Loading...
Loading...
Found 176 Skills
Architect/CR agent role. Receives git diff, task spec, ADRs, design doc, and project conventions. Reviews code and returns APPROVED or CHANGES_REQUIRED. Do NOT invoke directly — dispatched by team-execute.
Structural review of documents for gaps, clarity, completeness, and organization. Use when a brainstorm, plan, spec, ADR, or any doc needs polish before the next workflow step. For exploring new ideas from scratch, use brainstorming instead.
Detects orphaned code (files/functions that exist but are never imported or called in production), preventing "created but not integrated" failures. Use before marking features complete, before moving ADRs to completed, during code reviews, or as part of quality gates. Triggers on "detect orphaned code", "find dead code", "check for unused modules", "verify integration", or proactively before completion. Works with Python modules, functions, classes, and LangGraph nodes. Catches the ADR-013 failure pattern where code exists and tests pass but is never integrated.
Create, validate, and transition documentation artifacts (Vision, Journey, Epic, Story, Agent Spec, Spike, ADR, Persona, Runbook, Bug, Design) and their supporting docs (architecture overviews, journey maps, competitive analyses) through their lifecycle phases. Use when the user wants to write a spec, plan a feature, create an epic, add a user story, draft an ADR, start a research spike, define a persona, create a user persona, create a runbook, define a validation procedure, file a bug, report a defect, create a design, capture a wireframe, document a UI flow, sketch interaction states, update the architecture overview, document the system architecture, move an artifact to a new phase, seed an implementation plan, implement a spec, fix a bug, work on a story, or validate cross-references between artifacts. When a SPEC, STORY, or BUG comes up for implementation, always chain into the swain-do skill to create a tracked plan before any code is written. When swain-do is requested on an EPIC, VISION, or JOURNEY, decompose into implementable children first — swain-do runs on the children, not the container. Covers any request to create, update, review, or transition spec artifacts and supporting docs.
Guides customer-facing and internal technical solution design—discovery and requirements, integration and reference architecture, security/compliance fit, sizing and cost framing, RFP/RFI responses, PoC scoping, build-vs-buy, and handoff to delivery. Use when scoping a customer or partner solution, designing integration architecture for a deal, drafting RFP/RFI technical responses, planning a proof-of-concept, framing security and compliance fit, or preparing solution decks for stakeholders—not for org-wide landing zones and Well-Architected programs (cloud-architect, enterprise-cloud-architect), internal product ADRs and C4 (senior-system-architecture), production Terraform/IaC (infrastructure-engineer), hands-on cloud resource config (cloud-engineer), live PoC execution and competitive demos (sales-engineer), business strategy without technical design (business-consultant), contract redlines (commercial-counsel), or deep FinOps/GL (finops-analyst, compute-accounting-manager).
Mean-variance portfolio optimization via Conjugate Gradient — 40-60× faster than the legacy Neumann path (ADR-126 Phase 3, ADR-123 Wedge 8)
Scaffold and maintain a reusable research → design → plan → orchestrate → act folder for any non-trivial work — software features, marketing campaigns, org changes. Drops a domain-agnostic spine (00-README · 01-plan · 02/03 research · 04-discussion newest-first · 05-tracking · 09-orchestration · artifact/board.html plan-board) plus stateless action-skills that augment the docs in place without clobbering hand-written prose. Composes ikenga-artifact-builder, huashu-design, frontend-design, ikenga-pkg-builder when present; degrades gracefully when not. Profile-driven: `software` (rich default, code work), `general` (lean, non-code — campaigns, org changes), and `content` (editorial/marketing with key art). TRIGGER when the user asks to start a real plan for non-trivial work ("plan a feature," "scaffold a plan folder," "set up groundwork for…"), references an existing plans/ folder by groundwork structure, or runs any of these actions: groundwork init / research / design / review / clarify / orchestrate / refresh-board / refresh-living-spec / status. DO NOT TRIGGER for one-off code changes, single-document writeups, ADRs, or content that fits in a single markdown file — those don't need a multi-doc plan folder. If the user just wants a single artifact (dashboard, mockup), route to ikenga-artifact-builder instead.
Create or update living documentation from git history (branch diff, current branch, PR, or last N commits) for microservices. Use when users ask to document a feature/funcionalidad, document current branch/branch actual, generate release notes/changelog, explain what changed, or update docs for react, integrator, magento, or all services. Produces docs in each repo's docs/ folder (components, changelogs, adrs, runbooks, guides, technical, bugs, plans, tasks) with traceability to commits/files and Obsidian-compatible frontmatter.
Construct well-structured arguments using the hypothesis-argument-example triad. Covers formulating falsifiable hypotheses, building logical arguments (deductive, inductive, analogical, evidential), providing concrete examples, and steelmanning counterarguments. Use when writing or reviewing PR descriptions that propose technical changes, justifying design decisions in ADRs, constructing substantive code review feedback, or building a research argument or technical proposal.
Bootstrap AGENTS.md as a short table-of-contents plus a structured docs/ directory (architecture, product specs, acceptance tests, ADRs, exec plans, quality grades). Use when AGENTS.md is missing, when asked to "create AGENTS.md", "bootstrap project for agents", or "set up agent context".
Erstellt und optimiert GraphQL-Queries und Mutations fuer das microtech ERP-System buero+. Deckt den gesamten ERP-Datenbestand ab: Artikel, Warengruppen, Stuecklisten, Adressen mit Anschriften und Ansprechpartnern, Vorgaenge (Angebote, Auftragsbestaetigungen, Lieferscheine, Rechnungen, Gutschriften, Bestellungen), Vorgangspositionen, offene Posten, Lagerbestaende, Projekte, Dokumente (DMS), Kalender, Kontakte, Kontenplan, Zahlungsverkehr und SEPA-Mandate. Unterstuetzt Lesen, Anlegen, Aendern, Loeschen, Buchen (fnPost), Stornieren (fnReverse), Wandeln (fnConvert), Archivieren sowie ERP-Parametertabellen (Vorgangsarten, Steuerschluessel, Zahlungsbedingungen, Einheiten, Versandarten, Waehrungen, Mahnstufen, Adressstatus, Projektstatus, Dokumentenarten, Kommunikationsarten u.v.m.). Verwende diesen Skill wenn der Nutzer mit microtech ERP oder buero+ arbeiten will, ERP-Daten abfragen, Belege erstellen oder verarbeiten will, oder microtech-spezifische Begriffe wie tbl, fld, fnPost, fnConvert, rowRead, rowNew, rowSave, acoGPreis, lnkPostalAddresses, @acquireLocks erwaehnt. NICHT verwenden fuer andere ERP-Systeme (SAP, Shopify, Odoo, Dynamics), allgemeine SQL/Datenbank-Fragen oder generische GraphQL-Schemas ohne microtech-Bezug.
Build a graph-structured dossier on a seed entity via parallel fan-out + recursive expansion across web, memory, knowledge-graph, codebase, ADR index, and git intel