kb-audit — for Claude Code kb-audit, b24-catalog, community, for Claude Code, ide skills, APPROVE, APPROVE WITH FIXES, REQUEST CHANGES, wrangler.toml, catalog_master_view

v1.0.0

Об этом навыке

Подходящий сценарий: Ideal for AI agents that need use this skill whenever you are asked to:. Локализованное описание: CLAUDE.md is the source of truth for conventions — re-read the section matching the change. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Возможности

Use this skill whenever you are asked to:
review a pull request in this repo;
judge merge risk after code has already been committed;
decide between APPROVE, APPROVE WITH FIXES, REQUEST CHANGES;
triage a change that touches multiple concerns (schema + worker + prompt).

# Core Topics

ArtemFilin1990 ArtemFilin1990
[0]
[0]
Updated: 4/21/2026

Killer-Skills Review

Decision support comes first. Repository text comes second.

Reference-Only Page Review Score: 10/11

This page remains useful for teams, but Killer-Skills treats it as reference material instead of a primary organic landing page.

Original recommendation layer Concrete use-case guidance Explicit limitations and caution Quality floor passed for review
Review Score
10/11
Quality Score
64
Canonical Locale
en
Detected Body Locale
en

Подходящий сценарий: Ideal for AI agents that need use this skill whenever you are asked to:. Локализованное описание: CLAUDE.md is the source of truth for conventions — re-read the section matching the change. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

Зачем использовать этот навык

Рекомендация: kb-audit helps agents use this skill whenever you are asked to:. CLAUDE.md is the source of truth for conventions — re-read the section matching the change. This AI agent skill supports Claude Code

Подходит лучше всего

Подходящий сценарий: Ideal for AI agents that need use this skill whenever you are asked to:.

Реализуемые кейсы использования for kb-audit

Сценарий использования: Applying Use this skill whenever you are asked to:
Сценарий использования: Applying review a pull request in this repo;
Сценарий использования: Applying judge merge risk after code has already been committed;

! Безопасность и ограничения

  • Ограничение: schema migrations records root migrations only; ai-kb migrations are idempotent-by-shape.
  • Ограничение: Any change that depends on schema migrations.version reflecting ai-kb state (it does not).
  • Ограничение: schema migrations records root migrations only; ai-kb migrations are idempotent-by-shape

Why this page is reference-only

  • - Current locale does not satisfy the locale-governance contract.

Source Boundary

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

After The Review

Decide The Next Action Before You Keep Reading Repository Material

Killer-Skills should not stop at opening repository instructions. It should help you decide whether to install this skill, when to cross-check against trusted collections, and when to move into workflow rollout.

Labs Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is kb-audit?

Подходящий сценарий: Ideal for AI agents that need use this skill whenever you are asked to:. Локализованное описание: CLAUDE.md is the source of truth for conventions — re-read the section matching the change. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

How do I install kb-audit?

Run the command: npx killer-skills add ArtemFilin1990/b24-catalog/kb-audit. It works with Cursor, Windsurf, VS Code, Claude Code, and 19+ other IDEs.

What are the use cases for kb-audit?

Key use cases include: Сценарий использования: Applying Use this skill whenever you are asked to:, Сценарий использования: Applying review a pull request in this repo;, Сценарий использования: Applying judge merge risk after code has already been committed;.

Which IDEs are compatible with kb-audit?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for kb-audit?

Ограничение: schema migrations records root migrations only; ai-kb migrations are idempotent-by-shape.. Ограничение: Any change that depends on schema migrations.version reflecting ai-kb state (it does not).. Ограничение: schema migrations records root migrations only; ai-kb migrations are idempotent-by-shape.

How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add ArtemFilin1990/b24-catalog/kb-audit. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use kb-audit immediately in the current project.

! Reference-Only Mode

This page remains useful for installation and reference, but Killer-Skills no longer treats it as a primary indexable landing page. Read the review above before relying on the upstream repository instructions.

Upstream Repository Material

The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.

Upstream Source

kb-audit

CLAUDE.md is the source of truth for conventions — re-read the section matching the change. This AI agent skill supports Claude Code, Cursor, and Windsurf

SKILL.md
Readonly
Upstream Repository Material
The section below is imported from the upstream repository and should be treated as secondary evidence. Use the Killer-Skills review above as the primary layer for fit, risk, and installation decisions.
Supporting Evidence

Use this skill whenever you are asked to:

  • review a pull request in this repo;
  • judge merge risk after code has already been committed;
  • decide between APPROVE, APPROVE WITH FIXES, REQUEST CHANGES;
  • triage a change that touches multiple concerns (schema + worker + prompt).

Role

kb-audit is the meta-skill. It never does the deep domain check itself — it delegates to:

If the PR touches…Load also
migrations/*.sql, ai-kb/migrations/*.sql, or any new CREATE TABLE/VIEW/INDEX.claude/skills/d1-migration-safety
src/index.js, ai-kb/src/*.js, wrangler.toml, .github/workflows/deploy*.yml, auth/secrets.claude/skills/cloudflare-worker-review
staging / normalized catalog / catalog_master_view.claude/skills/catalog-import-review
AI_SYSTEM, searchCatalog, analog tables, the bot prompt.claude/skills/bearing-analog-check
any greenfield bot code inside ai-kb/.claude/skills/ai-kb-chatbot-build

Pre-flight checklist

  1. git log --stat origin/main..HEAD (or the PR's base..head). Keep the file list in mind.
  2. CLAUDE.md is the source of truth for conventions — re-read the section matching the change.
  3. docs/RUNBOOK.md is the source of truth for ops — read before judging deploy/secret changes.
  4. Memory of the repo:
    • Two workers share one D1: b24-catalog (root src/, wrangler.toml) + ai-kb (ai-kb/).
    • D1 id: 11a157a7-c3e0-4b6b-aa24-3026992db298, R2: vedro, Vectorize: ai-kb-index (1024/cosine).
    • schema_migrations records root migrations only; ai-kb migrations are idempotent-by-shape.
    • No bundler, no tests, no package.json at the runtime layer — wrangler deploy ships what's on disk.

Scope rules

  • One concern per PR. A PR that touches both migrations/0002_* and AI_SYSTEM and a new /api/admin/* route is a split candidate; ask for cherry-pick.
  • No drive-by refactors. Cosmetic rewrites inside the same PR as a security or schema change hide risk.
  • No silent runtime-only table creation when the migration layer exists (ensureSettingsTable is grandfathered; new tables must land in migrations).
  • No hardcoded secrets — the upload endpoint's old hardcoded token is in git history; rotate if re-introduced.
  • Narrow admin scope. Anything new that guards sensitive data belongs behind requireAdmin, not requireUpload.

Cross-cutting red flags

  • New CREATE TABLE IF NOT EXISTS in src/*.js without a matching migration file.
  • New Vectorize upserts where the embedding dimension is not filtered to EMBED_DIMS = 1024.
  • New admin route without ctx.waitUntil(audit(env, request, ...)).
  • deploy-ai-kb.yml edited to drop the title-retry loop or un-pin wrangler.
  • Any change that depends on schema_migrations.version reflecting ai-kb state (it does not).

Output contract

Use the shape defined in .claude/skills/README.md:

Decision: APPROVE | APPROVE WITH FIXES | REQUEST CHANGES

Why:
- <one-line justification per driver>

Blocking fixes:
- <path:line — concrete change>

Non-blocking improvements:
- <path:line — concrete change>

Merge recommendation:
- <squash | rebase | cherry-pick | hold>

Never return a decision without at least one concrete citation (path:line). "Looks good" is not a review.

References

  • references/review-checklist.md — expanded checklist tied to real repo paths.
  • references/merge-decision-matrix.md — when to escalate from APPROVE WITH FIXES to REQUEST CHANGES.

Scripts

  • scripts/review_pr.sh [base_ref] — prints the changed files, which specialist skills should load, and the highest-risk files in the PR.

Связанные навыки

Looking for an alternative to kb-audit or another community skill for your workflow? Explore these related open-source skills.

Показать все

openclaw-release-maintainer

Logo of openclaw
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

widget-generator

Logo of f
f

Создание настраиваемых плагинов виджетов для системы ленты новостей prompts.chat

flags

Logo of vercel
vercel

Фреймворк React

138.4k
0
Браузер

pr-review

Logo of pytorch
pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

98.6k
0
Разработчик