Reviews tool configurations for correctness.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add serpro69/claude-toolbox --skill before --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Before?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/serpro69-before-392389ef)More formats (shields.io, HTML) on the badges page.
---
name: review-tool
description: Reviews tool configurations for correctness.
---
<!-- codex: tool-name mapping applied. See .codex/scripts/session-start.sh -->
# Review Tool
**Goal: Validate tool configuration files against the project schema.**
## Conventions
Follow standard review conventions.
## Validation Rules
You MUST check every configuration file for:
- Required fields present (`name`, `version`, `entrypoint`)
- No deprecated fields (`legacy_mode`, `compat_shim`)
- Version string matches semver format
## Error Handling
When a validation error is found:
1. Record the file path, field name, and violation type
2. Continue checking remaining files — do not stop on first error
3. Group errors by severity: blocking vs. warning
## Required Outputs
- [ ] Validation report written to `docs/reports/`
- [ ] Inline summary with pass/fail counts
- [ ] Blocking errors indexed under `kk:review-findings`
## Workflow
**Mandatory order — load rules before validating.** Read all configuration schemas before examining any target files.
Phases: load schemas → scan files → classify errors → write report → present summary.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.