session start in 30 seconds with three commands replacing ten minutes of manual code reading
- Eliminates duplicate implementations across 12 parallel AI sessions with one shared ontology
- Bootstrap kit ROI in 5 days at 10 sessions/day through orientation token savings
| - Library remains separate from active setup, delivering only relevant skills to each tool or project
- Source attachment remembers GitHub or GitLab origin so you can compare versions before updating
- Security findings and approvals tied to exact version reviewed, not carried forward automatically
- Shared team skills do not override individual personal libraries
- Works with existing tools without requiring abandonment of Cursor, Claude Code or repositories
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 4 ▲ +4 (up) since last check | 2 ▲ +2 (up) since last check |
|---|
| Trust Flow (Majestic) | 3 | 0 |
|---|
| Citation Flow (Majestic) | 19 | 0 |
|---|
| Referring domains (Majestic) | 33 | 0 |
|---|
SysEdge
Skillbox