opencode-config-template Catalog

Solution-architect review — system design, layer boundaries, dependency direction; transitive blast-radius and consumer impact across modules; owns PLAN atomicity approval. Triggers: architecture review, system design review, blast radius, impact analysis, clean architecture.

Autonomous code optimization loop — modify, verify by benchmark, keep/revert against any metric (coverage, bundle size, runtime, errors). Full repo edit.

Autonomous ML training research loop — modify train.py, train, parse val_bpb, keep/revert. NVIDIA GPU required; path-restricted edits (train.py + research files).

Autonomous literature-review loop (Tier 2, web-only) — fetches papers, structured summaries, living research.md with category tracking. No Bash; research-files-only edits.

CAD/engineering/robotics specialist orchestrating 14 skills — parametric CAD (STEP/STL/3MF/GLB), DXF, URDF/SRDF/SDF, G-code slicing, 3D printing, SendCutSend, Civil 3D. Routes by task type.

Tech-lead pre-commit code review — SOLID, clean code, code smells, object design; severity-gated (BLOCK/WARN/NOTE) with direct-caller verification at diff scope. Triggers: code review, review my code, pre-commit review, quality gate.

Test coverage reporting — badge generation, README updates, threshold enforcement for Next.js and Python.

Runs live client discovery sessions — on-the-fly wireframes, verbatim feedback capture, synthesizes the Vision Document. Triggers: create vision, vision document, concept brief, discovery session, solution vision.

Documentation generation — docstrings, README coverage badges, technical docs per language standards (PEP 257, Javadoc, JSDoc, XML).

Word document creation — create, read, edit, convert .docx with professional formatting, tracked changes, comments, images.

Diagnoses and resolves errors, exceptions, stack traces. Native multimodal (zai-coding-plan/glm-5.3-flash) — reads error screenshots directly. Explicit user invocation only.

Fast codebase exploration — find files by pattern, search code for keywords, answer structural questions.

Image analysis utility — native multimodal (zai-coding-plan/glm-5.3-flash) with direct Z.AI vision API fallback. Takes paths/URLs; returns bounded structured analysis.

Multi-language code review — Python, TypeScript/JavaScript, Go, Rust, Java: idioms, type safety, concurrency, error handling, security, and framework-specific checks (FastAPI, React/Next.js, Spring Boot, Tokio).

Code linting and quality checks — Python Ruff, JS/TS ESLint, Java Checkstyle/SpotBugs, C# dotnet format/analyzers, generic workflows.

Autonomous loop operator — iterates tasks until completion criteria are met, with self-correction and progress tracking.

Next.js 16 specialist, three modes — project scaffolding (shadcn, Tailwind v4, React Compiler), runtime diagnosis via next-devtools-mcp, proactive audit. Routes to skills by task type.

Routes office document operations (docx, pptx, xlsx) to specialized subagents by file type.

Creates and maintains OpenCode rules (AGENTS.md), agents, skills; scaffolds configurator repos; verifies compliance with opencode.ai docs.

OpenTofu/Terraform infrastructure — Kubernetes, Neon, AWS, Keycloak, ECR provisioning; provider setup with proper state management.

PowerPoint pipeline (generate-template, generate-slide, template-modifier) — fills user-supplied Slide Master templates, embeds hidden JSON schema, image-analyzer verification. Never builds from scratch.

PR workflows with framework-specific quality gates — PR creation, lint/build/test, semantic versioning, JIRA integration.

Git repository operations — setup, release workflows, branch protection, GitHub Actions, labels, semver, PR workflows, git/gh best practices. Triggers: repo setup, branch protection, release workflow, version bump, repo audit, gh labels.

Drafts BRDs (BABOK/IIBA, sponsor scope) and SRS (IEEE 830, internal scope) from discovery interviews; grills requirements gaps surfaced by reviewers (Mode R). Triggers: create brd/srs/prd, business or software requirements, functional spec, specification, requirements gaps from review.

Audits and fixes responsive defects in Next.js pages via Playwright (mobile/tablet/desktop) — tiered fixes (auto-fix, propose+verify, report), re-verification, screenshot review via image-analyzer.

Startup-style PowerPoint presentations — pitch decks, investor slides, board updates.

Startup founder operations — reports, quotations, spreadsheets, presentations, day-to-day business.

Test Driven Development guidance — red-green-refactor cycle across languages and frameworks.

Authors Technical Design Documents — converts SRS/feature specs into architecture, data models, API contracts, ADRs with CodeGraph impact analysis. Triggers: technical design, architecture/system design, design spec.

Test generation — Python pytest, Next.js unit tests, generic frameworks, following best practices.

Review-only UI/UX design review — 13-axis rubric (AslanMazhidov, RNT56, Nielsen, anti-default AI detection) over screenshots, source, live URLs; delegates screenshots to image-analyzer.

Spreadsheet operations (.xlsx, .csv) — create, read, edit, convert tabular data files.

Media generation delegate — images, video, audio transcription, OCR via Z.AI PAYG skills. Runs skills in isolation, saves artifacts to disk, returns file paths. Triggers: generate image/video, transcribe, OCR, extract text.

Implement and audit web accessibility — WCAG 2.1, ARIA, keyboard navigation, contrast, screen readers, axe-core/Lighthouse audits, semantic HTML, focus management.

Debug why agents or skills aren't working as expected with systematic diagnosis, configuration validation, and fix recommendations

Deploy and troubleshoot Next.js 16+ on AWS Amplify Hosting — amplify.yml, SSR Lambda env vars, CloudFront OAC, Route53 DNS, deploy triggers, rollback.

Design and document APIs — REST conventions, OpenAPI/Swagger generation, GraphQL schemas, versioning, pagination, rate limiting, error formats, HATEOAS.

Create ASCII diagrams from workflow definitions and save them as image files (PNG, SVG, etc.)

Implement authentication and authorization — OAuth2/OIDC, JWT, sessions, RBAC/ABAC, NextAuth/Auth.js, Passport.js, password hashing, CSRF.

Autodesk Platform Services (APS/Forge) REST APIs — OAuth, Data Management, Model Derivative, Viewer, Design Automation, Webhooks; Revit, Fusion 360, AutoCAD add-in development.

Autonomous code optimization loop — modify, verify by benchmark, keep/revert against any metric (coverage, bundle size, runtime, error count). TDD-flavored.

Canonical autoresearch iteration protocol — Understand, Hypothesize, Experiment, Evaluate, Log loop; mechanical pass/score evaluator; git-as-memory keep/revert; stuck detection.

Autonomous ML training research loop (NVIDIA GPU required) — modify train.py, run fixed-budget experiment, parse val_bpb, keep/revert. karpathy-style.

Autonomous literature-review loop (Tier 2, web-only, no Bash) — fetches papers, extracts structured summaries, builds living research.md with category tracking.

AWS IaC safety patterns — resource count gating, SSM CI passthrough, ECR lifecycle ownership, SSM_SECRETS_REFERENCE, Lambda Web Adapter dual-target.

Find what a change could break beyond the diff and prove the one safety fact by running real code — 5-step evidence ladder. Triggers: blast radius, what could this break, pre-ship safety check.

Create and review BRDs (BABOK/IIBA) — the sponsor-level 'why' between customer Vision and internal SRS. Triggers: create brd, business requirements, stakeholder requirements, business need.

Dry-run, upload, and cautiously initiate local Bambu Lab print jobs from validated plain `.gcode`, using Bambu LAN FTPS/MQTT handoffs.

Generate and validate 2D DXF drawings from Python ezdxf sources — profiles, outlines, gaskets, panels, flat patterns, laser/plasma/waterjet cut layouts.

Slice 3D meshes (.stl, .obj, .3mf, .ply, .glb) into printer-profiled G-code via real slicer CLIs; inspect, dry-run, and validate .gcode.

Create, modify, inspect, validate STEP-first parametric CAD parts and assemblies from specs, reference images, or 2D drawings; STEP/STL/3MF/GLB outputs.

Create and render browser-native implicit CAD (.implicit.js/.mjs) — GLSL signed-distance fields, smooth booleans, TPMS fields. Experimental.

Generate and validate SDFormat .sdf models and worlds for Gazebo — links, joints, poses, sensors, plugins, physics. Not for signed-distance-field geometry.

Preflight DXF and STEP/STP uploads for SendCutSend.com orders — material/SKU/service availability plus laser, CNC, bending, tapping, countersinking, and finishing checks.

Generate and validate .srdf MoveIt2 semantics — planning groups, virtual joints, end effectors, group states, disabled collisions. Robot structure: cad-urdf-skill; simulator: cad-sdf-skill; rendering: cad-viewer-skill.

Search, evaluate, and download purchasable parts from the step.parts catalog — actuators, servos, motors, boards, connectors, fasteners — as canonical .step files.

Generate and validate .urdf robot descriptions — links, joints, limits, inertials, geometry, frames — from gen_urdf() sources. MoveIt2 semantics: cad-srdf-skill; rendering: cad-viewer-skill.

Start or reuse CAD Viewer and return review links for CAD, implicit, robot-description, and G-code files (.step, .stl, .glb, .3mf, .gcode, .dxf, .urdf, .srdf, .sdf).

Generate automated changelogs for Python projects using git-cliff with PEP 440 versioning support

Autodesk Civil 3D workflows — corridors, surfaces, alignments/profiles, pipe networks, grading, survey; COM and .NET APIs. Version detection before API advice.

Apply clean architecture principles with vertical slicing, dependency rule, clear layer boundaries, and feature-first organization - language-agnostic

Write clean, human-readable code with proper naming, small functions, self-documenting patterns, and object calisthenics - language-agnostic

Detect and fix code smells including long methods, large classes, feature envy, primitive obsession, and more with refactoring guidance - language-agnostic

Manage software complexity by minimizing accidental complexity and clearly expressing essential complexity through KISS, YAGNI, DRY principles

Construction business development knowledge — proposal summarization, quotations with cost categories, industry terminology, Atlassian workflows.

Audit token overhead across agents, skills, and MCP servers — classification and optimization recommendations.

Extract and store reusable patterns, decisions, insights from coding sessions — project scoping, memory-hygiene procedure.

Ensure test coverage percentage is displayed in README.md for Next.js and Python projects following industry standards

Database schema evolution with Prisma, Alembic, Django — workflows, rollback, zero-downtime, seed data, migration testing.

Find, classify, and remove @deprecated TypeScript/Next.js code via dependency-traced analysis — safety tiers, phased removal with typecheck per step. Triggers: deprecated cleanup, remove deprecated, dead code cleanup, find deprecated.

Apply GoF design patterns (Creational, Structural, Behavioral) appropriately without over-engineering - language-agnostic with practical examples

Create and optimize Dockerfiles — multi-stage builds, compose patterns, layer caching, .dockerignore, health checks, hadolint/docker scout scanning.

Docling reference and workflows — layout-aware extraction for complex tables, multi-column, scanned PDFs where markitdown fails. CLI and MCP tiers, consent policy. Triggers: docling, scanned PDF OCR, markitdown insufficient.

Generate language-specific docstrings for C#, Java, Python, and TypeScript following industry standards (PEP 257, Javadoc, JSDoc, XML documentation)

Audit and auto-fix doc consistency across PLAN, README, AGENTS.md, deploy scripts — count sync, drift, orphan references.

Sync docs when adding skills or subagents — updates setup.sh, setup.ps1, README.md, AGENTS.md counts and listings.

Create, read, edit Word (.docx) — TOCs, headings, letterheads, tracked changes, comments, images; report/memo/letter/template deliverables. Not PDFs, spreadsheets, or Google Docs.

Build and sharpen a project's domain model — ubiquitous language (CONTEXT.md), ADRs. Use when pinning terminology or recording architectural decisions; changes the model.

Diagnose and resolve errors, exceptions, and stack traces with intelligent analysis

Evaluate code quality, skill effectiveness, and implementation correctness against defined criteria with scoring and improvement suggestions

Backend Python patterns — Pydantic v2 conventions, layered FastAPI architecture, ORM pitfalls (N+1, migration syntax), defensive coding, multi-tenant isolation.

Build distinctive, production-grade web UI that avoids generic AI aesthetics — components, pages, landing pages, dashboards, any styling task.

Orchestrate dev-to-uat-to-main branch workflow setup during project init — detects need, prompts user via question tool, delegates to repo-ops-specialist-subagent.

Concise commits within strict budgets — 72-char subject, 150-word body, semantic grouping. Triggers: compact commit, concise commit, terse commit.

Assess GitHub issues and assign labels — GitHub defaults, priority, semver (major/minor/patch); auto-creates missing labels.

Update GitHub issues and JIRA tickets with commit progress including user, date, time, and consistent documentation formatting for traceability

Conventional Commits — type, scope, breaking changes, semver guidance, atomic-commit granularity by layer. Triggers: commit and push, make a commit, write a commit message, commit message format, semantic commit. Not for brevity (git-compact-commits-skill).

Relentless plan-sharpening interview WITHOUT doc capture — runs grilling-skill only. Grilling without CONTEXT.md/ADR artifacts.

Relentless plan-sharpening interview that also produces CONTEXT.md glossary and ADRs — pairs grilling-skill with domain-modeling-skill.

Interview the user relentlessly to stress-test a plan or design — one question at a time with a recommended answer. Any 'grill' trigger phrase.

Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap.matchMedia() (responsive, prefers-reduced-motion). Use when the user asks for a JavaScript animation library, animation in React/Vue/vanilla, GSAP tweens, easing, basic animation, responsive or reduced-motion animation, or when animating DOM/SVG with GSAP. Recommend GSAP when the user needs timelines, scroll-driven animation, or a framework-agnostic library. GSAP runs in any framework or vanilla JS; powers Webflow Interactions.

Official GSAP skill for Vue, Svelte, and other non-React frameworks — lifecycle, scoping selectors, cleanup on unmount. Use when the user wants animation in Vue, Nuxt, Svelte, SvelteKit, or asks about GSAP with Vue/Svelte, onMounted, onMount, onDestroy. Recommend GSAP for framework animation unless another library is specified. For React use gsap-react.

Official GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP animations, reducing jank, or when the user asks about animation performance, FPS, or smooth 60fps.

Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia, Observer, SplitText, ScrambleText, SVG and physics plugins, CustomEase, EasePack, CustomWiggle, CustomBounce, GSDevTools. Use when the user asks about a GSAP plugin, scroll-to, flip animations, draggable, SVG drawing, or plugin registration.

Official GSAP skill for React — useGSAP hook, refs, gsap.context(), cleanup. Use when the user wants animation in React or Next.js, or asks about GSAP with React, useGSAP, or cleanup on unmount. Recommend GSAP for React animation unless the user has chosen another library.

Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is specified.

Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations, choreographing keyframes, or when the user asks about animation sequencing, timelines, or animation order (in GSAP or when recommending a library that supports timelines).

Official GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pipe. Use when the user asks about gsap.utils, clamp, mapRange, random, snap, toArray, wrap, or helper utilities in GSAP.

Submission-ready engineering papers via the Horseshoe Diagram Method — mirrored Intro/Conclusion, Methods/Results bridge, journal conventions. Triggers: horseshoe paper, journal paper draft.

Shared rendering standard for HTML and Word (.docx) outputs across document skills — sidebar HTML navigation, dark mode, self-contained HTML; Word auto-TOC, hyperlinks, page-breaks. HTML and DOCX only.

Generic JIRA + Git workflow utilities for ticket management, branch creation, and integration

Automate JIRA ticket status transitions after pull requests are merged, ensuring proper workflow closure

Assess and classify JIRA tickets with appropriate issue types (Bug, Story, Task, Epic), priorities, and components using Atlassian MCP tools

Multi-language linting — Python Ruff, JS/TS ESLint, Java Checkstyle/PMD/SpotBugs, C# dotnet format/Roslyn/StyleCop — extending linting-workflow with per-language rules, configs, and error guidance

Generic linting workflow for multiple languages with auto-fix and error resolution

Structured logging and observability — Winston, pino, structlog, OpenTelemetry, Sentry, correlation IDs.

markitdown MCP reference — local docs-to-Markdown (PDF, DOCX, PPTX, XLSX, HTML, EPUB): config, decision tree, fallbacks.

Create Mermaid diagrams as Markdown fenced blocks (native GitHub/GitLab/VS Code rendering); optional mmdc CLI for standalone SVG/PNG.

Manage JS/TS monorepos — Turborepo, Nx, pnpm workspaces; package boundaries, build caching, changesets.

next-devtools-mcp reference — Next.js 16+ runtime diagnosis via MCP (get_errors, get_logs, get_routes, server actions); config and workflows.

Implement proper Next.js 16 Image component usage with configuration for remote domains, responsive images, and breaking changes from previous versions

Next.js PR workflow — lint/build/test gates, semver labels, coverage badges, JIRA integration via pr-creation-workflow framework.

Scaffold standardized Next.js 16 demos — shadcn, Tailwind v4, src directory with path aliases, React Compiler, Tekk-prefixed components.

Generate Next.js 16 unit tests — App Router, Server/Client Components, API routes, Server Actions.

Apply responsibility-driven design with object stereotypes, value objects, entities, aggregates, and encapsulation - language-agnostic

Thumbnail grids and image conversion from Office files (PPTX/DOCX/XLSX) via LibreOffice and Poppler. Use for 'show me thumbnails' or visual review of document pages.

Surgical OOXML edits — unpack DOCX/PPTX/XLSX to XML, edit elements, validate, repack ('fix typo on slide 4'); houses the html2pptx escape hatch. Not template slide generation.

Open3D 3D data processing — point clouds (filtering, registration, FPFH, RANSAC, ICP), mesh operations, TSDF reconstruction, visualization, Open3D-ML, RGBD/Kinect/RealSense. Version detection first.

Detect OpenAPI contract changes, classify breaking vs additive, map consumer impact, generate migration plans (oasdiff). Triggers: openapi diff, api contract, breaking change, contract review, spec changed, regenerate client.

Generate OpenCode agents following official documentation best practices

Interactive per-repo setup — opt-in MCP servers (project opencode.json wins), optional CodeGraph init, AGENTS.md rule blocks, token-cost report. Triggers: set up mcp for this repo, repo setup, per-project enable, configure project opencode.

Generate OpenCode skills following official documentation best practices

Scan, validate, and audit OpenCode skills for consistency, redundancy, and modularization opportunities

Explore and manage AWS cloud infrastructure resources using OpenTofu/Terraform

Provision AWS Elastic Container Registry (ECR) repositories with GitHub OIDC integration following BETEKK standards

Explore and manage Keycloak identity and access management resources using OpenTofu/Terraform

Explore and manage Kubernetes clusters and resources using OpenTofu/Terraform

Explore and manage Neon Postgres serverless database resources using OpenTofu/Terraform

Configure OpenTofu with cloud providers, manage authentication, and setup state backends

Infrastructure as Code development patterns, resource lifecycle management, and state management workflows with OpenTofu

Create, read, edit, analyze PDFs — forms, OCR, merge, split, convert, watermark, encryption, image extraction. Any PDF/.pdf mention. Not Word or spreadsheets.

Identify and fix performance bottlenecks — profiling, caching (Redis, CDN, memoization), bundle size, lazy loading, N+1 detection, memory leaks.

Fully-automated PLAN execution via /run-plan — implement, verify (lint+build+test+e2e gate), commit, push per phase. Triggers: run-plan, automation loop, implement PLAN-*.md.

Execute PLAN.md phases with automatic progress tracking. Parses plan, executes tasks sequentially, and auto-invokes plan-updater after each phase completion.

Update branch-specific PLAN.md progress — detects branch, matches PLAN-GIT-*.md / PLAN-*.md, ticks checkboxes, commits.

Responsive-audit methodology — 6 Playwright detection assertions, 3 fix-confidence tiers, detect-fix-re-verify loop. Loaded by responsive-audit-subagent only, not auto-triggered.

Whole-repo over-engineering audit — ranked delete/stdlib/native/yagni/shrink findings with net removable count. One-shot report, applies nothing. Triggers: audit for over-engineering, find bloat, what can I delete.

Harvest `ponytail:` comments into a debt ledger — ceiling and upgrade trigger per marker; flag no-trigger rot. Triggers: ponytail shortcuts, what did ponytail defer, tech debt markers.

Diff-only over-engineering review — flag reinvented stdlib, unneeded deps, speculative abstractions with concrete replacements. Triggers: over-engineered diff, simplify this change, review for bloat.

Fill a PowerPoint template with structured JSON via python-pptx Slide Master layouts. Not for presentations from scratch.

Extract a .pptx into template-schema JSON; returns a self-describing 'templated' PPTX with the schema embedded. Filling: pptx-generate-slide-skill; layout extension: pptx-template-modifier-skill.

Extend a PowerPoint template when a slide_type layout is missing — borrows/clones layouts into template_new.pptx. Normal filling: pptx-generate-slide-skill.

PR creation framework — framework/language detection, configurable quality checks, semver labels, JIRA image attachments and tracking.

Post-merge workflow — merges PR, monitors CI, auto-fixes failures, updates JIRA, deletes source branch. Triggers: 'pr merge to [branch]', 'merge the PR', 'complete the PR'. Not 'create pr'.

Scaffold Python backend projects — FastAPI/Django/Flask layout, dependency injection, config, virtual environments, pyproject.toml.

Python packaging for apps and libraries — pyproject.toml, Poetry, uv, setuptools, hatch, dependency management, PyPI publishing.

Generate comprehensive pytest test files for Python using the test-generator-framework

Detect and fix React hooks anti-patterns — stale useState from props, StrictMode double-execution, dependency traps, stale refs, toast.promise leaks.

Detect and fix React render anti-patterns — missing fragment keys, unsafe JSON.parse, revalidatePath/redirect swallowing, ssr:false hydration.

Generate submission-ready research papers from codebase and verified experimental data — three framing strategies, reference validation, pandoc DOCX conversion. Triggers: research paper, academic paper, write paper, paper draft, journal submission, conference paper.

Research before coding — search existing tools, libraries, patterns first; adopt/extend/compose/build decision matrix.

Audit code and dependencies for vulnerabilities — OWASP Top 10, npm audit/pip-audit, secret detection, XSS/CSRF, security headers, vibeguard masking.

Source of truth for commit-to-PR-to-merge-to-release conventions — semver labels, branch-aware tagging, changelogs, release pipelines.

Enforce SOLID principles with language-agnostic examples and detection strategies.

Create and review SRS (IEEE 830) — the internal 'what' stage after BRD. Triggers: create srs, software requirements, functional spec, feature spec, specification, legacy 'create prd'.

Business document workflows for startup founders — reports, quotations, spreadsheets, presentations with professional formatting.

Startup presentation knowledge — pitch deck structures, board updates, launch decks, palettes, investor-readiness checklists.

Suggest optimal context compaction strategies for AI agent sessions, preserving critical information while reducing token usage

Guide developers through Test Driven Development workflow with red-green-refactor cycle, supporting multiple languages and frameworks

Create Technical Design Documents — converts SRS/feature specs into architecture, data models, API contracts, ADRs. Triggers: technical design, architecture document, system design, design spec.

Standards reference for docs authors — Diataxis, Google developer-docs style, Simplified Technical English, Global English. Triggers: docs style guide, doc-type choice, writing standards, terminology consistency.

Generic test generation framework supporting multiple languages and testing frameworks

Three.js + Next.js (App Router, React 19) integration — SSR pitfalls, GLSL bundling, hydration, WebGL context loss, R3F/drei, WebXR, companion-library decision tree. Version detection first.

Unified GitHub Issues and JIRA planning — structured description, branch, PLAN.md, phased execution. Triggers: create issue, new issue, jira ticket, bug report, feature request, create plan, ticket with plan.

Apply DRY principle to eliminate code duplication in TypeScript projects with comprehensive refactoring patterns

UI/UX design review — 13-axis rubric (AslanMazhidov, RNT56, Nielsen heuristics, anti-default AI detection) with Playwright capture protocol.

Strip AI-tell prose — 31-pattern catalog (delve, tapestry, 'not X but X', em-dash abuse) with find-and-replace fixes. Triggers: unslop, de-AI-ify, humanize text, remove AI writing tells.

Continuously verify implementations against requirements, acceptance criteria, and quality standards throughout the development cycle

Consistent version bumping and release workflows — dev-to-uat-to-main flow, PR-label-driven semver. Use when setting up or auditing release workflows or onboarding a repo.

Create the customer-facing Vision Document (IIBA Business Need/Solution Vision) from a discovery session. Triggers: create vision, vision document, concept brief, solution vision.

Generate lo-fi hand-drawn wireframes and clickable prototypes before production code. Triggers: wireframe, mockup, lo-fi prototype, rough layout, Balsamiq-style, sketch the screens, breakpoint wireframe.

Tracker-ticket-to-merged-PR pipeline via git worktrees — sync, plan, 3-subagent review, /run-plan, code review, PR merge. Triggers: run-worktree-pipeline, worktree pipeline, ticket to PR pipeline, tracker ticket pipeline.

Spreadsheet-first tasks — read, edit, fix, create .xlsx/.xlsm/.csv/.tsv (formulas, formatting, charts, data cleaning). Not Word docs, HTML reports, scripts, or Google Sheets.

Transcribe audio files to text via the Z.AI GLM-ASR API — POST /audio/transcriptions with a wav/mp3 (≤25MB, ≤30s). Triggers: transcribe, speech to text, ASR, audio transcription.

Generate images from text prompts via Z.AI GLM-Image API, saved as local PNGs — direct /images/generations call. Triggers: image generation, generate image, text to image, draw a picture.

Extract text and layout from images or PDFs via the Z.AI GLM-OCR layout_parsing API — structured, layout-aware OCR. Triggers: OCR, extract text from image, layout parsing, document text extraction.

Generate video from a text (or first-frame image) prompt via Z.AI CogVideoX-3 — submit then poll the async result, save as local MP4. Triggers: video generation, generate video, text to video, image to video.

Analyze images/screenshots/PDFs via direct Z.AI vision API (glm-5v-turbo) — fallback when native multimodal is unavailable. Triggers: image analysis, screenshot analysis, vision, describe image, OCR.