Loading...
Loading...
Found 320 Skills
Track subcontractor payments, lien waivers, and compliance. Manage payment schedules and documentation.
Use this skill when asked to perform any of the following actions in a Java project: - To add jspecify support - To prevent NullPointerExceptions - To better handle Nullability This skill will add jspecify dependency, configure Maven or Gradle build to automatically use jspecify for checking Nullability issues.
Check BIM model consistency: naming conventions, parameter completeness, spatial relationships, and data integrity across model elements.
Command a Royal Navy agent squadron from sailing orders through execution and stand-down. Use when work can be parallelized, requires tight coordination, or needs explicit action-station controls, quality gates, and a final captain's log.
Keep a system's business logic independent of the technology it talks to, by reasoning about which way dependencies point across a hexagonal / ports-and-adapters / clean-architecture boundary. A system holds three kinds of code — its reason to exist (the business logic), its connections to the outside world, and how it's run (the wiring and entrypoint) — so the question is never "which folder" but "is this the reason, a connection, or how it's run, and what may it depend on?" Use it to scaffold a new system, place a feature, integration, or entrypoint, review how it's shaped, or write an ADR about the layout — and whenever a dependency points the wrong way or you're unsure where something belongs. Language-/framework-agnostic: the kinds map onto whatever names a project uses (app/infra/run, domain/adapters/cmd). Reach for it even when the user never says "hexagonal": "where should this go", "scaffold it ports-and-adapters", "review against hexagonal principles", "which layer owns this" are all signals.
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deploying with vLLM or HuggingFace Transformers.
Used when a Spec Pack is completed, reusable assets need to be promoted to the project SSOT (ADR/contract/ops/NFR/registry), and there are risks of "contaminating the project with full package replication / skipping spec-context / mistaking merge-back for git merge".
Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.
Generates Mermaid diagrams from codebases, topics, files, conversations, or specs. Supports flowcharts, sequence diagrams, class diagrams, state diagrams, ER diagrams, C4 architecture, mindmaps, Gantt charts, timelines, user journeys, gitGraphs, pie charts, quadrant charts, requirement diagrams, and beta types (xychart, sankey, block, architecture). Use when asked to create a Mermaid diagram, visualize a process or system, draw a flowchart, sequence diagram, class diagram, state machine, ERD, architecture diagram, mind map, timeline, Gantt chart, user journey, git branching graph, or any "diagram this" request.
Remove AI-writing patterns from French text and inject voice, personality, and soul. Use when editing, reviewing, rewriting, or cleaning up French content that reads like ChatGPT/Claude output. Humanize, humanise, déslopifier. Detects and fixes 27 patterns: AI vocabulary overuse (crucial, essentiel, notamment, par ailleurs, dans le paysage), anglicisms from English-first models (faire du sens, adresser un problème), copula avoidance, formulaic openings (À l'ère de, Dans le paysage actuel), superficial participle analyses (-ant), em dash overuse, redundant adjective doublets, rule of three, sycophantic tone, typographic tells (curly quotes instead of guillemets). Trigger on: humaniser, déslopifier, rendre plus humain, nettoyer le texte IA, enlever le slop, réécrire pour que ça sonne humain, make it sound human.
Systematic documentation authoring workflow for AI coding agents. Analyzes repositories to determine what documentation is needed, classifies each document by Diataxis type (tutorial, how-to, reference, explanation), and generates accurate, maintainable documentation that stays synchronized with the codebase. Handles greenfield projects (no docs exist), brownfield updates (refresh, enhance, rewrite existing docs), and doc audits with workflow-specific guidance for each. Use when the user requests documentation for a project: README creation, API reference, architecture docs, developer guides, changelogs, or any technical writing tied to a codebase. Also use when existing docs need auditing, updating, rewriting, or restructuring. Triggers on phrases like "write a README", "document this project", "API reference", "architecture doc", "developer guide", "getting started guide", "tutorial", "how-to", "audit our docs", "what docs are missing", "refresh the docs", "Diataxis", "doc the public API", "write a CHANGELOG", "explain this codebase", "onboarding doc", or "ADR". Triggers when creating or editing `README.md`, `CONTRIBUTING.md`, `CHANGELOG.md`, `docs/`, `mkdocs.yml`, `docusaurus.config.*`, `sphinx`/`conf.py`, ADRs, or any markdown file paired with code. Triggers when public APIs, CLI flags, configuration options, or environment variables change and the user wants the docs kept in sync. Do NOT use for standalone prose, marketing copy, blog posts, design documents, RFCs unrelated to a codebase, or documents where the source of truth is not source code.
Design data architecture at enterprise and solution levels. Cover data mesh, lakehouse, governance, domain-driven design, conceptual/logical/physical data modeling, platform selection, and compliance frameworks. Produce ADRs, data model diagrams, platform comparison matrices, and governance policy templates. Triggers on "design data platform", "choose data warehouse", "data mesh", "lakehouse architecture", "data governance", "data modeling", "platform selection", "data architecture decision", "compliance framework", or "data strategy". For applied AI solution architecture (RAG data plane, embeddings, vector stores in commercial or enterprise products), use applied-ai-architect-commercial-enterprise. For dbt analytics layers and mart delivery, use analytics-data-engineer—not data-architect.