Pytorch Clickhouse
pytorch/test-infra
Load this FIRST whenever working with PyTorch CI data (any pytorch/ org repo), the torchci/HUD codebase, or the PyTorch HUD ClickHouse database.
Answer analytical, KPI, metric, trend, cohort, and business-performance questions through a Sidemantic semantic layer.
Install Semantic Analyst
$ npx skills add sidequery/sidemantic --skill semantic-analyst -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install sidequery/sidemantic semantic-analyst --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/sidequery/sidemantic.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/sidemantic/skills/semantic-analyst .claude/skills/semantic-analyst && 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 "semantic-analyst" agent skill from https://github.com/sidequery/sidemantic/tree/main/plugins/sidemantic/skills/semantic-analyst into .claude/skills/semantic-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-analyst", 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/sidequery/sidemantic/tree/main/plugins/sidemantic/skills/semantic-analystType 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 sidequery/sidemantic --skill semantic-analyst -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install sidequery/sidemantic semantic-analyst --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sidequery/sidemantic.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/sidemantic/skills/semantic-analyst .agents/skills/semantic-analyst && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "semantic-analyst" agent skill from https://github.com/sidequery/sidemantic/tree/main/plugins/sidemantic/skills/semantic-analyst into .agents/skills/semantic-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-analyst", 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 sidequery/sidemantic --skill semantic-analyst -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install sidequery/sidemantic semantic-analyst --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sidequery/sidemantic.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/sidemantic/skills/semantic-analyst .cursor/skills/semantic-analyst && 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 "semantic-analyst" agent skill from https://github.com/sidequery/sidemantic/tree/main/plugins/sidemantic/skills/semantic-analyst into .cursor/skills/semantic-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-analyst", 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/sidequery/sidemantic.git --path plugins/sidemantic/skills/semantic-analyst--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 sidequery/sidemantic --skill semantic-analyst -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install sidequery/sidemantic semantic-analyst --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sidequery/sidemantic.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/sidemantic/skills/semantic-analyst .gemini/skills/semantic-analyst && 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 "semantic-analyst" agent skill from https://github.com/sidequery/sidemantic/tree/main/plugins/sidemantic/skills/semantic-analyst into .gemini/skills/semantic-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-analyst", 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 sidequery/sidemantic semantic-analystInstalls 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 sidequery/sidemantic --skill semantic-analyst -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/sidequery/sidemantic.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/sidemantic/skills/semantic-analyst .github/skills/semantic-analyst && 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 "semantic-analyst" agent skill from https://github.com/sidequery/sidemantic/tree/main/plugins/sidemantic/skills/semantic-analyst into .github/skills/semantic-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-analyst", 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 sidequery/sidemantic --skill semantic-analyst -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install sidequery/sidemantic semantic-analyst --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/sidequery/sidemantic.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/sidemantic/skills/semantic-analyst .opencode/skills/semantic-analyst && 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 "semantic-analyst" agent skill from https://github.com/sidequery/sidemantic/tree/main/plugins/sidemantic/skills/semantic-analyst into .opencode/skills/semantic-analyst/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "semantic-analyst", 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
semantic-analyst- GitHub stars
- 129
- Token cost
- ~982 tokens
- SKILL.md length
- 435 words
- Files
- 2
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Answer analytical, KPI, metric, trend, cohort, and business-performance questions through a Sidemantic semantic layer.
- Works in 6 steps: Search the semantic catalog for the… → Explain candidate metrics and inspect… → Translate the question into existing… → …
- Asked to analyze data
- SKILL.md covers Workflow, Decide What Belongs in the Model, Handle Semantic Gaps and Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Semantic Analyst is an agent skill from sidequery/sidemantic. Answer analytical, KPI, metric, trend, cohort, and business-performance questions through a Sidemantic semantic layer. Use when asked to analyze data, explain why a metric changed, compare segments or periods, calculate a business measure, or explore warehouse data when Sidemantic MCP tools or semantic model files are available. Discover and reuse trusted definitions, distinguish durable semantic-model gaps from one-off query logic, and prefer semantic queries over duplicated raw SQL.
Its SKILL.md is about 980 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Databases, covering Data warehousing, SQL and Data analysis. It works with SQL, Model Context Protocol, ClickHouse and DuckDB. The repository describes itself as: The universal metrics layer. Compatible with 15+ formats: Cube, MetricFlow, LookML, Omni, BSL, LDM, Cortex, Malloy, OSI, SML, TML, Hex, Rill, Superset. The licence is AGPL-3.0.
When your agent uses it
- Asked to analyze data
- Explain why a metric changed
- Compare segments
- Calculate a business measure
Example prompts
- “/semantic-analyst”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Search the semantic catalog for the user's concepts. Search by business terms and likely synonyms; do not dump the full graph unless…
- Explain candidate metrics and inspect the relevant models. Check descriptions, dependencies, filters, aggregation or formula, grain…
- Translate the question into existing metrics, dimensions, segments, time grains, and one-off filters. Validate uncertain field combinations.
- Prefer a structured semantic query. Use semantic SQL only when the structured query cannot express a needed operation. Use raw warehouse…
- Check the result for the requested grain, units, time range, exclusions, null behavior, and denominator. State material assumptions.
- Answer the business question directly. Include the metric definition or query provenance when it affects interpretation.
What it can do on your machine
Read from SKILL.md and the folder at commit db203eb. 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
No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Semantic Analyst loads about 982 tokens when it runs. Until then it costs about 127 tokens; SKILL.md has 435 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from sidequery/sidemantic at commit db203eb, republished under its AGPL-3.0 licence (© sidequery). 435 words, ~982 tokens.
Download SKILL.mdSave it as
.claude/skills/semantic-analyst/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- semantic-analyst
- description
- Answer analytical, KPI, metric, trend, cohort, and business-performance questions through a Sidemantic semantic layer. Use when asked to analyze data, explain why a metric changed, compare segments or periods, calculate a business measure, or explore warehouse data when Sidemantic MCP tools or semantic model files are available. Discover and reuse trusted definitions, distinguish durable semantic-model gaps from one-off query logic, and prefer semantic queries over duplicated raw SQL.
Semantic Analyst
Use the semantic layer as accumulated business knowledge, not merely as a convenient query interface.
Workflow
- Search the semantic catalog for the user's concepts. Search by business terms and likely synonyms; do not dump the full graph unless search is unavailable or broader topology is necessary.
- Explain candidate metrics and inspect the relevant models. Check descriptions, dependencies, filters, aggregation or formula, grain, relationships, source file, and provenance before deciding that a metric matches the request.
- Translate the question into existing metrics, dimensions, segments, time grains, and one-off filters. Validate uncertain field combinations.
- Prefer a structured semantic query. Use semantic SQL only when the structured query cannot express a needed operation. Use raw warehouse SQL only for genuinely exploratory work outside the modeled surface, and label that result as outside the semantic layer.
- Check the result for the requested grain, units, time range, exclusions, null behavior, and denominator. State material assumptions.
- Answer the business question directly. Include the metric definition or query provenance when it affects interpretation.
Decide What Belongs in the Model
Promote durable business semantics into the model; keep ephemeral analytical operations in the query.
- Reuse an existing metric for requests such as revenue last week by state.
- Apply query filters for narrow cohorts such as California users who signed up Tuesday.
- Model definitions with durable policy, such as net revenue excluding refunds or repayment rate with an eligibility denominator.
- Model ratios or derived measures that recur across analyses.
- Keep unusual exploratory cohorts or temporary calculations out of the model until they become reusable.
Do not create combinatorial metrics that merely bake a dimension value, date range, or one-off filter into an otherwise reusable metric.
Show full SKILL.md (151 more words)Show less
Handle Semantic Gaps
When no existing definition faithfully represents the request, do not silently invent equivalent SQL. Return a concise structured gap:
semantic_gap:
requested_concept: net revenue
why_missing: Existing revenue does not define refund treatment.
reusable: true
recommended_action: model_metric
proposed_definition:
name: net_revenue
policy: gross revenue minus refunded amount
open_questions:
- Which refund statuses count?Use recommended_action: query_only for ephemeral operations and clarify when business policy is ambiguous.
If working as a coding agent with repository access, inspect the model's reported source_file, update the semantic definition through normal files and Git, run sidemantic validate path/to/models/ --verbose, run relevant project tests, and retry the original semantic query. Use the separate modeler skill for substantial authoring or migration work. If files cannot be edited, report the gap and proposed definition without claiming it was persisted.
Guardrails
- Never substitute a similarly named metric without checking its definition.
- Never hide missing business policy inside ad hoc SQL.
- Never persist a new metric merely because a query is complex.
- Never claim causality from descriptive results alone.
- Preserve access controls and field visibility; do not work around unavailable semantic fields.
© sidequery, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in plugins/sidemantic/skills/semantic-analyst of sidequery/sidemantic.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit db203eb
Compare with similar skills
Semantic Analyst 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 |
|---|---|---|---|---|---|---|
| Semantic Analyst this skillsidequery/sidemantic | 129 | — | ~982 | Automated safety check: Pass | AGPL-3.0 | |
| Pytorch Clickhousepytorch/test-infra | 113 | — | ~2.8k | Automated safety check: Pass | Custom licence | |
| Google Cloud Storage Basicsgoogle/skills | 21k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Chdb SQLvemetric/vemetric | 394 | 1 repos | ~1.2k | Automated safety check: Pass | Apache-2.0 | |
| Querying Tempotempoxyz/tidx | 107 | — | ~3.1k | Automated safety check: Pass | MIT | |
| Analysis Artifactswarpdotdev/oz-skills | 825 | — | ~1.1k | Automated safety check: Pass | MIT |
Similar skills
- Official
Google Cloud Storage Basics
google/skills
Stores, retrieves, and manages data as objects in Cloud Storage on Google Cloud (also known colloquially as GCS) buckets.
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…
Querying Tempo
tempoxyz/tidx
Query indexed Tempo chain data via tidx HTTP API and CLI. An agent skill from tempoxyz/tidx.
Analysis Artifacts
warpdotdev/oz-skills
Generate reproducible analysis artifacts — SQL queries, Python visualizations, and summary tables — as you work through a BigQuery data analysis.
Database Migration
Rain-kl/OpenFlare
Wavelet 项目专用：当新增或修改数据库表结构、索引、初始化数据、系统配置 seed、模板 seed、默认管理员、goose SQL 迁移、internal/infra/persistence/migrator、ClickHouse 分析库 DDL 或数据库升级流程时必须使用。本技能指导在 internal/infra/persistence/migrator/goose 下编写…
More from sidequery/sidemantic
Webapp Builder
sidequery/sidemantic
Build interactive analytics webapps, demos, dashboards, or embedded app surfaces from Sidemantic semantic models using copyable component primitives and deterministic query inspection.
Modeler
sidequery/sidemantic
Build, validate, and manage semantic models using Sidemantic.
Related
Categories
Questions about Semantic Analyst
What does Semantic Analyst do?
Answer analytical, KPI, metric, trend, cohort, and business-performance questions through a Sidemantic semantic layer. Semantic Analyst is an agent skill from sidequery/sidemantic. Answer analytical, KPI, metric, trend, cohort, and business-performance questions through a Sidemantic semantic layer.
When should I use Semantic Analyst?
Semantic Analyst fits situations like: asked to analyze data; explain why a metric changed; compare segments; calculate a business measure.
How do I install Semantic Analyst in Claude Code?
Run `npx skills add sidequery/sidemantic --skill semantic-analyst -a claude-code`. Or copy the skill folder (plugins/sidemantic/skills/semantic-analyst in sidequery/sidemantic) into .claude/skills/semantic-analyst in your project. Claude Code loads it when a task matches its description.
How do I install Semantic Analyst in Codex?
Run `npx skills add sidequery/sidemantic --skill semantic-analyst -a codex`. Or copy the skill folder (plugins/sidemantic/skills/semantic-analyst in sidequery/sidemantic) into .agents/skills/semantic-analyst in your project. Codex loads it when a task matches its description.
Can I use Semantic Analyst 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 sidequery/sidemantic --skill semantic-analyst -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/semantic-analyst, .gemini/skills/semantic-analyst, .github/skills/semantic-analyst and .opencode/skills/semantic-analyst in your project.
What does Semantic Analyst need to run?
SKILL.md names no scripts, command-line tools or credentials: Semantic Analyst is instructions for the agent only.
Does Semantic Analyst access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Semantic Analyst 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. Review the folder before installing.
What licence does Semantic Analyst use?
Semantic Analyst is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Semantic Analyst use?
About 982 tokens (SKILL.md is roughly 3.9k 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 Semantic Analyst?
Skills that share tags, products or a category with Semantic Analyst: Pytorch Clickhouse (pytorch/test-infra, 113 stars), Google Cloud Storage Basics (google/skills, 21k stars), Chdb SQL (vemetric/vemetric, 394 stars) and Querying Tempo (tempoxyz/tidx, 107 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Semantic Analyst?
sidequery (a GitHub organization) maintains it in sidequery/sidemantic, which has 129 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 7, 2026.
Source: sidequery/sidemantic on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.