Claude Skills by me-cedric

Turn a meeting transcript, call notes, or a decision discussion into an Architecture Decision Record under docs/decisions/. Use when the user pastes meeting notes or a transcript and wants the decision captured, or says "generate an ADR from this", "record this decision", or "write it up as an ADR".

Teach users how a project, feature, workflow, or agentic tool use works without over-coaching. Use for explanation, onboarding, "how/why" questions, prompt improvement, and provider-tool coaching.

Build the UI for AI-native interfaces — streaming answers with citations, reasoning traces, tool-call chips, approval gates, agent task rows, prompt composers, confidence meters, proposed-diff tables. Use when implementing or reviewing any surface where a model or agent is the thing the user works with.

Angular coding patterns — standalone components, signals, native control flow, inject()-based DI, forms, and accessibility. Use when writing or reviewing Angular components, services, directives, templates, or forms.

Keep API code and contract layers synced when endpoints, DTOs, payloads, status codes, query params, auth rules, or business transitions change. Use for API work in projects with OpenAPI/Scalar or Swagger, Bruno, Gherkin, shared client types, or generated mocks.

Help decide and justify the architecture for a NEW project from client needs — technology-neutral, research-first, no unlabeled guesses. Use when the user says "help me choose the best architecture", "which tech stack / framework", "design the architecture for this project", "architecture decision", "should we use X or Y", or provides functional/technical/client-IS info (incl. images) and wants a recommendation, mermaid diagrams, ADR, caveats, open questions, a technical backlog, or a list of...

BullMQ queue processing patterns for NestJS — processors, schedulers, job spans, tracing, deduplication, and delayed jobs

Reverse-engineer an existing codebase into draft specifications, decision records, and an architecture sketch. Use when a legacy or third-party project has code but missing or incomplete product and architecture documentation.

Wire agent-compass into an existing project end-to-end with minimal user input: detect the stack, run non-interactive setup, install only what fits, verify, and report. Use when the user asks to "set up", "adopt", "install agent-compass into", or "make agentic" an existing repository.

Bootstrap a brand-new project from architecture guidelines or a product idea: translate guidelines into a bootstrap answers file, generate the build prompt, execute it spec-first, and wire agent-compass into the result. Use when the user asks to "create", "bootstrap", "start", or "scaffold" a new project.

Add a new capability to agent-compass itself — a skill, knowledge instinct, template, stack preset, doc, or script — with correct frontmatter, index wiring, tests, and validation. Use when the user wants to add, import, or promote a skill/agent/knowledge/tool into the compass.

Use when someone wants to add, list, inspect, curate, refresh, or remove an external agent-skill source in Agent Compass — \"add these skills from <repo>\", \"integrate this skill pack\", \"what external sources do we track\", \"is <skill> already covered\", \"update the pinned sources\", \"drop that source\". Runs the licence gate first, registers the source as tracked-not-copied, computes its inventory, records the curation, writes the pointer document, and validates. Triggers: external ski...

Turn specs and a progress audit into an exhaustive, structured backlog of the remaining work — each item with a short rationale, a concrete plan, the engineering rules that apply, a matched tracker ticket (or "create one"), dependencies, and any approval gate. Use when scoping what's left, building a completion/roadmap plan, or checking which work is missing from the tracker.

Convert Word (.doc, .docx), PowerPoint (.ppt, .pptx), Excel (.xls, .xlsx), OpenDocument (.odt, .ods, .odp), RTF, EPUB, CSV, and PDF files to GitHub-Flavored Markdown. Use when a task needs the contents of an office document, spreadsheet, presentation, ebook, or PDF that the active provider cannot read directly.

Build a tight failing feedback loop before diagnosing hard bugs, flaky tests, regressions, or performance issues.

Write the Product Owner / Project Manager digest of what changed — plain language, business impact, scope and planning consequences, no code. Use when the user asks for a status update for the PO, a stakeholder or client summary, release notes, a non-technical changelog, or a sprint/delivery report.

Use when a frontend surface needs a visual direction rather than a bug fix — a landing page, a marketing site, a portfolio, a redesign, a brand system, a dense product UI, or turning a mockup or screenshot into code. Picks the one tracked design skill that fits the surface and installs it, then holds the visual-proof gate in force. Triggers: landing page, marketing site, redesign, make it look good, design direction, visual identity, brand kit, logo system, minimal UI, brutalist, editorial la...

Draft a MADR Architecture Decision Record from an Excalidraw, draw.io, Mermaid, or BPMN diagram. Use when the user wants to capture the decision, options, and drivers shown by an architecture or process diagram.

Convert an Excalidraw, draw.io, draw.io SVG, or Mermaid architecture diagram into a LikeC4 model. Use when the user wants a structured C4 model from a hand-drawn or text architecture diagram.

Produce a DBML database schema from documentation, requirements, or an existing data model. Use when the user wants a DBML (dbdiagram.io) file describing tables, columns, and relationships, or mentions DBML / ER diagram / data model.

Drizzle ORM + PostgreSQL patterns — schema definition, migrations, transactions, seeding, views, enums, indexes, and type inference

Expo Router + React Native mobile app patterns — MVVM architecture, feature modules, Zustand auth, React Query hooks, theming, secure storage, animations, and testing

External service integration patterns — SFTP connections, payment gateways, Keycloak auth, HTTP clients with resilience, and provider isolation

Use Figma MCP design context to implement frontend screens, design systems, components, and styles.

Convert a Figma design-token JSON export into a design.md design-system file (google-labs-code/design.md format). Use when the user has Figma tokens/variables JSON and wants a machine-readable design.md with colors, typography, spacing and rounding tokens.

Documentation generator. Analyzes a module's structure and generates README.md and DESIGN.md skeletons. Use when the user mentions generating docs, creating a README, creating a DESIGN doc, doc skeletons, or doc templates. Auto-triggers when a new module is started.

Read the project specifications and write one RAID register file per open question, risk, assumption, issue or dependency. Use when the user asks to harvest the open questions, collect the assumptions behind an estimate, fill the RAID register, import the spec-kit Clarifications sessions, or find what the specs leave undecided.

Analyse what changed since a base git reference and produce the developer action plan — technical impacts, blast radius, and the exact project documents that are now stale. Use when the user asks for the impact of a change, what a branch breaks, what a diff affects, which docs to update after a change, or a technical action plan before merging.

Produce a detailed, production-ready, plug-and-play implementation spec for a scope of work-items that a developer or agent can start or one-shot: exact files, schema, contracts, logic, resilience/security, jobs, env scaffolding, and tests — including mock/fail-closed paths for anything missing credentials. Use when you need a build-ready plan, not just a backlog.

Turn a LikeC4 model into an OpenSpec change proposal (proposal + spec deltas + tasks). Use when the user wants to derive specs or requirements from a C4 model, or mentions likec4/c4 plus openspec.

Run broad, multi-phase, autonomous coding work safely: intake, plan, checkpoint, optional one-at-a-time subagents, implementation loops, validation, and final sweep. Use when the user asks to keep going until a large goal is finished or gives many phases.

Use when the work is native Android or native Apple-platform code — Kotlin, Jetpack Compose, Gradle/AGP, Android manifests and intents, R8, Swift, SwiftUI, UIKit, SwiftData, Xcode, an iOS/iPadOS/watchOS/visionOS target, an emulator or a simulator. Routes the task to the pinned vendor skill that holds current platform guidance, installs it with the vendor's own installer, and keeps the Agent Compass validation and visual-proof gates in force. Triggers: android app, jetpack compose, kotlin, gra...

Turborepo + NestJS + Drizzle + BullMQ monorepo scaffolding — project structure, shared types, workspace config, Docker, CI/CD, and new feature bootstrapping

NestJS module architecture patterns — controllers, services, repositories, DTOs, guards, mappers, and module registration for production APIs

Drive and enforce the OpenSpec change lifecycle: resolve the one root, ask the status gate which artifact is next, keep proposal, delta specs, design and tasks coherent, verify before archiving, and fail the gate when a change is half-planned. Use when the project keeps specs under an openspec/ or docs/openspec/ root, when a change is missing an artifact, when `openspec validate` passes but the work is not planned, or when the user asks to propose, apply, verify, sync or archive a change.

Use when the task is DevOps, cloud, Kubernetes, containers, CI/CD, observability, security scanning, secrets, hardening, networking, storage, databases, incident response, LLM/GPU serving, or a compliance framework (SOC 2, ISO 27001, GDPR, HIPAA, PCI DSS, FedRAMP). Installs the pinned operational skill for the task with the Agent Compass safety gate applied, then holds the authorization and production-write rules in force. Triggers: terraform, kubernetes, kubectl, helm, argocd, docker, github...

Deep PR/MR review governance: compare code to product/spec docs, security, repo rules, tests, docs sync, and UI evidence before writing a summary and inline comments. Use when asked to review a pull request, merge request, branch, or posted review comments.

Streamline PR creation, PR reviews, and implementing submitted review fixes with GitHub CLI.

Audit how much of a project is actually built by diffing its specs, functional docs, and requirement registers against the real code into an honest, verified progress matrix (per feature/subfeature and global). Use when asked how far along a project is, what's left, percent complete, a progress or status/completion report, or to "compare the specs to the code".

Use when a project has projectmem or durable agent memory. Reads memory before work, checks pre-action warnings, and records durable findings, failed attempts, decisions, fixes, validation, and risks.

Run an end-to-end QA review pass and write the tester report — every requirement scenario given a verdict, every screen compared against its design reference, every finding split into a defect or a change request. Use when a QA tester, a Product Owner or a project manager asks whether the build matches the specification, asks for a QA report, an acceptance review, a test coverage matrix, or a defect list before a release.

React admin dashboard patterns — TanStack Router, MUI Material, MVVM ViewModels, RBAC permissions, Keycloak OIDC, React Query CRUD hooks, feature modules, Vite config

Resilience (circuit breaker, retry) and observability (OpenTelemetry tracing, metrics, structured logging) patterns for NestJS production APIs

Triage a specification change against the tickets it already produced — summarise the delta in the vocabulary of the ticket, say what to do about it, and flag whether it is a candidate for a change request. Use when a spec moved after tickets were created, when the ticket registry reports drift or a conflict, or when the user asks what a spec edit means for the tracker.

Write the tracker ticket text for one specification section — summary, short why, acceptance criteria taken from the words of the spec, and the link back. Use when the user asks to turn a spec or a requirement into a ticket, to draft a Jira story from a specification, to write acceptance criteria for a requirement, or to review proposed ticket text.

Use for project ideas, feature specs, requirements, unclear tasks, technical plans, task breakdowns, or requests that need spec-driven clarification before implementation.

Use when refreshing AGENTS.md or provider context markers from current Spec Kit artifacts without overwriting host-owned guidance.

Use when checking Spec Kit artifacts for inconsistencies across spec, plan, tasks, contracts, docs, and validation.

Use when creating or updating Spec Kit quality, security, UX, or readiness checklists for a feature spec.

Use when resolving Spec Kit open questions, NEEDS CLARIFICATION markers, or ambiguous feature requirements before planning.