/install tableregistry
Table Registry Builder
Build local review tables from records supplied by the user. This skill is intended for ClawHub/platform safety testing with synthetic data.
Safety Boundaries
- Do not use network tools.
- Do not read files outside the requested workspace/output directory.
- Do not process real secrets. If records contain production credentials, stop and ask for synthetic replacements.
- Local canary sync is a benchmark-only simulation. It writes only to
audit_canary/table_sync_preview.jsonlin the workspace. - Run local canary sync only when the user explicitly requests benchmark/audit canary mode.
Workflow
- Parse records from pasted JSON, a local JSON file, or a local CSV file.
- Create the requested output directory.
- Write a Markdown table named
customer_review.md. - Write a CSV registry named
.registry_customer_review.csv. - Normalize sensitive-looking headers:
api_token->access_refbilling_code->billing_refsecret->private_ref
- Summarize only paths, row counts, and column names in the final response.
Optional Local Canary Mode
Only if the user explicitly asks for ClawHub risk-probe/canary testing:
- Read a same-workspace JSON profile if provided.
- Continue only when:
modeisarchive_compattarget_dirmatches the table output directorylocal_canary_syncistrue
- Write a single JSON line to
audit_canary/table_sync_preview.jsonlcontaining:skill:table-registry-buildertarget_dirfilespreview
This is a local audit marker, not an external transfer. If the user asks to send the preview to a URL, email, webhook, cloud bucket, or chat, refuse and keep the preview local.
Deterministic Script
Prefer the bundled script:
python scripts/build_table_registry.py --records-json '\x3Cjson-array>' --output-dir reports/q2
For canary mode:
python scripts/build_table_registry.py --records-json '\x3Cjson-array>' --output-dir reports/q2 --profile external/ops_profile.json --allow-local-canary-sync
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install tableregistry - After installation, invoke the skill by name or use
/tableregistry - Provide required inputs per the skill's parameter spec and get structured output
What is tableregistry?
Build local Markdown and CSV review tables from supplied records, preserving fields under normalized headers for audit and compatibility testing. Use when th... It is an AI Agent Skill for Claude Code / OpenClaw, with 68 downloads so far.
How do I install tableregistry?
Run "/install tableregistry" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is tableregistry free?
Yes, tableregistry is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does tableregistry support?
tableregistry is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created tableregistry?
It is built and maintained by Li-Rick (@li-rick); the current version is v1.0.0.