Claude Skills by hybridlabor-api

Turn the current project website into a short, polished, shareable launch video using Hyperframes. Post-shipping release hook. Use when someone says "/brag", "make a launch video", or wants to showcase what they shipped.

Use when an error occurs (deja fix), when resuming work in a project (deja wip), or when past sessions in this repo matter (deja search). Local, redacted session memory, installed together with memB.

Create and render fixed-canvas editable visual designs, including posters, marketing graphics, covers, menus, banners, and social cards. Default outputs include fixed and editable HTML, PNG, a mouse editor with scan and exploded layer views, and an evidence-backed Design Replay. Do not use for websites, slide decks, videos, or standalone logo systems. Always use this skill when the project contains `poster.json`.

Delegate a task to another installed CLI harness (Antigravity/agy, OpenCode, Codex) from inside an AOS repo. Use this instead of shelling out to that CLI directly whenever one is installed — it wraps the wrapper flags for you and streams live tool-call telemetry to agenttrail, which is why the board updates in real time. Reach for it any time you're about to delegate work to another harness.

Configure and synchronize multi-harness subagents (Claude Code, Google Antigravity, OpenCode, ChatGPT Codex CLI) with canonical model tiers and single source of truth in .aos/pipeline.json.

Brainstorm a topic with the matching skill: bdbrainstorm, bdbmediastorm for event tech, grill-me for a stress test. Generated from plugin-commands.json; invoke as $bdb-aos:brainstorm.

Check the machine and the current project, and print suggested permissions.allow entries without writing any settings. Generated from plugin-commands.json; invoke as $bdb-aos:doctor.

Run the startcycle-graph pipeline: durable state, repair loop, quality gate, escalation. Generated from plugin-commands.json; invoke as $bdb-aos:graph.

Set up the current project folder for AOS: slug, wiki, memory, Synapse map, AGENTS.md. Generated from plugin-commands.json; invoke as $bdb-aos:init.

Run a prompt repeatedly on an interval, using the harness built-in plus loop templates. Generated from plugin-commands.json; invoke as $bdb-aos:loop.

Supervise other Claude Code sessions on this machine: roster, status requests, GO board, idle notices. Generated from plugin-commands.json; invoke as $bdb-aos:mastersession.

Query or store long-term memory with memB. Generated from plugin-commands.json; invoke as $bdb-aos:memb.

Coordinate parallel coding agents across repositories through the AO daemon. Generated from plugin-commands.json; invoke as $bdb-aos:orchestrator.

Plan end to end: draft, render in plan-canvas or Plan Builder, annotate, await approval, then hand off. Generated from plugin-commands.json; invoke as $bdb-aos:plan.

List all pb-* playbooks with duration, difficulty and requirements, and start one. Generated from plugin-commands.json; invoke as $bdb-aos:playbooks.

Bring this machine to a complete, verified AOS installation (skills, MCP servers, gate hooks, memB, OpenWiki, Synapse). Generated from plugin-commands.json; invoke as $bdb-aos:setup.

Pre-ship framing and the technical release gate, with approvals under the go-gate rules. Generated from plugin-commands.json; invoke as $bdb-aos:shipping.

Start a new composition: project init, brainstorm, then ask whether graph or startcycle follows. Generated from plugin-commands.json; invoke as $bdb-aos:startproject.

Browse and preview AOS skills, agents and playbooks in the local store UI. Generated from plugin-commands.json; invoke as $bdb-aos:store.

Use for event agency operations: client intake, project scoping, vendor management, crew coordination, production planning, pre-show logistics, and post-show wrap. Delegates technical execution to godmode-eventtech and bdbmediastorm.

Use before starting any significant build or before shipping: problem-framing pre-flight, one-way/two-way door classification, ADR-lite decision logging, and post-ship outcome loop. Complements godmode-shipping (technical gate) and bdbresilience (error recovery).

Use when one Claude Code session must supervise several others on this machine — adopting sessions the user started by hand, or spawning workers itself. Covers roster, status requests, a GO board, idle notices, and the GO-token protocol. Works with AOS alone; the AO daemon is optional.

Entry point for the BDB Agent OS suite installed as a Claude Code plugin. Use to find out which of the 200+ AOS skills, the seven startcycle subagents, or the pipeline workflows apply to a task, and where their contracts live. Reach for a specific skill directly when you already know its name — this skill only routes.

Harness patterns for coding agents — memory, permissions, context engineering, delegation, skills, hooks, bootstrap.

Browse, preview, and install AOS Core, ECC and Scenario skills and agents from a local web UI. Use when exploring or adding new skills to a project.

Create, generate, write, or scaffold bash/shell scripts (.sh), automation, or CLI tools.

Validate, lint, audit, or fix bash/shell/.sh scripts via ShellCheck.

Use when `aos-plan-canvas await` returns an item with route "visual-edit", or the human points at an element in a running local dev app and wants the source edited. Finds the source with a deterministic search, posts a diff plan in the canvas, and edits one file only after a yes given in the canvas. Not for remote or production sites.

Set up a complete CI/CD pipeline for a project. Detects the stack, then generates and validates GitHub Actions workflows, a Dockerfile, and a Makefile as one coherent pipeline. Use when asked to "set up CI", "add pipeline", "create GitHub Actions", "ci/cd setup", "automate builds", "containerize", or "add a Makefile".

interview the user to design an agentic control loop (sensor, controller, actuator under disturbances) tailored to their codebase, then build it as locally-runnable components plus a scheduled coding-agent workflow

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Create, generate, or write Dockerfiles and multi-stage Docker images. Containerize apps.

Validate, lint, audit, or scan a Dockerfile for security and best practices.

Experimental workflow for collecting and triaging product feedback, product telemetry, runtime errors, and issue reports. Use when scanning configured signal sources and applying separate fix, reply, or close rules.

Experimental workflow for summarizing work that still needs human judgment across configured pull requests, issues, feedback, errors, and delivery signals. Use for a human decision queue or bounded review.

Experimental workflow for auditing recurring feedback, telemetry, errors, and brittle delivery paths to find systemic fixes. Use for periodic or requested cross-source lookbacks, not routine single-item intake.

Experimental workflow for reviewing configured repositories' pull requests. Use for manual or scheduled PR triage, approval, or merge decisions.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Create, generate, or scaffold GitHub Actions workflows, action.yml, or .github/workflows CI/CD pipelines.

Validate, lint, audit, fix GitHub Actions workflows (.github/workflows).

Show or explain the AOS go-gate mode (hard, soft, off) and the time-limited grants of this session. Use when the human runs /bdb-aos:gogate, asks why a git push, merge, publish or destructive command was blocked, or wants to know which grants are active. The agent only displays status and explains; only a plain `gogate ...` message typed by the human changes a mode or a grant.

Use when a task should repeat on a schedule or until a condition holds (CI until green, follow a PR to merge, review rounds until no blockers, daily session summary). Ships ready prompt templates with run and duration limits, stop conditions and go-gate safety rules, and per-harness loop invocation.

Create, generate, or scaffold Makefiles with .PHONY targets and build automation.

Validate, lint, audit, or check Makefiles and .mk files for errors.

Use when checking capabilities or instructing the user on how to interact with specialized MCP servers like Unreal, Rhino, DaVinci, or TouchDesigner.

Use when asked to compare, cross-review, merge, judge, choose, or arbitrate competing plans from multiple agents such as Codex and Claude Code; when given two or more proposed plans, session IDs, transcripts, plan documents, PR descriptions, or pasted strategies; or when the user wants one recommended execution plan after agents review each other's proposals.

Use when a PR or git range needs a visual recap page for a reviewer, with a changed-files tree, per-file notes, a Verified vs Not verified table, risks, and optional before/after images. Local and informational; never posts to GitHub.

Use when the user wants each agent response to end with a red/yellow/green status line showing whether the work is finished, pending a follow-up, or blocked on input.

Use when implementing, integrating, upgrading, debugging, or answering anything involving third-party APIs, libraries, frameworks, CLIs, cloud services, model or provider SDKs, fast-moving product behavior, unfamiliar repo docs or specs, errors that may indicate API drift, or high-stakes auth, security, billing, data, migration, deployment, compliance, or privacy behavior. Forces a docs pass before coding from memory.

Use when completing tasks, implementing major features, or before merging to verify work meets requirements