/nw-ab-validation-checklist
KNOWLEDGE (data) — the agent-spec validation checklist. The item definitions the validate-spec procedure RUNS against. No sequence of its own.
Claude Code
$ npx -y skills add nWave-ai/nWave --skill nw-ab-validation-checklist --agent claude-code
Codex
$ npx skills add nWave-ai/nWave --skill nw-ab-validation-checklist -a codex -y
Cursor
$ npx skills add nWave-ai/nWave --skill nw-ab-validation-checklist -a cursor -y
Gemini CLI
$ npx skills add nWave-ai/nWave --skill nw-ab-validation-checklist -a gemini-cli -y
GitHub Copilot
$ npx skills add nWave-ai/nWave --skill nw-ab-validation-checklist -a github-copilot -y
OpenCode
$ npx skills add nWave-ai/nWave --skill nw-ab-validation-checklist -a opencode -y
Windsurf
$ npx skills add nWave-ai/nWave --skill nw-ab-validation-checklist -a windsurf -y
SKILL.md
nw-ab-validation-checklist.SKILL.mdname: nw-ab-validation-checklist
description: "KNOWLEDGE (data) — the agent-spec validation checklist. The item definitions the validate-spec procedure RUNS against. No sequence of its own."
user-invocable: false
nw-ab-validation-checklist (KNOWLEDGE / data)
**Kind**: KNOWLEDGE (data). The canonical checklist: every item it defines, and only those. `nw-ab-validate-spec` runs all of them in order. This skill holds the definitions (SSOT), not the run-sequence; other assets name the checklist, never its item count.
| # | Item | Gate | |---|------|------| | 1 | Frontmatter | name, description, model, tools, maxTurns, skills present | | 2 | Line Count | `wc -l` under 400; domain knowledge in skills | | 3 | Divergence Only | zero instructions restating Claude defaults | | 4 | Least Privilege | tools list minimal; no Write/Edit for reviewers | | 5 | Safety by construction (GDP-0) | tool-surface frontmatter + typed grammar first, not prose; a hook only last-resort with a recorded reason | | 6 | Affirmative Phrasing | zero negatively-phrased rules | | 7 | Terminology | one term per concept | | 8 | Description Quality | description states WHEN to delegate | | 9 | Success Criteria Format | numbered/checkbox list, not prose | | 10 | Caveman House Style | dry/declarative, tables + compact lists, lean body | | 11 | Reasoning Mandate Present | `## Reasoning Mandate` section present | | 12 | One Job, One Trigger | one job + one trigger; KNOWLEDGE vs PROCEDURE classified; PROCEDURE states trigger + sequence + composition; zero multi-job parameterized switches; existing command + agent NAMES preserved (no rename/proliferation; new command is the rare `/nw-*` exception) | | 13 | Skill Addressing | apply the source-aware Skill addressing procedure in `nw-agent-creation-workflow`; always-needed skills preload once from frontmatter, conditional skills have precise reachable triggers in one generated index; installed-only source limitations remain explicit, not orphan findings or invented build inputs |
Read more
name: nw-ab-validation-checklist description: "KNOWLEDGE (data) — the agent-spec validation checklist. The item definitions the validate-spec procedure RUNS against. No sequence of its own." user-invocable: false
nw-ab-validation-checklist (KNOWLEDGE / data)
**Kind**: KNOWLEDGE (data). The canonical checklist: every item it defines, and only those. `nw-ab-validate-spec` runs all of them in order. This skill holds the definitions (SSOT), not the run-sequence; other assets name the checklist, never its item count.
| # | Item | Gate | |---|------|------| | 1 | Frontmatter | name, description, model, tools, maxTurns, skills present | | 2 | Line Count | `wc -l` under 400; domain knowledge in skills | | 3 | Divergence Only | zero instructions restating Claude defaults | | 4 | Least Privilege | tools list minimal; no Write/Edit for reviewers | | 5 | Safety by construction (GDP-0) | tool-surface frontmatter + typed grammar first, not prose; a hook only last-resort with a recorded reason | | 6 | Affirmative Phrasing | zero negatively-phrased rules | | 7 | Terminology | one term per concept | | 8 | Description Quality | description states WHEN to delegate | | 9 | Success Criteria Format | numbered/checkbox list, not prose | | 10 | Caveman House Style | dry/declarative, tables + compact lists, lean body | | 11 | Reasoning Mandate Present | `## Reasoning Mandate` section present | | 12 | One Job, One Trigger | one job + one trigger; KNOWLEDGE vs PROCEDURE classified; PROCEDURE states trigger + sequence + composition; zero multi-job parameterized switches; existing command + agent NAMES preserved (no rename/proliferation; new command is the rare `/nw-*` exception) | | 13 | Skill Addressing | apply the source-aware Skill addressing procedure in `nw-agent-creation-workflow`; always-needed skills preload once from frontmatter, conditional skills have precise reachable triggers in one generated index; installed-only source limitations remain explicit, not orphan findings or invented build inputs |
Other skills on nwave.
More skills from other plugins.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
ask-matt
Ask which skill or flow fits your situation. A router over the skills in this repo.
Questions about nw-ab-validation-checklist.
- Which coding agents can use nw-ab-validation-checklist?
- nw-ab-validation-checklist 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.

