Basin
cloudflare/skills
Build and troubleshoot Cloudflare Basin analytics workflows with Basin Pipelines, Basin Catalog, and Basin SQL.
Audits a Dinobase source's existing annotations and fills only the gaps in table descriptions, column docs, PII flags and relationships through a subagent.
Install Dinobase Semantic Layer Indexing
$ npx skills add kappa90/dinobase --skill indexing-semantic-layer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kappa90/dinobase indexing-semantic-layer --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/kappa90/dinobase.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/indexing-semantic-layer .claude/skills/indexing-semantic-layer && 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 "indexing-semantic-layer" agent skill from https://github.com/kappa90/dinobase/tree/main/.claude/skills/indexing-semantic-layer into .claude/skills/indexing-semantic-layer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indexing-semantic-layer", 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/kappa90/dinobase/tree/main/.claude/skills/indexing-semantic-layerType 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 kappa90/dinobase --skill indexing-semantic-layer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kappa90/dinobase indexing-semantic-layer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kappa90/dinobase.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/indexing-semantic-layer .agents/skills/indexing-semantic-layer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "indexing-semantic-layer" agent skill from https://github.com/kappa90/dinobase/tree/main/.claude/skills/indexing-semantic-layer into .agents/skills/indexing-semantic-layer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indexing-semantic-layer", 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 kappa90/dinobase --skill indexing-semantic-layer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kappa90/dinobase indexing-semantic-layer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kappa90/dinobase.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/indexing-semantic-layer .cursor/skills/indexing-semantic-layer && 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 "indexing-semantic-layer" agent skill from https://github.com/kappa90/dinobase/tree/main/.claude/skills/indexing-semantic-layer into .cursor/skills/indexing-semantic-layer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indexing-semantic-layer", 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/kappa90/dinobase.git --path .claude/skills/indexing-semantic-layer--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 kappa90/dinobase --skill indexing-semantic-layer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kappa90/dinobase indexing-semantic-layer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kappa90/dinobase.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/indexing-semantic-layer .gemini/skills/indexing-semantic-layer && 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 "indexing-semantic-layer" agent skill from https://github.com/kappa90/dinobase/tree/main/.claude/skills/indexing-semantic-layer into .gemini/skills/indexing-semantic-layer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indexing-semantic-layer", 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 kappa90/dinobase indexing-semantic-layerInstalls 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 kappa90/dinobase --skill indexing-semantic-layer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kappa90/dinobase.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/indexing-semantic-layer .github/skills/indexing-semantic-layer && 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 "indexing-semantic-layer" agent skill from https://github.com/kappa90/dinobase/tree/main/.claude/skills/indexing-semantic-layer into .github/skills/indexing-semantic-layer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indexing-semantic-layer", 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 kappa90/dinobase --skill indexing-semantic-layer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kappa90/dinobase indexing-semantic-layer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kappa90/dinobase.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/indexing-semantic-layer .opencode/skills/indexing-semantic-layer && 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 "indexing-semantic-layer" agent skill from https://github.com/kappa90/dinobase/tree/main/.claude/skills/indexing-semantic-layer into .opencode/skills/indexing-semantic-layer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "indexing-semantic-layer", 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
indexing-semantic-layer- GitHub stars
- 263
- Token cost
- ~1.3k tokens
- SKILL.md length
- 330 words
- Files
- 1
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Audits a Dinobase source's existing annotations and fills only the gaps in table descriptions, column docs, PII flags and relationships through a subagent.
- Works in 5 steps: Check the input schema → Audit existing annotations → Explore gaps → …
- Documenting a newly loaded Dinobase source so agents can query it correctly
- Calls uv and python3
- Finding tables and columns that still lack descriptions or PII flags
What it does
Given a source name, this skill launches a general-purpose subagent with a detailed brief to audit what is already annotated and fill every gap without overwriting annotations that are already good. Step 0 prints the JSON input format that the dinobase annotate command accepts, and step 1 runs four checks with dinobase query against the metadata tables to find undocumented tables and columns.
For each gap the subagent reads the column list and a few sample rows to work out what entity or event the table represents, which columns carry business data rather than structural noise, which hold personal data such as email, name, phone, IP or user ID, and which are foreign keys. It also looks for relationships missing from the graph.
Writing happens in a single dinobase annotate call with a JSON array of only the missing items, mixing description, flag and relationship entries. A final step re-runs the checks to confirm no gaps remain. Commands run through uv, and the later part of the excerpt is truncated.
When your agent uses it
- Documenting a newly loaded Dinobase source so agents can query it correctly
- Finding tables and columns that still lack descriptions or PII flags
- Topping up a partially annotated source without redoing finished work
Example prompts
- “Index the semantic layer for the stripe source and only fill what's missing.”
- “Audit the github source annotations and flag any columns that hold personal data.”
- “Check which tables in the hubspot source still have no description and write them.”
Requirements
- uv and the dinobase CLI
- A Dinobase source with data already loaded
Workflow steps
5 steps, taken from the step headings in SKILL.md.
- Check the input schema
- Audit existing annotations
- Explore gaps
- Write only what's missing
- Verify completeness
What it can do on your machine
Read from SKILL.md and the folder at commit 2dd0636. 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
Shell commands in SKILL.md call:
uvpython3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.
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
Dinobase Semantic Layer Indexing loads about 1.3k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 330 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 330 words (~1,262 tokens).
- name
- indexing-semantic-layer
- argument-hint
- <source_name>
Files
Just SKILL.md in .claude/skills/indexing-semantic-layer of kappa90/dinobase.
Open the folder on GitHubat commit 2dd0636
Compare with similar skills
Dinobase Semantic Layer Indexing 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 |
|---|---|---|---|---|---|---|
| Dinobase Semantic Layer Indexing this skillkappa90/dinobase | 263 | — | ~1.3k | Automated safety check: Pass | Custom licence | |
| Basincloudflare/skills | 3k | 1 repos | ~684 | Automated safety check: Pass | Apache-2.0 | |
| Monte Carlo Preventsickn33/agentic-awesome-skills | 47k | 1 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Querying Data Lakeaws/agent-toolkit-for-aws | 2.8k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Querying AWS Sagemaker Catalogaws/agent-toolkit-for-aws | 2.8k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| Cortex CodeKilo-Org/kilo-marketplace | 190 | — | ~4.6k | Automated safety check: Warn | Proprietary |
Similar skills
- Official
Monte Carlo Prevent
sickn33/agentic-awesome-skills
Surfaces Monte Carlo data observability context (table health, alerts, lineage, blast radius) before SQL/dbt edits.
- Official
Querying Data Lake
aws/agent-toolkit-for-aws
Execute and manage Athena SQL queries across default and federated catalogs (Glue, S3 Tables, Redshift).
- Official
Querying AWS Sagemaker Catalog
aws/agent-toolkit-for-aws
Runs SQL analytics on SageMaker Catalog asset metadata tables exported as Apache Iceberg in S3 Tables.
Cortex Code
Kilo-Org/kilo-marketplace
Routes Snowflake-related operations to Cortex Code CLI for specialized Snowflake expertise.
Analyzing Data
astronomer/agents
Queries the data warehouse with SQL and answers business questions about data.
More from kappa90/dinobase
Dinobase Connector Builder
kappa90/dinobase
Writes a new Dinobase YAML connector for a REST API that has no verified dlt source, covering auth, pagination, read and write endpoints and incremental loading.
Dinobase Business Data Queries
kappa90/dinobase
Sets up Dinobase, a local DuckDB database that syncs data from 100+ business sources, then answers questions across them with SQL joins and previewed write-backs.
Related
Categories
Questions about Dinobase Semantic Layer Indexing
What does Dinobase Semantic Layer Indexing do?
Audits a Dinobase source's existing annotations and fills only the gaps in table descriptions, column docs, PII flags and relationships through a subagent. Given a source name, this skill launches a general-purpose subagent with a detailed brief to audit what is already annotated and fill every gap without overwriting annotations that are already good. Step 0 prints the JSON input format that the dinobase annotate command accepts, and step 1 runs four checks with dinobase query against the metadata tables to find undocumented tables and columns.
When should I use Dinobase Semantic Layer Indexing?
Dinobase Semantic Layer Indexing fits situations like: documenting a newly loaded Dinobase source so agents can query it correctly; finding tables and columns that still lack descriptions or PII flags; topping up a partially annotated source without redoing finished work.
How do I install Dinobase Semantic Layer Indexing in Claude Code?
Run `npx skills add kappa90/dinobase --skill indexing-semantic-layer -a claude-code`. Or copy the skill folder (.claude/skills/indexing-semantic-layer in kappa90/dinobase) into .claude/skills/indexing-semantic-layer in your project. Claude Code loads it when a task matches its description.
How do I install Dinobase Semantic Layer Indexing in Codex?
Run `npx skills add kappa90/dinobase --skill indexing-semantic-layer -a codex`. Or copy the skill folder (.claude/skills/indexing-semantic-layer in kappa90/dinobase) into .agents/skills/indexing-semantic-layer in your project. Codex loads it when a task matches its description.
Can I use Dinobase Semantic Layer Indexing 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 kappa90/dinobase --skill indexing-semantic-layer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/indexing-semantic-layer, .gemini/skills/indexing-semantic-layer, .github/skills/indexing-semantic-layer and .opencode/skills/indexing-semantic-layer in your project.
What does Dinobase Semantic Layer Indexing need to run?
Going by SKILL.md and its folder, Dinobase Semantic Layer Indexing needs the command-line tools its instructions call (uv and python3). Our summary lists: uv and the dinobase CLI; A Dinobase source with data already loaded.
Does Dinobase Semantic Layer Indexing access the network?
SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Dinobase Semantic Layer Indexing 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 Dinobase Semantic Layer Indexing use?
Dinobase Semantic Layer Indexing 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 Dinobase Semantic Layer Indexing use?
About 1.3k tokens (SKILL.md is roughly 5k 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 Dinobase Semantic Layer Indexing?
Skills that share tags, products or a category with Dinobase Semantic Layer Indexing: Basin (cloudflare/skills, 3k stars), Monte Carlo Prevent (sickn33/agentic-awesome-skills, 47k stars), Querying Data Lake (aws/agent-toolkit-for-aws, 2.8k stars) and Querying AWS Sagemaker Catalog (aws/agent-toolkit-for-aws, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dinobase Semantic Layer Indexing?
kappa90 (a GitHub user) maintains it in kappa90/dinobase, which has 263 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on July 6, 2026.
Source: kappa90/dinobase on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.