Skip to content

nWave-ai/nWave / nWave/skills/nw-ab-validation-checklist

nw-ab-validation-checklist

Verified

KNOWLEDGE (data) — the agent-spec validation checklist. The item definitions the validate-spec procedure RUNS against. No sequence of its own.

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.

#ItemGate
1Frontmattername, description, model, tools, maxTurns, skills present
2Line Countwc -l under 400; domain knowledge in skills
3Divergence Onlyzero instructions restating Claude defaults
4Least Privilegetools list minimal; no Write/Edit for reviewers
5Safety by construction (GDP-0)tool-surface frontmatter + typed grammar first, not prose; a hook only last-resort with a recorded reason
6Affirmative Phrasingzero negatively-phrased rules
7Terminologyone term per concept
8Description Qualitydescription states WHEN to delegate
9Success Criteria Formatnumbered/checkbox list, not prose
10Caveman House Styledry/declarative, tables + compact lists, lean body
11Reasoning Mandate Present## Reasoning Mandate section present
12One Job, One Triggerone 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)
13Skill Addressingapply 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
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall