Skip to content
Skills Library
AI & agents · Review & audit

dev_invoke_gemini-cli

/dev_invoke_gemini-cli

Legacy Claude-only provider orchestration for Google Gemini CLI using markdown file handoff. Write review request to REVIEW.md, Gemini analyzes, outputs findings to FINDINGS.md. Use only when the user explicitly requests Gemini. Do not trigger for generic QAQC, quality assurance, security review, architecture review, or second-opinion requests. Triggers: gemini, gemini cli, delegate to gemini, gemini subagent, gemini-3-pro-preview, gemini-3-flash-preview Prerequisites: Gemini CLI authenticated (gemini login or GEMINI_API_KEY) Models: gemini-3-pro-preview (default), gemini-3-flash-preview (larg

Licence
MIT
Last repository change
26.10.2026

Assessment and security

95/ 100Class: good
Format20 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Legacy Claude-only provider orchestration for Google Gemini CLI using markdown file handoff. Write review request to REVIEW.md, Gemini analyzes, outputs findings to FINDINGS.md. Use only when the user explicitly requests Gemini. Do not trigger for generic QAQC, quality assurance, security review, architecture review, or second-opinion requests. Triggers: gemini, gemini cli, delegate to gemini, gemini subagent, gemini-3-pro-preview, gemini-3-flash-preview Prerequisites: Gemini CLI authenticated (gemini login or GEMINI_API_KEY) Models: gemini-3-pro-preview (default), gemini-3-flash-preview (larg

Original author description

Legacy Claude-only provider orchestration for Google Gemini CLI using markdown file handoff. Write review request to REVIEW.md, Gemini analyzes, outputs findings to FINDINGS.md. Use only when the user explicitly requests Gemini. Do not trigger for generic QAQC, quality assurance, security review, architecture review, or second-opinion requests. Triggers: gemini, gemini cli, delegate to gemini, gemini subagent, gemini-3-pro-preview, gemini-3-flash-preview Prerequisites: Gemini CLI authenticated (gemini login or GEMINI_API_KEY) Models: gemini-3-pro-preview (default), gemini-3-flash-preview (larg

How it works

  1. Pattern: Markdown File Handoff
  2. Model Selection
  3. Invocation
  4. Core Flags Reference
  5. Review Request Template (REVIEW.md)
  6. Findings Template (FINDINGS.md)
  7. Workflow Example (ras-commander)
  8. Environment Variables
  9. Rate Limits
  10. Session Management
Original SKILL.md headings · 279 lines, 1,038 words
SKILL.md preview
---
name: dev_invoke_gemini-cli
description: |
  Legacy Claude-only provider orchestration for Google Gemini CLI using markdown file handoff.
  Write review request to REVIEW.md, Gemini analyzes, outputs findings to FINDINGS.md.
  Use only when the user explicitly requests Gemini. Do not trigger for generic QAQC,
  quality assurance, security review, architecture review, or second-opinion requests.

  Triggers: gemini, gemini cli, delegate to gemini, gemini subagent,
  gemini-3-pro-preview, gemini-3-flash-preview

  Prerequisites: Gemini CLI authenticated (gemini login or GEMINI_API_KEY)
  Models: gemini-3-pro-preview (default), gemini-3-flash-preview (large context)
shared_corpus: false
harness_scope: claude_only
---

# Invoking Gemini CLI

> Legacy Claude-only orchestration skill. This is not part of the standard production harness policy. It is excluded from the shared multi-harness corpus and should be used only when the user explicitly requests Gemini.

When the user explicitly requests Gemini, delegate the requested review or analysis task to Gemini CLI using markdown files for input and output. Write review criteria to REVIEW.md, invoke Gemini, then read FINDINGS.md for results.

## Pattern: Markdown File Handoff

```
Claude Code                         Gemini CLI
    |                                   |
    +-- Write REVIEW.md ----------------+
    |   (code + review criteria)        |
    |                                   |
    +-- Execute: gemini -y "Read        |
    |   REVIEW.md, analyze, write       |
    |   findings to FINDINGS.md"        |
    |                                   |
    |                                   +-- Reads REVIEW.md
    |                                   +-- Analyzes content
    |                                   +-- Writes FINDINGS.md
    |                                   |
    +-- Read FINDINGS.md <--------------+
    |   (analysis + recommendations)    |
    v                                   v
```

**Benefits**:
- Eliminates shell escaping issues
- Keeps context structured in reviewable files
- Enforces explicit output structure
- Supports session resume

## Model Selection

| Model | Use Case | Status |
|-------|----------|--------|
| `gemini-3-pro-preview` | **Default.** Strong reasoning | CLI default |
| `gemini-3-flash-preview` | Large context, fast analysis | For big codebases |

**Recommendation**: Use default `gemini-3-pro-preview` for most tasks. Switch to `gemini-3-flash-preview` for very large context (>100K tokens) via `-m` flag.

**Note**: If you encounter 429 capacity errors with `gemini-3-pro-preview`, retry or wait briefly.

## Invocation

### Standard Pattern Within This Legacy Skill

```bash
cd /path/to/project && gemini -y "Read REVIEW.md in the current directory. Follow the review criteria. Write all findings to FINDINGS.md."
```

### With Explicit Model

```bash
cd /path/to/project && gemini -y -m gemini-3-flash-preview "Read REVIEW.md, analyze per criteria, write findings to FINDINGS.md"
```

### Resume Session

```bash
gemini -r <session_id> "Read REVIEW.md for updated criteria, append to FINDINGS.md"
```

## Core Flags Reference

| Flag | Purpose |
|------|---------|
| `-y` | YOLO mode - auto-approve all actions |
| `-m <model>` | Model: `gemini-3-pro-preview`, `gemini-3-flash-preview` |
| `-r <id>` | Resume session by ID |
| `--output-format json` | JSON output for parsing |
| `--list-sessions` | List available sessions |

## Review Request Template (REVIEW.md)

```markdown
# Review Request: [Brief Title]

## Objective
[What kind of review/analysis is needed]

## Review Criteria
Rate each finding: CRITICAL | HIGH | MEDIUM | LOW

### Security
- SQL injection vulnerabilities
- XSS risks
- Authentication/authorization issues
- Hardcoded secrets

### Reliability
- Error handling gaps
- Edge cases not covered
- Race conditions
- Resource leaks

### Performance
- N+1 query patterns
- Unnecessary allocations
- Missing caching opportunities

### Maintainability
- Code clarity
- Naming conventions
- Documentation gaps

## Code to Review

### File: src/api/users.ts
```typescript
// Paste code here or reference file
```

### File: src/services/auth.ts
```typescript
// Paste code here
```

## Context
[Any relevant background, constraints, or requirements]

## Output Format
Write to FINDINGS.md with:
- Summary of review
- Findings table with severity, location, description
- Specific recommendations
- Overall assessment
- Session ID for follow-up
```

## Findings Template (FINDINGS.md)

Instruct Gemini to produce:

```markdown
# Review Findings: [Title]

## Summary
[Brief overview of review results]

## Findings

| Severity | Location | Issue | Recommendation |
|----------|----------|-------|----------------|
| CRITICAL | users.ts:45 | SQL injection via unsanitized input | Use parameterized queries |
| HIGH | auth.ts:23 | Missing rate limiting on login | Add rate limiter middleware |
| MEDIUM | users.ts:78 | No input validation | Add schema validation |
| LOW | auth.ts:12 | Magic number | Extract to named constant |

## Detailed Analysis

### CRITICAL: SQL Injection (users.ts:45)
[Detailed explanation with code example]

### HIGH: Missing Rate Limiting (auth.ts:23)
[Detailed explanation with recommendation]

## Recommendations
1. [Priority action items]
2. [Secondary improvements]

## Overall Assessment
[Summary judgment: PASS | NEEDS WORK | FAIL]

## Session
Session ID: `<id>` (for follow-up questions)
```

## Workflow Example (ras-commander)

### 1. Write REVIEW.md

```markdown
# Review Request: Remote Execution Security

## Objective
Security review of the PsExec-based remote execution module.

## Review Criteria
Rate findings: CRITICAL | HIGH | MEDIUM | LOW

Focus on:
- Command injection vulnerabilities
- Credential exposure
- Path traversal risks
- Session hijacking

## Code to Review

### File: ras_commander/remote/PsexecWorker.py
```python
[paste relevant code]
```

### File: ras_commander/remote/Execution.py
```python
[paste relevant code]
```

## Context
- This module executes HEC-RAS remotely via PsExec
- Runs with elevated privileges on remote Windows machines
- Handles user credentials for authentication

## Output Format
Write to FINDINGS.md with severity-rated findings and specific mitigations.
```

### 2. Execute Gemini

```bash
cd "C:/GH/ras-commander" && gemini -y "Read REVIEW.md, perform security review per criteria, write findings to FINDINGS.md"
```

### 3. Read FINDINGS.md

Review the findings, address issues, and continue development.

## Environment Variables

```bash
GEMINI_API_KEY=xxx         # Required (or use OAuth login)
GOOGLE_API_KEY=xxx         # Alternative (takes precedence)
```

## Rate Limits

| Limit | Value |
|-------|-------|
| Requests/minute | 60 |
| Requests/day | 1,000 |

## Session Management

- Session ID appears in Gemini output
- Use `gemini --list-sessions` to see available sessions
- Resume with `gemini -r <id> "follow-up instruction"`

## Tips

1. **Paste actual code** - Don't describe, include the real code in REVIEW.md
2. **Define severity levels** - CRITICAL/HIGH/MEDIUM/LOW helps prioritization
3. **Specify output structure** - Tell Gemini exactly what FINDINGS.md should contain
4. **Provide context** - Domain, compliance requirements, constraints
5. **Ask focused questions** - One review type per request gets better results

## Legacy Capability Notes

Codex is the production-supported second harness for this repository. Use this
legacy Gemini path only when the user explicitly asks for Gemini.

**Use Codex by default for**:
- QAQC and code review
- Security review
- Complex implementation
- Extended thinking tasks
- Multi-file refactoring

**Use this Gemini path only for**:
- explicit Gemini requests
- reproducing historical Gemini-based review workflows

**Use specialized ras-commander agents for**:
- HDF analysis -> `hdf-analyst`
- Geometry parsing -> `geometry-parser`
- USGS integration -> `usgs-integrator`

## Cross-References

**Agents** (delegate when needed):
- `code-oracle-gemini` -- Delegate for large context Gemini analysis

**Skills** (related workflows):
- `dev_invoke_codex-cli` -- Alternative: Codex CLI for deep reasoning
- `dev_invoke_kimi-cli` -- Alternative: Kimi CLI for test generation
- `qa_review_triple-model` -- Uses this skill as one of three reviewers

Versions

The database has no other skills named dev_invoke_gemini-cli.

Database snapshot: 13.11.2026 · package version 60412b198b00 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100gemini
    Provides Gemini CLI delegation workflows for large-context analysis and complex reasoning using Gemini 3.0 Flash and Gemini 3.0 Pro models, including English prompt formulation, execution flags, and safe result handling. Use when the user explicitly asks to use Gemini for tasks…
  • 100gemini-cli
    Run Gemini CLI for AI queries. Use when user asks to "run/ask/use gemini", compare Claude vs Gemini, or delegate tasks to Gemini.
  • 95dev_invoke_kimi-cli
    Legacy Claude-only provider orchestration for Opencode CLI using Kimi K2.5 via markdown file handoff. Write test request to TASK.md, Opencode with Kimi K2.5 generates tests/reviews, outputs to OUTPUT.md. Use only when the user explicitly requests Kimi or Opencode/Kimi. Do not…
  • 95qa_review_triple-model
    Legacy Claude-only provider-mixed review workflow using Opus, Gemini, Codex, and Kimi K2.5. Each reviewer writes findings to separate markdown files, then orchestrator synthesizes. Use only when the user explicitly requests triple review, quad review, multi-model review, Gemini,…
  • 100gemini
    Expert Google Gemini API assistance covering Gemini 1.5 Pro / Flash, multimodal reasoning (audio, video, PDF), and structured outputs. Use when building multi-modal AI applications with Google's foundation models.
  • 100gemini
    Use when the user asks to run Gemini CLI (gemini, gemini resume) or references Google Gemini for code analysis, refactoring, or automated editing

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.