Skill Claude CodeCodex
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
Skill Claude CodeCodex
NONoise SDLC advisor — reads the project-local .nonoise/sdlc-flow.md, tells the user where they are in the flow and what skill to engage next, with a copy-pasteable example prompt. Use when the user types /polly, says "start polly" / "avvia polly" / "run polly", or asks an ambiguous "where do I start?" / "what's…
Skill Claude CodeCodex
Quint First Principles Framework — structured reasoning methodology with 6 phases (Initialize → Abduct → Deduce → Induce → Audit → Decide), Reff via WLNK, and Congruence Level tracking. Use when you need to formally validate an architectural decision, a PRD, or any non-trivial claim. Invokable standalone or delegated…
Command
Reconcile the project's FPF state with recent repository changes.
Command
Manages evidence freshness by identifying stale decisions and providing governance actions. Implements FPF B.3.4 (Evidence Decay).
Command
Search the FPF knowledge base and display holon details with assurance information.
Command
Command "q-reset" from russosalv/NONoise, covering reset cycle and instruction.
Command
Returns the current FPF phase (IDLE, ABDUCTION, DEDUCTION, INDUCTION, DECISION).
Command
You are the Initializer operating as a state machine executor. Your goal is to establish the Bounded Context (A.1.1) for this reasoning session AND to set up the per-cycle output folder that all subsequent phases will write to.
Command
You are the Abductor (Scribe). The user has a specific solution in mind that they want to evaluate alongside the existing hypotheses. Your goal is to formalize it as a single L0 hypothesis and append it to the cycle's markdown trail.
Command
Generate Hypotheses (Abduction).
Command
Verify Logic (Deduction).
Command
You are the Inductor operating as a state machine executor. Your goal is to gather Empirical Validation (EV) for L1 hypotheses to promote them to L2, and to record the evidence trail in markdown.
Command
Audit Evidence (Trust Calculus).
Command
You are the Decider operating as a state machine executor. Your goal is to finalize the choice and generate the Design Rationale Record (DRR) in markdown — and (in tooled mode) in .quint/decisions/. This is the cycle's final artifact.
Skill Claude CodeCodex
Dialogic skill that turns raw business input (PDFs, DOCX, markdown notes, stakeholder emails, call transcripts, meeting summaries) into structured requirement files under docs/requirements/ / .md, following NONoise conventions. USE AS PRE-STEP before arch-brainstorm — it converts unstructured stakeholder material into…
Skill Claude CodeCodex
Produces and incrementally maintains a versioned reverse-engineering dossier for a subject — a legacy codebase, a microservice, a third-party API, an internal library, a data pipeline. Output is markdown chapters under docs/support/reverse/ /, combining project documents (sprint inputs, meeting notes, functional…
Skill Claude CodeCodex
Discovers AI skills from a curated registry of external sources (Anthropic official, Claude plugin marketplaces, community repos, awesome-lists) and installs them into the current project. Use when the user asks to "find a skill for X", "do we have something for Y?", "add /stack support", "install a skill from…
Skill Claude CodeCodex
Translates macro functional tasks from a NONoise sprint manifest (docs/sprints/Sprint-N/sprint-manifest.md) into work items on an external issue tracker via a pluggable adapter pattern. Ships adapters for GitHub Issues (default), Azure DevOps, Jira, Linear, plus dry-run mode that prints what would be created without…
Skill Claude CodeCodex
Step 3 of the NONoise architectural workflow. Promotes validated PRDs from docs/prd/ / to docs/sprints/Sprint-N/ / and produces one aggregated Sprint Manifest at docs/sprints/Sprint-N/sprint-manifest.md listing all promoted PRDs, derived user stories, macro functional tasks (vertical slices) with confidence…
Skill Claude CodeCodex
Use ONLY when the user explicitly asks the AI assistant to route, dispatch, fan-out, split, or parallelize a task across multiple AI model CLIs (Claude / Codex / Gemini / Copilot's many models) — phrases like "usa lo swarm", "swarm:", "/swarm", "instrada", "fan-out", "route this task", "scegli il modello migliore…
Skill Claude CodeCodex
Creates or updates .vscode/tasks.json and .vscode/launch.json based on the stack detected in the project (Node, .NET, Python). Use when the user asks to "create vscode tasks", "generate launch.json", "configure vscode for debug", or similar.
Command Claude Code
Build/refresh the project's knowledge graph via the /graphify slash skill (no API key needed).
Command Claude Code
Invoke Polly — the NONoise SDLC advisor.