Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Historic SQL Table Digest

A pipeline skill that turns one staged historic-SQL table JSON file into typed table-usage evidence.

Data & AnalyticsAdvanced★ 1,616⑂ 105AI score 7/10Last updated: Sep 11, 2026

What it does

Reads exactly one tables/<schema>.<name>.json file produced by the historic-sql adapter and condenses how that table is actually queried into a short narrative plus structured fields.

  • Read order: WorkUnit notes → the table JSON → manifest.json only if the dialect is missing
  • Maps columnsByClause.where to common filters, groupBy to group-bys, observedJoins to joins
  • Picks frequencyTier (high/mid/low/unused) from execution, distinct-user and recency buckets
  • Calls emit_historic_sql_evidence with kind: "table_usage" exactly once, then stops
  • Hard boundaries: no wiki writes, no SL source edits, no duplicate evidence, no inventing columns, joins or tables
  • Identifier verification protocol using discover_data, entity_details and sql_execution probes; unresolvable identifiers must be tagged [unverified - from <rawPath>]

Who it's for

  • Engineers operating or extending the ktx (Kaelio) memory-agent pipeline
  • Data platform teams auto-generating warehouse schema documentation from query logs
  • Anyone studying design patterns that stop an LLM from hallucinating table and column names

Example scenarios

  1. tables/public.orders.json changes → the skill emits one evidence object: narrative about paid/refunded lifecycle analysis, frequencyTier: "high", common filters status and created_at, a join to public.customers.
  2. A table with no recent templates → frequencyTier: "unused" with staleSince set, then stop.
  3. Unsure whether a literal tier value really exists → run SELECT DISTINCT tier ... LIMIT 50 as a probe before writing it down.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/Kaelio/ktx/HEAD/packages/cli/src/skills/historic_sql_table_digest/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the packages/cli/src/skills/historic_sql_table_digest folder from the GitHub repo Kaelio/ktx into my ~/.claude/skills/historic-sql-table-digest/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/Kaelio/ktx.git /tmp/ktx && mkdir -p ~/.claude/skills/historic_sql_table_digest && cp -r /tmp/ktx/packages/cli/src/skills/historic_sql_table_digest/* ~/.claude/skills/historic_sql_table_digest/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/Kaelio/ktx.git
  3. Create the skill folder: mkdir -p ~/.claude/skills/historic_sql_table_digest
  4. Copy the files: cp -r ktx/packages/cli/src/skills/historic_sql_table_digest/* ~/.claude/skills/historic_sql_table_digest/
  5. Restart Claude Code and confirm historic_sql_table_digest shows up in your skill list.
  6. Note: the skill invokes ktx runtime tools such as read_raw_file, emit_historic_sql_evidence and entity_details. Without the ktx CLI installed and configured it cannot run standalone.
View source on GitHub ↗License: Apache-2.0