Local Platform E2E
computesdk/benchmarks
Stand up benchmarks-platform locally (Postgres + MinIO + ClickHouse in docker) and run a real @benchsdk/runner benchmark against it, with no cloud or provider credentials.
Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model).
Install Pgjev
$ npx skills add realZachi/pg-jev --skill pgjev -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install realZachi/pg-jev pgjev --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/realZachi/pg-jev.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/pgjev .claude/skills/pgjev && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "pgjev" agent skill from https://github.com/realZachi/pg-jev/tree/master/.agents/skills/pgjev into .claude/skills/pgjev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pgjev", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/realZachi/pg-jev/tree/master/.agents/skills/pgjevType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add realZachi/pg-jev --skill pgjev -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install realZachi/pg-jev pgjev --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/realZachi/pg-jev.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/pgjev .agents/skills/pgjev && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "pgjev" agent skill from https://github.com/realZachi/pg-jev/tree/master/.agents/skills/pgjev into .agents/skills/pgjev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pgjev", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add realZachi/pg-jev --skill pgjev -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install realZachi/pg-jev pgjev --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/realZachi/pg-jev.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/pgjev .cursor/skills/pgjev && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "pgjev" agent skill from https://github.com/realZachi/pg-jev/tree/master/.agents/skills/pgjev into .cursor/skills/pgjev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pgjev", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/realZachi/pg-jev.git --path .agents/skills/pgjev--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add realZachi/pg-jev --skill pgjev -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install realZachi/pg-jev pgjev --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/realZachi/pg-jev.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/pgjev .gemini/skills/pgjev && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "pgjev" agent skill from https://github.com/realZachi/pg-jev/tree/master/.agents/skills/pgjev into .gemini/skills/pgjev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pgjev", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install realZachi/pg-jev pgjevInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add realZachi/pg-jev --skill pgjev -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/realZachi/pg-jev.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/pgjev .github/skills/pgjev && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "pgjev" agent skill from https://github.com/realZachi/pg-jev/tree/master/.agents/skills/pgjev into .github/skills/pgjev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pgjev", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add realZachi/pg-jev --skill pgjev -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install realZachi/pg-jev pgjev --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/realZachi/pg-jev.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/pgjev .opencode/skills/pgjev && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "pgjev" agent skill from https://github.com/realZachi/pg-jev/tree/master/.agents/skills/pgjev into .opencode/skills/pgjev/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "pgjev", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
pgjev- GitHub stars
- 1.1k
- Token cost
- ~2.9k tokens
- SKILL.md length
- 1,466 words
- Files
- 9 (incl. scripts, references)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model).
- Works in 4 steps: Check the target server: bash… → Install the extension files (nothing to… → Configure the API key (from… → …
- A user mentions pgjev
- SKILL.md covers Figure out which job you have, Install, Write a query and Explain, plus 2 more sections
- Runs Shell scripts from its folder; calls make, bash and pip; reaches pgjev.com; needs TYPESAFE_API_KEY and POSTGRES_PASSWORD
What it does
Pgjev is an agent skill from realZachi/pg-jev. Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model). Use this skill whenever a user mentions pgjev, pg-jev, the jev extension, jev(), jevprob, jevchoice, jevscore, a "natural-language WHERE clause", "ask my Postgres table a question", classifying or scoring rows with AI inside Postgres, or hits an error starting with jev:. Covers "install pgjev on my server / in Docker", "write a query that picks…
Its SKILL.md is about 2.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 10 other files, including scripts and reference files (for example `references/functions.md`, `references/how-it-works.md` and `references/install.md`).
It sits in Writing & Content, covering Plain language and style rules, QA and bug reports and Containers. It works with PostgreSQL and Docker. The repository describes itself as: Ask your Postgres tables questions in plain language. A PostgreSQL extension powered by TypeSafe's Jev.
When your agent uses it
- A user mentions pgjev
- The jev extension
- A natural-language WHERE clause
- Ask my Postgres table a question
Example prompts
- “natural-language WHERE clause”
- “ask my Postgres table a question”
- “install pgjev on my server / in Docker”
- “/pgjev”
Requirements
- Python 3
- A Bash shell
- Docker
- A credential in TYPESAFE_API_KEY
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- Check the target server: bash scripts/check_server.sh [psql connection args]. It reports the version,
- Install the extension files (nothing to compile; PGXS just copies jev.control + SQL). Pick one
- Configure the API key (from https://console.typesafe.ai). Three options, pick what fits the deployment
- Verify: psql -d mydb -f scripts/smoke_test.sql. It creates a temp table, runs each function once, and
What it can do on your machine
Read from SKILL.md and the folder at commit e3450d4. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
makebashpipdockerpsql
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
pgjev.com
Also links to:
github.comconsole.typesafe.ai
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
TYPESAFE_API_KEYPOSTGRES_PASSWORD
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Pgjev loads about 2.9k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 177 tokens; SKILL.md has 1,466 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,466 words (~2,947 tokens).
“jev(table, 'condition') is an ordinary boolean SQL function. Every row is sent to TypeSafe's Jev model (a "System One" model that returns calibrated probabilities, not text) and judged against the condition. No index, no embeddings, no vector column. The sibling…”
- name
- pgjev
Files
SKILL.md and 8 other files (scripts, references) in .agents/skills/pgjev of realZachi/pg-jev.
- SKILL.md
- references/functions.md
- references/how-it-works.md
- references/install.md
- references/query-patterns.md
- references/settings.md
- scripts/check_server.sh
- scripts/install.sh
- scripts/smoke_test.sql
Open the folder on GitHubat commit e3450d4
Compare with similar skills
Pgjev next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Pgjev this skillrealZachi/pg-jev | 1.1k | — | ~2.9k | Automated safety check: Pass | Custom licence | |
| Local Platform E2Ecomputesdk/benchmarks | 126 | — | ~3k | Automated safety check: Notes | MIT | |
| Local Stacktheopenco/llmgateway | 1.7k | — | ~1.6k | Automated safety check: Notes | Custom licence | |
| DeerFlow Smoke Testbytedance/deer-flow | 84k | — | ~2.5k | Automated safety check: Notes | MIT | |
| SQL Database Support for pRESTprest/prest | 4.6k | — | ~1.6k | Automated safety check: Pass | MIT | |
| Cb Build TestBlkLeg/CircuitBreaker | 201 | — | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
Local Stack
theopenco/llmgateway
Run an isolated per-worktree LLM Gateway stack — own Postgres, Redis, storage Redis, and app ports — and tear it down safely.
DeerFlow Smoke Test
bytedance/deer-flow
Walks through an end-to-end smoke test of a DeerFlow deployment: pull the latest code, deploy with Docker or locally, verify services, run health checks and write a report.
SQL Database Support for pREST
prest/prest
Guides classifying, gap-analyzing and scaffolding support for a new SQL database in pREST, from Postgres-compatible variants to entirely new dialects.
Cb Build Test
BlkLeg/CircuitBreaker
How Circuit Breaker is built, tested, packaged, and kept secret-safe — the make dev/verify/test targets, the PostgreSQL integration test database and its fixtures, the mono Docker image and native…
Monstermq Broker Config
vogler75/monster-mq
Guide for configuring, deploying, and operating the MonsterMQ broker.
Related
Works with
Categories
Questions about Pgjev
What does Pgjev do?
Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model). Pgjev is an agent skill from realZachi/pg-jev. Install, configure, query and explain pgjev (the jev PostgreSQL extension that filters, ranks and classifies rows with plain-language conditions via TypeSafe's Jev model).
When should I use Pgjev?
Pgjev fits situations like: A user mentions pgjev; the jev extension; A natural-language WHERE clause; ask my Postgres table a question.
How do I install Pgjev in Claude Code?
Run `npx skills add realZachi/pg-jev --skill pgjev -a claude-code`. Or copy the skill folder (.agents/skills/pgjev in realZachi/pg-jev) into .claude/skills/pgjev in your project. Claude Code loads it when a task matches its description.
How do I install Pgjev in Codex?
Run `npx skills add realZachi/pg-jev --skill pgjev -a codex`. Or copy the skill folder (.agents/skills/pgjev in realZachi/pg-jev) into .agents/skills/pgjev in your project. Codex loads it when a task matches its description.
Can I use Pgjev in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add realZachi/pg-jev --skill pgjev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/pgjev, .gemini/skills/pgjev, .github/skills/pgjev and .opencode/skills/pgjev in your project.
What does Pgjev need to run?
Going by SKILL.md and its folder, Pgjev needs a shell for the scripts in its folder, the command-line tools its instructions call (make, bash, pip, docker and psql) and credentials named TYPESAFE_API_KEY and POSTGRES_PASSWORD. Our summary lists: Python 3; A Bash shell; Docker; A credential in TYPESAFE_API_KEY.
Does Pgjev access the network?
SKILL.md names 3 domains. In commands or code: pgjev.com; the agent is likely to contact it when it follows the instructions. As links in the text: github.com and console.typesafe.ai. This is read from the text; nothing was executed.
Is Pgjev safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Pgjev use?
Pgjev has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Pgjev use?
About 2.9k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 8.1k tokens, read only when the agent opens those files.
What are the alternatives to Pgjev?
Skills that share tags, products or a category with Pgjev: Local Platform E2E (computesdk/benchmarks, 126 stars), Local Stack (theopenco/llmgateway, 1.7k stars), DeerFlow Smoke Test (bytedance/deer-flow, 84k stars) and SQL Database Support for pREST (prest/prest, 4.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Pgjev?
realZachi (a GitHub user) maintains it in realZachi/pg-jev, which has 1,069 GitHub stars. The repository was last updated on October 6, 2026.
Source: realZachi/pg-jev on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.