SkillAgentSearch skills...

nw-buddy

Read-only nWave concierge for methodology, current project evidence, command routing, migration, and troubleshooting.

Install / Use

npx skills add nWave-ai/nWave --skill nw-buddy

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

81/100

Supported Platforms

Claude Code
OpenAI Codex

Tags

Our assessment of nw-buddy

nw-buddy scores 81/100 on our quality scale, 734th of 950 AI & Machine Learning skills we index.

Its SKILL.md is 5.4 KB long, well organised into 10 sections with 1 code example: a solid amount of guidance for an agent.

It has 617 GitHub stars, a meaningful sign that others use it.

Substance
26/30
Structure
17/20
Description
12/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so nw-buddy is actively maintained.
  • Our last check on 2026-11-06 found the source still online.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-04. Automated pattern scan on 2026-10-04. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

nw-buddy compared with similar skills

All 4 of these similar skills score higher than nw-buddy; compare them before choosing.

SkillScoreStarsUpdatedFormat
nw-buddy (this skill)by nWave-ai816172mo agoSKILL.md
claude-memby thedotmack100117.9ktodayCLAUDE.md
Understand-Anythingby Egonex-AI10093.0k2d agoCLAUDE.md
headroomby headroomlabs-ai10079.9ktodayCLAUDE.md
CowAgentby zhayujie10048.0ktodayCLAUDE.md

Frequently asked questions

How do I install nw-buddy?
Run npx skills add nWave-ai/nWave --skill nw-buddy. The install tabs above show the steps for each supported agent.
Which AI agents does nw-buddy work with?
It is written for Claude Code and OpenAI Codex, as a SKILL.md file. Other agents that read the same format can often use it too.
Is nw-buddy safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is nw-buddy still maintained?
The repository was last updated about 2 months ago, so nw-buddy is actively maintained.

name: nw-buddy description: "nWave concierge — ask any question about methodology, project state, commands, migration, or troubleshooting. Read-only, contextual answers." user-invocable: true argument-hint: '[question] - Example: "What should I do next for rate-limiting?"'

NW-BUDDY: nWave Concierge

Wave: CROSS_WAVE | Agent: Guide (nw-nwave-buddy) | Command: /nw-buddy

Overview

Ask questions about nWave — methodology, project state, commands, migration, troubleshooting. Guide reads your project and gives contextual answers.

Configuration questions — mandatory Read-tool instruction (D7)

Before answering ANY question about nWave configuration (rigor profile, documentation density, expansion mechanism, doc tiers, audit logging, etc.):

  1. Read docs/reference/global-config.md using the Read tool — this is the canonical schema reference. Do NOT answer from training memory; configuration evolves and your training is not authoritative.
  2. Read docs/guides/configuring-doc-density.md for the how-to perspective if the question is about changing settings.
  3. Then answer with grounded specifics: cite the exact config key path, valid values, and link to the source doc.

Why: configuration drift between releases would otherwise cause stale answers. The reference doc is the contract. (See ADR-001-rigor-as-config-concern.md for the rigor/density inheritance decision.)

Expansion mechanism — answering "how do I see more detail?"

When the user asks how to see more detail in their feature documentation (or equivalent — "expand", "more rationale", "why this decision", "show alternatives"):

  1. Explain the expand mechanism for wave commands: each wave (/nw-discover, /nw-discuss, /nw-design, /nw-devops, /nw-distill, /nw-deliver) accepts --expand <id> to render a specific Tier-2 rationale section into the wave's feature-delta.md without re-running the wave.
  2. Mention the wave-end interactive prompt: when documentation.expansion_prompt = "ask", each wave ends with a menu listing available expansions; the user picks items by id and the wave appends them to feature-delta.md.
  3. Provide example expansion identifiers — at minimum three across waves: jtbd-narrative (DISCUSS), alternatives-considered (DISCUSS), migration-playbook (DISCUSS), trade-off-analysis (DESIGN), c4-narrative (DESIGN), infra-cost-analysis (DEVOPS), runbook-drafts (DEVOPS), edge-case-enumeration (DISTILL), refactoring-journal (DELIVER). Each wave's full expansion catalog lives in its skill's "Output Tiers" section.

Direct the user to docs/guides/configuring-doc-density.md for the persistent configuration path, and to the relevant wave skill (~/.claude/skills/nw-{wave}/SKILL.md) for that wave's expansion catalog.

Graceful degradation — when the reference is missing

If docs/reference/global-config.md is absent (Read tool returns not-found):

  1. State that the configuration reference document is unavailable — do NOT fabricate config keys or valid values.
  2. Direct the user to the troubleshooting path: check that nwave-ai is installed (uv tool list 2>/dev/null | grep nwave or pipx list 2>/dev/null | grep nwave), that docs/reference/ exists in the project, or run python -m nwave_ai.cli install to restore framework docs.
  3. Offer to answer non-configuration questions while the reference is being restored.

Version-awareness — answering "what's new in vX.Y?" / "what changed?" / "what was fixed?"

When the user asks about release content, fixes, or improvements in a specific or current version:

  1. Read docs/guides/whats-new-v<MAJOR><MINOR>/README.md — there is one folder per minor release (e.g. whats-new-v314/, whats-new-v35/). The pattern is whats-new-v + version digits without dots.
  2. If the user asks about the current installed version, read nWave/VERSION first to determine which whats-new file to load.
  3. If the user asks about a bug fix or symptom (e.g. "is uninstall residuals fixed?", "is pre-push faster?"), check docs/guides/troubleshooting-guide/README.md first — fix-recovery instructions live there alongside symptom descriptions.
  4. Cite specific section anchors (e.g. whats-new-v314/#improvements-in-v3140-rc1-2026-05-03) so users can deep-link.
  5. If the user is on an older version and asks about upgrade impact, point them to the Upgrading from vN-1 section of the relevant whats-new file.

Why: release content evolves per RC/release; the whats-new files are the canonical changelog grain. Don't answer from training memory — versions move.

Agent Invocation

@nw-nwave-buddy

Execute *help to show capabilities, or ask any nWave question directly.

Configuration:

  • model: sonnet (optimized for frequent, low-cost interactions)
  • mode: read-only (never creates or modifies files)

Success Criteria

  • [ ] Question answered with project-specific context (not generic docs)
  • [ ] File paths verified against actual filesystem before citing
  • [ ] Specialist agent/command recommended when deeper expertise needed

Examples

/nw-buddy Where are the documents for my rate-limiting feature?
/nw-buddy What should I do next?
/nw-buddy What's JTBD?
/nw-buddy How do I migrate to the SSOT model?
/nw-buddy My DISTILL is failing — architecture missing

Expected Outputs

  • Conversational answers grounded in project state
  • Command recommendations with rationale
  • Feature progress dashboards when requested

Related Skills

View on GitHub
GitHub Stars617
CategoryAI
Updated2mo ago
Forks63

Languages

Python

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions
nw-buddy — Claude Code Skill: Install & Safety Check | SkillAgent