ai-review
- Repo stars 0
- Author updated Live
- Author repo skills-registry
- Domain
- AI
- Compatible agents
-
- Claude Code
- Cursor
- Cline
- Codex
- Windsurf
- Gemini CLI
- +20
- Trust score
- 88 / 100 · community maintained
- Author / version / license
- @tomevault-io · no license declared
- Token usage
- Lean
- Setup complexity
- Plug-and-play
- External API key
- Not required
- Operating systems
- Unspecified (assume cross-platform)
- Runtime requirements
- No special requirements
- Permissions
-
- Read-only
- Write / modify
- Network behavior
- Local-only
- Install commands
- 26 variants
Profile is derived at build time from SKILL.md and install vectors. Subject to drift from author intent.
Heads up: 未限定 allowed-tools，默认拥有全部工具权限。
---
name: ai-review
description: Review Gemini API agent code against mandatory rules in backend/AGENTS.md Use when this capabili…
category: ai
runtime: no special runtime
---
# ai-review output preview
## PART A: Task fit
- Use case: Review Gemini API agent code against mandatory rules in backend/AGENTS.md Use when this capability is needed. Use this after creating or modifying any Gemini API agent code. This should be run as part of the code review process. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more..
- Inputs: target material, constraints, expected output, and acceptance criteria.
- Evidence boundary: follow “What I do / When to use me / Important notes” and do not present inference as author intent.
## PART B: Execution result
- **01** The card summarizes the use case; runtime output centers on “Review Gemini API agent code against mandatory rules in backend/AGENTS.md Use when this capability is needed. Use this after creating or modifying any Gemini API agent code. This should be run as part of the code review process. runs entirely locally. Works with Claude Code, Cursor, Cline and 23 more.”.
- **02** When the source has headings, the agent prioritizes “What I do / When to use me / Important notes” so the result follows the author’s structure.
- **03** Typical output includes task judgment, concrete steps, required commands or file edits, validation, and follow-up options.
- **04** Risk context follows the fingerprint: read files, write/modify files; mostly runs locally; usually needs no extra API key.
## Running Rules
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding scope.
- Return the result, validation criteria, and next iteration options. Choose the trigger
The source does not require a stable slash command. After installation, invoke the skill by name and describe the task.
Provide inputs and boundaries
Name target files or source material, expected output, forbidden changes, and whether network or shell access is allowed. Permission fingerprint: read files, write/modify files.
Validate with a small run
Start with a small task and check whether the result follows “What I do / When to use me / Important notes”. Inspect diffs, logs, previews, or tests before expanding scope.
Review before delivery
Confirm the final output includes a concrete result, evidence, and next action. If it stays generic, tighten inputs, boundaries, and acceptance criteria.
---
name: ai-review
description: Review Gemini API agent code against mandatory rules in backend/AGENTS.md Use when this capabili…
category: ai
source: tomevault-io/skills-registry
---
# ai-review
## When to use
- Review Gemini API agent code against mandatory rules in backend/AGENTS.md Use when this capability is needed. Use this…
- Use it when the task has clear inputs, repeatable steps, and validation criteria.
## What to provide
- Target material, scope, expected result, and forbidden changes.
- Whether network, commands, file writes, or external services are allowed.
## Execution rules
- Organize steps around “What I do / When to use me / Important notes” and keep inference separate from source facts.
- read files, write/modify files; mostly runs locally; usually needs no extra API key.
- Validate with a small sample before expanding the task.
## Output requirements
- Return the deliverable, key evidence, validation method, and next action.
- Mark missing information as unknown; do not invent commands, platforms, or dependencies. Evidence boundary and execution chain
The author source anchors workflow facts; repository files anchor sources and commands; Fluxly only adds fit, limitations, and quality judgment.
skill "ai-review" {
input -> user goal + target files + boundaries + acceptance criteria
context -> What I do / When to use me / Important notes
rules -> SKILL.md triggers / order / output contract
runtime -> no special runtime | read files, write/modify files | mostly runs locally
guardrails -> usually needs no extra API key + small-sample validation + diff/log review
output -> copyable result + checklist + next iteration
}What I do
- Read
backend/AGENTS.mdto get the mandatory rules for Gemini API - Review the changed or new files that contain Gemini API agent code
- Check for:
- Rate limiting (10/hour per user for AI endpoints)
- Proper structured output schema handling
- Error handling and retry logic
- Correct client initialization
- No hardcoded API keys
- Report any violations with specific line references
When to use me
Use this after creating or modifying any Gemini API agent code. This should be run as part of the code review process.
Important notes
- The rules in
backend/AGENTS.mdare mandatory for all AI agent implementations - Focus on the specific rules in that file - don't make up additional requirements
- Provide actionable feedback with file:line references for any issues found
Source: Arkokat/hearthkeeper — distributed by TomeVault.
Decide Fit First
Design Intent
How To Use It
Boundaries And Review