gemini-agents
phuryn/product-engineeringAI & ML engineeringProduct & project management
gemini-agents is a skill in phuryn/product-engineering, last changed 18 Nov 2026. It can touch credentials, run shell commands, reach the network, name web addresses and bundle scripts — read the findings before installing.
'Ask Gemini', 'have Gemini build or review this': Google's Antigravity CLI as a partner. It may break Google's terms on a consumer plan, so the user agrees first.
At a glance
What it can touch
How much a skill can do, not whether it is risky.
Pattern check
1 item to review
Web address that is a bare IP number
R06 · High · SKILL.md:136Commit 8ebb50b · 20 Nov 2026
How the check worksPattern check:1 item to reviewSee it
QAI Index
We rate every listed skill the same way, from 0 to 100.
A guide to compare by, not a verdict on the skill.
How it's scoredGet an email when its check changes.
Keep it with the other skills you use, installed with one command.
Install
Sign in to see how to install it
Free with Google or an email link, no password needed. Then pick your agent and copy its steps.
What it can touch
Sign in to see the file and line behind each one
The summary at the top stays open to everyone. Signing in is free, with Google or an email link.
Pattern check
Pattern check: 1 item to review · commit 8ebb50b · 20 Nov 2026
We checked every text file in this skill, at commit 8ebb50b on 20 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.
How the check worksReport an incorrect finding
Outside links we did not follow
- http://1.1.1.1
Format check
Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.
Agent Skills specPasses with warnings
The format our Agent Skills docs set out, held to the strictest version of each rule among the agents we check.
- Warning
The body is about 5,692 tokens (approx.); the spec suggests under 5,000. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
The description doesn't say when to use the skill. D6
Fix: Add a sentence such as "Use when …" naming the requests or files that should trigger it.
- Note
There is no license field, so readers can't tell whether they may reuse the skill. O2
Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
- Warning
Claude CodePasses
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Note
The body is about 5,692 tokens (approx.); the spec suggests under 5,000. After compaction Claude Code keeps only the first 5,000 tokens of a skill. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
Claude apps & API uploadPasses
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Note
The body is about 5,692 tokens (approx.); the spec suggests under 5,000. Anthropic's guidance says the same. B2
Fix: Move detail into reference files that the agent reads only when needed.
- Note
- OpenAI (Codex & API)Passes
- VS Code & CopilotPasses
SKILL.md
Files
4 files
| Path | Size |
|---|---|
| SKILL.md (opens in a new tab) | 22.5 KB |
| receipts.md (opens in a new tab) | 11.5 KB |
| scripts/agy.py (opens in a new tab) | 71.1 KB |
| scripts/test_agy.py (opens in a new tab) | 84.1 KB |
Changelog
Newest first: each commit that changed its folder on GitHub, and each change to its listing here.
- Listed on QAI
- Updated: Simplify the skills: less routine work, one home per rule, rare detai… (a2b0820 (opens in a new tab))
- Updated: Review once per phase; options carry a size; four tool fixes (8166e1b (opens in a new tab))
- Updated: Every stage ends with end-to-end tests and current docs (7003d4e (opens in a new tab))
- Updated: Round 146: a Gemini review counts file-tool reads only (50ee90f (opens in a new tab))
- Updated: Round 145: a review must read its subject, and a repository's hooks s… (56a016b (opens in a new tab))
- Updated: gemini-agents: Google's Antigravity CLI as a partner the user agrees … (035773d (opens in a new tab))
QAI Index badge
Show this skill's QAI Index in a README or on a website. It links back to this page and changes when we refresh the catalog.
[](https://qai.io/skills/phuryn/product-engineering/gemini-agents)More from phuryn/product-engineering
| Skill | QAI Index | What it can touch | Pattern check | Licence | Updated |
|---|---|---|---|---|---|
agent-instructionsWriting or restructuring AGENTS.md or CLAUDE.md, adding a rule ('remember this'), or after an agent ignored a rule it had: make each rule get met when it applies. 64/QI
Pattern check: Nothing flaggedMITUpdated 18 Nov 2026 | 64/QI |
| Pattern check: Nothing flagged | MIT | 18 Nov 2026 |
app-lifecyclePlanning a SaaS stage, 'what's next', 'where are we', calling a stage done: the detailed path from an idea to production, each stage with its done-when. 59/QI
Pattern check: Nothing flaggedMITUpdated 20 Nov 2026 | 59/QI |
| Pattern check: Nothing flagged | MIT | 20 Nov 2026 |
beachhead-segmentChoosing the first market or customer segment to win, scored on burning pain, willingness to pay, winnable share and referrals. 64/QI
Pattern check: Nothing flaggedMITUpdated 18 Nov 2026 | 64/QI |
| Pattern check: Nothing flagged | MIT | 18 Nov 2026 |
chatgpt-pluginBefore building, submitting or changing a ChatGPT plugin or Apps SDK app: get it through OpenAI's directory review (auth, package, OAuth, data rules, portal). 63/QI
Pattern check: Nothing flaggedMITUpdated 8 Nov 2026 | 63/QI |
| Pattern check: Nothing flagged | MIT | 8 Nov 2026 |
claude-agents'Ask Claude', 'have Claude build or review this': drive Claude Code headless (claude -p) from another agent as a peer, builder or fresh reviewer. 59/QI
Pattern check: Nothing flaggedMITUpdated 18 Nov 2026 | 59/QI |
| Pattern check: Nothing flagged | MIT | 18 Nov 2026 |
clerk-productionSetting up or changing Clerk sign-in, organizations, roles or billing on Next.js, or sign-in that does nothing or lands wrong: Clerk in production. 64/QI
Pattern check: Nothing flaggedMITUpdated 18 Nov 2026 | 64/QI |
| Pattern check: Nothing flagged | MIT | 18 Nov 2026 |
Other AI & ML engineering skills
Same category, most repo stars first.