Skip to content
Development
Skill

/nw-expectation-charter

Supplies or reviews user-view qualitative charter facts when EXAMINE applies.

From plugin
nwave
635183 skills37 agents

Claude Code

$ npx -y skills add nWave-ai/nWave --skill nw-expectation-charter --agent claude-code

SKILL.md

nw-expectation-charter.SKILL.md
name: nw-expectation-charter
description: Supplies or reviews user-view qualitative charter facts when EXAMINE applies.
user-invocable: false

Expectation Charter

The charter gives the examiner an independent human oracle. Derive it from public product intent and the observed user surface. Work from the user's point of view; design, tests, implementation and diffs are not needed to define the expected public experience. Dispatch `nw-product-owner` for the charter task.

Charter content

The Product Owner supplies intent, exploration, positive observations and a negative observation from public product facts. Explain unresolved prerequisites, their owner and remedy; uncertainty is not acceptance.

Value conservation

State intent, public starting conditions, what to explore and concrete positive and negative observations. A public start recipe uses a real product surface: exact CLI argv, a consumer's public library setup/call, an HTTP/RPC request, or ordered UI actions. Preparing internal state or invoking a private application/domain seam is not that recipe.

Every precondition and observation must preserve the public product intent: clarify wording without adding or removing an input class, surface, failure mode, quality or promise. A negative observation negates the same promised outcome on admitted input; it does not invent a new scenario. Missing intent or an exact usable public recipe returns to the product owner/human for clarification, rather than inferring user intent from architecture, source or tests.

Do not include internal implementation names, test selectors, diffs or a precomputed verdict. CLI, API and infrastructure capabilities can be user surfaces when a real operator observes them. A charter is an expectation, not proof that the candidate behaved correctly.

Host-owned evidence and reuse

Keep adequate unchanged product authority and prior charter evidence when still applicable; changed facts require the owning role's current result, not a hand-edited generated document. EXAMINE receives the public contract, charter and actual observations for its independent user-view assessment. The host captures observations and retains candidate/currentness evidence. No separate charter directory grammar, session-log writer or progress ledger is introduced by this skill.

Expectation rows and the examine level

The charter is the examiner's human oracle; it does not set the expectation rows or the examine level. Each fixed expectation row states a `lacuna`: what its own oracle does not see. A new or changed row without a non-blank lacuna is refused. A row also carries `blocking`, `isolated` (each `yes` or `no`) and free-text `needs`. A kept row is append-only: it leaves the set only with an unmet `expectation_defect` verdict. The repair rounds are stated to the examiner and enforced by the nwdes examination: `quick` admits one examination, `standard` two and `extended` three.

Read more
@nwave-ai
Ships withnwave

nWave supplies specialist roles and a host-led delivery workflow for software teams.

635183 skills37 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
635
Star history of nWave-ai/nWave on GitHub, a chart by star-history.com

Other skills on nwave.

nw-ab-agent-template

nw-ab-agent-template

KNOWLEDGE — the canonical agent-spec template (frontmatter + body skeleton). Reference loaded by the create/migrate procedures;…

@nwave-ai@nwave-aiInstall Skill
nw-ab-anti-patterns

nw-ab-anti-patterns

KNOWLEDGE — agent/skill/command anti-pattern catalog with fixes. Reference scanned by validate-spec; no sequence.

@nwave-ai@nwave-aiInstall Skill
nw-ab-create-agent

nw-ab-create-agent

PROCEDURE — create a NEW agent via the 5-phase workflow (ANALYZE→DESIGN→CREATE→VALIDATE→REFINE). Trigger: build a new AI agent.…

@nwave-ai@nwave-aiInstall Skill
nw-ab-examples

nw-ab-examples

KNOWLEDGE — canonical worked examples for agent creation, migration, and command optimization. Reference for the relevant…

@nwave-ai@nwave-aiInstall Skill
nw-ab-house-style

nw-ab-house-style

KNOWLEDGE — caveman-native authoring house style + by-construction guarantees (Reasoning Mandate injection, measured-gain…

@nwave-ai@nwave-aiInstall Skill

More skills from other plugins.

brainstorming
Auto-invoked

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…

@obra@obraInstall Skill
ask-matt

ask-matt

Ask which skill or flow fits your situation. A router over the skills in this repo.

skills13d309k
@mattpocock@mattpocockInstall Skill
accessibility
Auto-invoked

accessibility

Design, implement, and audit accessible UI to WCAG 2.2 Level AA across Web, iOS, and Android — semantic ARIA roles and labels,…

ecc2w293k
@affaan-m@affaan-mInstall Skill
compiler-commit

compiler-commit

Use when you want to verify compiler changes and commit with the correct convention. Runs tests, lint, and format, then commits…

react4d252k
@facebook@facebookInstall Skill

Questions about nw-expectation-charter.

Which coding agents can use nw-expectation-charter?
nw-expectation-charter installs in Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf with the skills CLI, using each agent's flag shown on this page. Flowy's auto-invocation, which fires a skill when your prompt matches, runs in Claude Code only.