By incubyte
Guides AI-assisted development through a spec-driven TDD workflow: triage, spec writing, architecture evaluation, TDD planning, ping-pong test-code cycles, browser verification, and code review. Includes codebase analysis, dependency analysis, git hotspot detection, and design discovery.
Architectural health assessment grounded in domain language. Compares how a product describes itself against how the code is structured.
Start a brainstorming session. Open-ended, collaborative idea generation for product, architecture, UX, or any problem space. Researches online, builds on your ideas, and helps narrow to the best path forward.
Run browser-based regression tests against specs. Verifies acceptance criteria in a running app via Chrome MCP, produces pass/fail reports with screenshots. Read-only — does not modify code.
Analyze your development sessions and get actionable coaching insights
Start a discovery session. A PM persona that interviews you (or synthesizes from transcripts) and produces a client-shareable PRD. Use standalone or let /bee invoke it automatically.
**IMPORTANT — Deferred Tool Loading:** Before calling `AskUserQuestion`, you MUST first call `ToolSearch` with query `"select:AskUserQuestion"` to load it. It is a deferred tool and will fail if called without loading first. Do this once at the start of your work.
**IMPORTANT — Deferred Tool Loading:** Before calling `AskUserQuestion`, you MUST first call `ToolSearch` with query `"select:AskUserQuestion"` to load it. It is a deferred tool and will fail if called without loading first. Do this once at the start of your work.
You are an architecture test generator. You turn architecture assessment findings into runnable boundary tests that document good structure and expose where architecture leaks from the domain model.
**IMPORTANT — Deferred Tool Loading:** Before calling `AskUserQuestion`, you MUST first call `ToolSearch` with query `"select:AskUserQuestion"` to load it. It is a deferred tool and will fail if called without loading first. Do this once at the start of your work.
You are a codebase analyst. Quick and efficient.
This skill should be used when evaluating how well code supports LLM-assisted development. Contains context window friendliness, explicitness, module boundaries, test-as-spec, and naming criteria.
This skill should be used when explaining why Bee follows spec-first TDD workflows, or when teaching mode is on. Contains the reasoning behind spec → plan → test → code ordering.
This skill should be used when evaluating architecture options, checking dependency direction, or deciding between onion, MVC, and simple patterns. Contains YAGNI-based decision criteria.
This skill should be used when updating workflow state in bee-state.local.md. Contains the full command reference for update-bee-state.sh including init, set, get, clear, all flags, and multi-line field syntax.
This skill should be used after discovery completes on a greenfield project when the discovery document contains a Module Structure section. Contains the full procedure for parsing module boundaries, generating BOUNDARIES.md, and optionally linking it from CLAUDE.md.
Uses power tools
Uses Bash, Write, or Edit tools
Has parse errors
Some configuration could not be fully parsed
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A collection of Claude Code plugins by Incubyte.
Spec-driven development that scales process to match the task. Triages by size and risk, then navigates you through the right workflow: triage, context gathering, spec, architecture, code, test, verify, review.
@bee inline annotationsEntry point: /bee:sdd
Learn any technology by building real projects. Claude guides you step-by-step — you write every line of code yourself.
Entry point: /learn:start
Builds a compounding wiki from raw documents. Drop articles into clippings/, ingest them into an Obsidian-compatible wiki with cross-references, then query your knowledge base with synthesized answers and citations.
[[wikilinks]] and YAML frontmatterEntry point: /second-brain:ingest
Take a raw product idea through ten guided phases and walk away with a structured PRD. Pushes back on vague metrics, refuses to write PRDs for ideas that should die.
discovery-state.mdEntry point: /discovery:start
Auto-detects the active issue-tracker MCP (Azure DevOps, Jira) and exposes an abstract verb surface (getIssue, addComment, transition, linkIssue, ...). Declared as a dependency by incident-postmortem and issue-triage; Claude Code auto-installs it when you install either verb-plugin. Ships no MCP, no agent, no slash command — it's a library.
.claude/tracker-policy.json; lazy-prompts for missing keys and offers to persist the answerEntry point: pulled in transitively by the verb-plugins; no direct user invocation.
Paste an incident URL (Azure DevOps or Jira) and the agent gathers evidence from chat (Slack/Teams), the tracker, Datadog logs, and merged pull requests; reconstructs a chronological timeline with evidence tags; pauses for review; then writes a Google-SRE-style blameless postmortem.
incident-timeline-builder, postmortem-writer/incident-postmortem:run <URL or ID>Auto-installs issuekit.
Entry point: /incident-postmortem:run <URL or ID>
Paste any issue URL (Azure DevOps or Jira; Bug, Incident, Story, Feature, Task, or Spike) and the agent triages it end-to-end: assigns to you, transitions to investigating, runs the matching investigation skill, refines title and description, posts an assessment comment, sets severity + due date or sprint + story points, links related work, applies the triaged label, and posts a summary to the configured chat channel.
issue-refiner, requirements-investigator (uses issuekit:issue-investigator for Bug/Incident)/issue-triage:run <URL or ID> — full workflow/issue-triage:investigate-and-refine <URL or ID> — lightweight subset (no severity, transitions, sprints, comments, labels, or escalation)Auto-installs issuekit.
Entry point: /issue-triage:run <URL or ID>
Add the marketplace once, then install the plugins you want:
/plugin marketplace add incubyte/ai-plugins
/plugin install bee@incubyte-plugins
/plugin install learn@incubyte-plugins
/plugin install discovery@incubyte-plugins
/plugin install incident-postmortem@incubyte-plugins
/plugin install issue-triage@incubyte-plugins
Learn any technology by building real projects. Claude guides you step-by-step — you write every line of code yourself.
End-to-end incident postmortem generator. Paste an incident issue URL (Azure DevOps or Jira) and the agent gathers evidence from chat (Slack/Teams), the tracker (related issues, history), Datadog logs, and merged pull requests; reconstructs a chronological timeline with evidence tags; and writes a Google-SRE-style blameless postmortem (summary, impact, timeline, root cause, contributing factors, what went well/wrong, action items, lessons learned). Tracker-agnostic via issuekit. Bundles incident-timeline-builder and postmortem-writer skills.
Shared adapter layer for issue-tracker plugins. Auto-detects the active MCP (Azure DevOps, Jira), exposes an abstract verb surface (getIssue, addComment, transition, linkIssue, ...), converts markdown bodies to the target format (HTML for Azure DevOps, ADF/markdown for Jira), and reads policy from .claude/tracker-policy.json. No MCP bundled, no agent, no slash command. Required by incident-postmortem and issue-triage.
CCAF (Claude Certified Architect – Foundations) mock-exam readiness gate. Assembles a 60-question case-study-framed mock with machine-enforced domain weighting — every question generated fresh per attempt and independently verified — administers it 4 per screen with resumable progress, and scores it on the real 100–1000 band with a 720 pass line plus a per-domain breakdown. Run /ccaf:mock-exam.
End-to-end product discovery flow that produces a structured PRD.
npx claudepluginhub incubyte/ai-plugins --plugin beeVirtual development team: TDD, debugging, code review, backlog management, and proven workflow patterns
Document Driven Development — a structured workflow for AI-assisted software development with TDD, specs, and cross-review
Persona-driven AI development team: orchestrator, team agents, review agents, skills, slash commands, and advisory hooks for Claude Code
Unified toolkit for Context-Driven Development with spec-first planning, TDD workflow, and Beads integration
A Claude Code plugin for structured, context-efficient software development.
VGV Wingspan - AI-native workflows following Very Good Ventures best practices.