Chdb SQL
vemetric/vemetric
A skill your agent uses when the user wants to run SQL — especially analytical SQL — on local files (parquet/csv/json), URLs, S3 paths, or remote databases (Postgres, MySQL, MongoDB, ClickHouse…
Runs read-only SQL queries and schema exploration against PostgreSQL databases declared in .env, chosen by label or index, with writes blocked unless a connection allows them.
Install Postgres Query Client
$ npx skills add evolution-foundation/evo-nexus --skill db-postgres -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install evolution-foundation/evo-nexus db-postgres --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/evolution-foundation/evo-nexus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/db-postgres .claude/skills/db-postgres && 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 "db-postgres" agent skill from https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/db-postgres into .claude/skills/db-postgres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-postgres", 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/evolution-foundation/evo-nexus/tree/main/.claude/skills/db-postgresType 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 evolution-foundation/evo-nexus --skill db-postgres -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install evolution-foundation/evo-nexus db-postgres --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/evolution-foundation/evo-nexus.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/db-postgres .agents/skills/db-postgres && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "db-postgres" agent skill from https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/db-postgres into .agents/skills/db-postgres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-postgres", 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 evolution-foundation/evo-nexus --skill db-postgres -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install evolution-foundation/evo-nexus db-postgres --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/evolution-foundation/evo-nexus.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/db-postgres .cursor/skills/db-postgres && 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 "db-postgres" agent skill from https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/db-postgres into .cursor/skills/db-postgres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-postgres", 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/evolution-foundation/evo-nexus.git --path .claude/skills/db-postgres--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 evolution-foundation/evo-nexus --skill db-postgres -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install evolution-foundation/evo-nexus db-postgres --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/evolution-foundation/evo-nexus.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/db-postgres .gemini/skills/db-postgres && 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 "db-postgres" agent skill from https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/db-postgres into .gemini/skills/db-postgres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-postgres", 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 evolution-foundation/evo-nexus db-postgresInstalls 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 evolution-foundation/evo-nexus --skill db-postgres -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/evolution-foundation/evo-nexus.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/db-postgres .github/skills/db-postgres && 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 "db-postgres" agent skill from https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/db-postgres into .github/skills/db-postgres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-postgres", 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 evolution-foundation/evo-nexus --skill db-postgres -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install evolution-foundation/evo-nexus db-postgres --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/evolution-foundation/evo-nexus.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/db-postgres .opencode/skills/db-postgres && 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 "db-postgres" agent skill from https://github.com/evolution-foundation/evo-nexus/tree/main/.claude/skills/db-postgres into .opencode/skills/db-postgres/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "db-postgres", 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
db-postgres- GitHub stars
- 544
- Token cost
- ~1.8k tokens
- SKILL.md length
- 383 words
- Files
- 2 (incl. scripts)
- Skills in repo
- 117
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Runs read-only SQL queries and schema exploration against PostgreSQL databases declared in .env, chosen by label or index, with writes blocked unless a connection allows them.
- Works in 4 steps: If the user doesn't specify a label, run… → Write the smallest SQL that answers the… → Run via query. Inspect the result. → …
- Querying or exploring data in a Postgres database
- SKILL.md covers Setup — one-time, per database, Usage, Output shape and Guardrails, plus 3 more sections
- Runs Python scripts from its folder; calls python3 and uv; needs DB_POSTGRES_1_PASSWORD and DB_POSTGRES_2_PASSWORD
What it does
Each database is declared in .env as a numbered block (DB_POSTGRES_1_*, DB_POSTGRES_2_* and so on) with a required label, and the agent picks one by label or index when it runs a command. A connection can be given as separate host and credential fields or as a single DSN, and the DSN wins when both are present. The bundled db_client.py script lists configured connections, health-checks one, runs a query and lists tables and schema.
Queries are read-only by default. A write is refused with a write_blocked error unless that connection's block sets ALLOW_WRITE to true. Every command prints one JSON line on stdout and reports errors as JSON on stderr with a non-zero exit, using codes such as not_found, ambiguous, driver_missing and connection_failed. When a result passes MAX_ROWS it is marked truncated and the full rows are saved to a CSV that the agent can read instead of re-running the query.
When your agent uses it
- Querying or exploring data in a Postgres database
- Auditing a table's contents with read-only SQL
- Listing the tables and schemas of a configured connection
- Health-checking a database connection from the agent
Example prompts
- “How many users signed up in the last week in msgops-dev?”
- “List all tables in the bms-prod database.”
- “Run a health check on the evo-ai-dev connection.”
- “Query the orders table in connection 2 and show the most recent rows.”
Requirements
- Python 3 with psycopg2
- A DB_POSTGRES_N_* block in .env for each database
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- If the user doesn't specify a label, run accounts to see what's configured and pick the one that matches their intent. If ambiguous, ask.
- Write the smallest SQL that answers the question — prefer aggregates, LIMIT, and EXPLAIN before dumping rows.
- Run via query. Inspect the result.
- For performance-sensitive queries, load the deep-dive references below.
What it can do on your machine
Read from SKILL.md and the folder at commit 7f5dd76. 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 1 file in scripts/ (Python), which the agent can run.
Shell commands in SKILL.md call:
python3uv
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
raw.githubusercontent.comgithub.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
DB_POSTGRES_1_PASSWORDDB_POSTGRES_2_PASSWORD
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Postgres Query Client loads about 1.8k tokens when it runs. Until then it costs about 81 tokens; SKILL.md has 383 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NoteMentions a .env fileSKILL.md:3
Query PostgreSQL databases configured in .env (DB_POSTGRES_N_*). Use when the user asks to query, explore, or audit data - NoteMentions a .env fileSKILL.md:19
Query Postgres databases declared in `.env`. Connections follow the same numbered pattern as `SOCIAL_YOUTUBE_N_*` / `SOC - NoteMentions a .env fileSKILL.md:23
Add a block to `.env` (gitignored). Increment the index per connection: - NoteMentions a .env fileSKILL.md:32
RES_1_PASSWORD=... # raw; .env is gitignored - NoteMentions a .env fileSKILL.md:114
tions` — no `DB_POSTGRES_N_*` blocks in `.env`
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 383 words (~1,776 tokens).
“Query Postgres databases declared in .env. Connections follow the same numbered pattern as SOCIAL_YOUTUBE_N_* / SOCIAL_INSTAGRAM_N_* — one block per database, labelled for humans, picked by label or index at call time.”
- name
- db-postgres
Files
SKILL.md and 1 other file (scripts) in .claude/skills/db-postgres of evolution-foundation/evo-nexus.
- SKILL.md
- scripts/db_client.py
Open the folder on GitHubat commit 7f5dd76
Compare with similar skills
Postgres Query Client 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 |
|---|---|---|---|---|---|---|
| Postgres Query Client this skillevolution-foundation/evo-nexus | 544 | — | ~1.8k | Automated safety check: Notes | Custom licence | |
| Chdb SQLvemetric/vemetric | 394 | 1 repos | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| MoviePilot Database Operationjxxghp/MoviePilot | 12k | — | ~7.1k | Automated safety check: Pass | GPL-3.0 | |
| Cloudsql Idle Connection Timeoutdivinevideo/divine-mobile | 265 | — | ~1.1k | Automated safety check: Pass | MPL-2.0 | |
| Psycopg2 Like Percent Escapedivinevideo/divine-mobile | 265 | — | ~1.1k | Automated safety check: Pass | MPL-2.0 | |
| Gaik ToolkitGAIK-project/gaik-toolkit | 100 | — | ~5.7k | Automated safety check: Pass | MIT |
Similar skills
MoviePilot Database Operation
jxxghp/MoviePilot
Inspects, queries and carefully modifies the MoviePilot SQLite or PostgreSQL database through a bundled script that reads connection settings itself, without needing the password in the prompt.
Cloudsql Idle Connection Timeout
divinevideo/divine-mobile
Fix psycopg2 "could not receive data from server: Operation timed out" or "connection already closed" errors when using Cloud SQL with long-running Python scripts.
Psycopg2 Like Percent Escape
divinevideo/divine-mobile
Fix psycopg2 "IndexError: tuple index out of range" when using LIKE with parameterized queries.
Gaik Toolkit
GAIK-project/gaik-toolkit
GAIK toolkit overview and reference. An agent skill from GAIK-project/gaik-toolkit.
Ravendb
ravendb/docs
Read this before writing any RavenDB query, client call or /databases/ request.
More from evolution-foundation/evo-nexus
All 117 skills in this repoAI Image Creator
evolution-foundation/evo-nexus
Generates PNG images through OpenRouter models, with transparent backgrounds and reference-image edits, and describes existing images with multimodal vision.
MongoDB Query Client
evolution-foundation/evo-nexus
Runs read-only MongoDB finds, aggregations and collection listings against databases named in your .env, choosing the connection by label or index.
MySQL and MariaDB Query Tool
evolution-foundation/evo-nexus
Queries MySQL or MariaDB databases declared in .env by label, read-only by default unless a connection explicitly allows writes.
Redis Inspector
evolution-foundation/evo-nexus
Reads keys and server state from Redis instances configured in .env through a read-only Python client, choosing connections by label or index.
Int Bling
evolution-foundation/evo-nexus
Bling ERP integration via API v3. An agent skill from evolution-foundation/evo-nexus.
Int Evo CRM
evolution-foundation/evo-nexus
Query and manage Evo AI CRM data via REST API. An agent skill from evolution-foundation/evo-nexus.
Related
Works with
Categories
Questions about Postgres Query Client
What does Postgres Query Client do?
Runs read-only SQL queries and schema exploration against PostgreSQL databases declared in .env, chosen by label or index, with writes blocked unless a connection allows them. env as a numbered block (DB_POSTGRES_1_*, DB_POSTGRES_2_* and so on) with a required label, and the agent picks one by label or index when it runs a command. A connection can be given as separate host and credential fields or as a single DSN, and the DSN wins when both are present.
When should I use Postgres Query Client?
Postgres Query Client fits situations like: querying or exploring data in a Postgres database; auditing a table's contents with read-only SQL; listing the tables and schemas of a configured connection; health-checking a database connection from the agent.
How do I install Postgres Query Client in Claude Code?
Run `npx skills add evolution-foundation/evo-nexus --skill db-postgres -a claude-code`. Or copy the skill folder (.claude/skills/db-postgres in evolution-foundation/evo-nexus) into .claude/skills/db-postgres in your project. Claude Code loads it when a task matches its description.
How do I install Postgres Query Client in Codex?
Run `npx skills add evolution-foundation/evo-nexus --skill db-postgres -a codex`. Or copy the skill folder (.claude/skills/db-postgres in evolution-foundation/evo-nexus) into .agents/skills/db-postgres in your project. Codex loads it when a task matches its description.
Can I use Postgres Query Client 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 evolution-foundation/evo-nexus --skill db-postgres -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/db-postgres, .gemini/skills/db-postgres, .github/skills/db-postgres and .opencode/skills/db-postgres in your project.
What does Postgres Query Client need to run?
Going by SKILL.md and its folder, Postgres Query Client needs Python for the scripts in its folder, the command-line tools its instructions call (python3 and uv) and credentials named DB_POSTGRES_1_PASSWORD and DB_POSTGRES_2_PASSWORD. Our summary lists: Python 3 with psycopg2; A DB_POSTGRES_N_* block in .env for each database.
Does Postgres Query Client access the network?
SKILL.md names 2 domains. As links in the text: raw.githubusercontent.com and github.com. This is read from the text; nothing was executed.
Is Postgres Query Client safe to install?
Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. 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 Postgres Query Client use?
Postgres Query Client 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 Postgres Query Client use?
About 1.8k tokens (SKILL.md is roughly 7.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Postgres Query Client?
Skills that share tags, products or a category with Postgres Query Client: Chdb SQL (vemetric/vemetric, 394 stars), MoviePilot Database Operation (jxxghp/MoviePilot, 12k stars), Cloudsql Idle Connection Timeout (divinevideo/divine-mobile, 265 stars) and Psycopg2 Like Percent Escape (divinevideo/divine-mobile, 265 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Postgres Query Client?
evolution-foundation (a GitHub organization) maintains it in evolution-foundation/evo-nexus, which has 544 GitHub stars. The repository holds 117 skills in this directory. The repository was last updated on May 13, 2026.
Source: evolution-foundation/evo-nexus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.