Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add calesthio/generative-media-skills --skill google-gemini-imagegit clone --depth 1 https://github.com/calesthio/generative-media-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/calesthio/generative-media-skills/google-gemini-image)<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/google-gemini-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/google-gemini-image/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/calesthio/generative-media-skills/google-gemini-image"><img src="https://agentmods.dev/badge/skills/calesthio/generative-media-skills/google-gemini-image.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 320 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 247 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 316 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00132 | $0.08222 |
| Opus 5 | $0.00066 | $0.04111 |
| Sonnet 5 | $0.00026 | $0.01644 |
| Haiku 4.5 | $0.00013 | $0.00822 |
Grade A, and why
google-gemini-image scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 514 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Produce still images with Gemini
Treat this as a production discipline, not a bag of adjectives. Establish rights and delivery constraints, choose a route and model, assign references explicit roles, generate a reviewable draft, and repair one defect class at a time.
Evidence labels and freshness
Interpret labels consistently:
- Documented fact: stated in a cited Google first-party source.
- Inference: a conclusion drawn from documented capabilities; validate it on the actual workload.
- Production heuristic: operational advice, not a provider guarantee.
All volatile facts in this skill were verified 2026-07-09. Recheck model IDs, launch stages, locations, pricing, quotas, API schemas, retention, and deprecation dates before a consequential run. Provider words such as “best” or “professional” are positioning, not independent benchmark results.
Bound the job before calling a model
Collect or infer these fields. Stop for user input when an assumption would alter rights, identity, factual meaning, or required deliverables.
deliverable: file count, channel, crop/aspect ratio, minimum pixels, file type
intent: what the image must communicate and to whom
must_preserve: identities, product geometry, approved logo, exact copy, legal marks
may_change: background, lighting, styling, pose, crop, color treatment
references: file -> role -> rights/consent -> priority
factuality: timeless invention | supplied facts | current facts requiring grounding
privacy: public | internal | confidential | personal/biometric
acceptance_tests: exact strings, subject match, layout, factual checks, brand checks
route_constraints: Gemini Developer API or Google Cloud; latency/cost/batch needs
Do not cover Veo, motion generation, or Gemini Live/audio. Gemini 3.1 Flash Image and Gemini 3.1 Flash-Lite Image can accept video as context for a still-image result through generateContent, but that is an image workflow; do not let it expand this skill into video production.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 514 lines · 132 tokens per session scan A 339e31e51950
google-gemini-image is a skill published in the GitHub repository calesthio/generative-media-skills (170 stars, last pushed 2mo ago), licensed MIT. It adds 132 tokens to every session and 8,222 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
cliptalk-cover-director
Produces evidence-backed cover candidates and reviewable cover variants for a ClipTalk video. Use when the user asks for a cover, poster frame, thumbnail, or multiple cover directions; do not use for timeline editing or social-video reframing.
cliptalk-smart-reframe
Creates a subject-aware, time-varying crop track and a review-only social-format preview from an accepted ClipTalk cut. Use for automatic vertical, square, or portrait reframing; do not use for a fixed manual crop or before content editing is accepted.
cliptalk-content-extractor
Locates and assembles source passages matching a semantic request. Use for extracting explanations, topics, quotes, demonstrations, or other specifically described content.
cliptalk-interview-editor
Produces a coherent interview edit by combining speaker discovery, topic selection, dialogue context, cleanup, subtitles, and preview. Use for interviews, podcasts, testimonials, or question-and-answer recordings.
cliptalk-shortform-hook-director
Finds and assembles a reviewable short-form cut with a strong opening hook. Use for Shorts, Reels, social clips, talking-head cutdowns, or requests for a punchier opening.
cliptalk-social-reframe-exporter
Creates a review-only 9:16, 4:5, 1:1, or 16:9 version from an existing accepted ClipTalk cut, then checks the rendered preview. Use only when a cut already exists and the user asks to adapt it for Shorts, Reels, Douyin, Xiaohongshu, WeChat Channels, or square feeds; do not use when the user still needs content found…