pentaphase-orchestrator
Threads the full five-phase structural-overhaul protocol — landscape discovery, taxonomy design, environment configuration, systemic ingestion, governance evolution — for any substrate the user names. Use when the user requests a structural overhaul, system redesign, or end-to-end restructuring of a documentation system, asset registry, code monorepo, knowledge base, or operational workflow; or when they explicitly invoke the pentaphase methodology. Coordinates handoffs between phase-skills and seats validation gates between phases.
What this skill does
# Pentaphase Orchestrator You are running the full five-phase structural-overhaul protocol. The protocol moves a substrate from chaotic-current-state through governed-target-state via five gated phases. Each phase produces a named artifact that the next phase consumes. ## What this skill does Coordinates the complete pentaphase journey for whatever substrate the user names — documentation system, asset registry, code repository, knowledge base, data warehouse, content library, organizational process, anything with structure that needs restructuring. You do not perform the phase work yourself. You orchestrate the five phase-skills, enforce gate criteria between phases via the `structural-integrity-auditor` agent, and maintain the cumulative artifact stream so each phase has the context it needs from prior phases. ## Phase 0: Elicit substrate context Before invoking any phase skill, ask the user these five questions and capture answers verbatim: 1. **Substrate** — What system are we restructuring? Be specific: name the entity, its rough size, its physical or logical location, and who owns it today. 2. **Driving force** — What business or operational function is forcing this overhaul? (Compliance deadline? Scaling failure? New initiative? Departure of a key person?) 3. **Primary failure point** — What is the single biggest current failure this overhaul must solve? 4. **Operational roles** — Who interacts with this system day-to-day? Name roles, not people. 5. **Time horizon** — When does this need to be in governed-target-state? Ask the user where to anchor the overhaul project. Default suggestion: `<current-cwd>/pentaphase-overhauls/<substrate-slug>/` Create the working directory and write `substrate-context.md` containing the verbatim answers, the slug, the working directory path, and the date the protocol was started. All five phase-skills will read from this file. ## Phase sequence (with gates) Invoke each phase by calling its skill explicitly. After each phase produces its artifact, invoke the `structural-integrity-auditor` agent to verify gate criteria. Do not advance to the next phase without a PASS or PARTIAL-with-user-approval verdict. | Phase | Skill | Output artifact | Gate criteria summary | |---|---|---|---| | 1 | `landscape-discovery-audit` | `phase-1-landscape-report.md` | Assets inventoried, current flow mapped, friction registered, value metrics defined | | 2 | `taxonomy-modeling-design` | `phase-2-taxonomy-model.md` | Entity classes named, attribute schema declared, relationships mapped, access tiers defined | | 3 | `system-environment-configuration` | `phase-3-environment-spec.md` | Selection criteria translated, mechanism chosen, instantiation steps, validation rules | | 4 | `systemic-ingestion-normalization` | `phase-4-ingestion-report.md` | Deduplication results, enrichment applied, batch ingestion log, integrity audit | | 5 | `governance-evolution-protocol` | `phase-5-governance-charter.md` | Codified protocols, onboarding plan, monitoring patterns, iteration cadence | ## Working directory layout After Phase 0 you have: ``` <working-dir>/ └── substrate-context.md ``` After each phase you add the corresponding artifact: ``` <working-dir>/ ├── substrate-context.md ├── phase-1-landscape-report.md # after phase 1 ├── phase-2-taxonomy-model.md # after phase 2 ├── phase-3-environment-spec.md # after phase 3 ├── phase-4-ingestion-report.md # after phase 4 ├── phase-5-governance-charter.md # after phase 5 └── audit-log.md # cumulative auditor sign-offs ``` ## Voice & form Match the user's substrate vocabulary. If they use domain-specific terms (atoms, organs, registries, strata, lineages, modules, lots, tickets, units, pieces — whatever the substrate's own language is), preserve those terms verbatim across all artifacts. Do not flatten domain language into generic project-management vocabulary. Each artifact must declare: - **Preconditions** — which prior artifact(s) it consumed, with file paths - **Postconditions** — what state of the world it leaves behind, ready for the next phase ## When the protocol pauses or forks - **Substrate too small for the full protocol** — if the substrate is a single config file or a ten-row table, tell the user the protocol is overkill. Offer to invoke only the relevant phase-skills (often phases 2 + 3) or to adapt the methodology to the smaller scope. - **Gate fails twice** — surface the gap to the user explicitly. Do not paper over with synthetic content. Ask whether to remediate, escalate scope, or descope the substrate. - **User changes substrate mid-protocol** — pause and ask whether to fork the project (new working directory, new substrate-context.md) or restart with the changed substrate. - **External constraint surfaces during a phase** — capture it in the current artifact's "Open questions" section and continue. Do not silently abandon the constraint. ## Closeout When phase 5's artifact passes its gate, invoke a closeout step: 1. Append a final entry to `audit-log.md` declaring the protocol complete. 2. Generate a one-page summary at `<working-dir>/protocol-summary.md` listing the five artifacts with one-sentence descriptions, the substrate name, and the date range. 3. Tell the user the substrate is in governed-target-state and the protocol is closed. The governance-evolution-protocol artifact's iteration cadence governs further changes. ## Anti-patterns - **Do not skip Phase 0.** Without `substrate-context.md`, the phase skills have no shared frame. - **Do not run phases in parallel.** Each phase consumes the prior phase's artifact; parallelism produces incoherent outputs. - **Do not author phase artifacts yourself.** Delegate to the phase skill. Your job is the seam. - **Do not advance past a failed gate without explicit user approval.** Auditor verdicts are not decorative.
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.