Structured data research: search sources, extract structured data, archive raw sources, maintain canonical tracker pages, deduplicate. Parameterized via YAML recipes for investor updates, donations, company updates, or any email-to-structured-data pipeline.
83%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The canonical home for this skill is data-research in garrytan/gbrain
Structured research pipeline: search sources, extract structured data, archive raw, deduplicate, update canonical trackers, backlink entities.
One skill for any email-to-structured-data pipeline. The only differences between tracking investor updates, expenses, and company metrics are the search queries, extraction schemas, and tracker page format. All three use the same 7-phase pipeline with parameterized recipes.
Infer the research target from conversation context, recent brain activity, active
tasks (ops/tasks.md), and memory files. If the request is ambiguous, present the
most likely interpretation based on what the user has been working on. Only ask for
clarification if context is genuinely insufficient. Options:
Recipes are YAML files at ~/.gbrain/recipes/{name}.yaml. Scaffold a new one by
copying a built-in recipe file and editing its fields.
Brain first (maybe we already have this data). Then:
Deterministic first (regex patterns from recipe), LLM fallback. Log every LLM fallback for future regex improvement (fail-improve loop). Skip marketing, newsletters, noise based on recipe's classification rules.
EXTRACTION INTEGRITY RULE:
This prevents a known hallucination bug where batch-processed amounts were 13/13 wrong from LLM working memory while saved files were correct.
put_raw_data for email bodies, API responsesfile_upload for PDF attachments, documents.redirect.yaml pointers for large files in storageBefore adding to tracker:
Three example recipes ship with GBrain (see ~/.gbrain/recipes/):
Follow the agent operator protocol for any gbrain error code, exit code, [AGENT] block or notice block. Specific to this skill:
file_upload is refused for a path outside the allowed root (remote callers are confined): ask the user to upload from the brain host or pass the content inline.put_page / add_timeline_entry returns revision_conflict or write_pending: re-read and merge for the first; poll gbrain write-request <request_id> for the second.rate_limited): back off for the stated delay and keep the cursor; log the gap instead of guessing the missing rows.Brain page at the recipe's tracker_page path with markdown tables:
### 2026
| Date | Company | MRR | ARR | Growth | Status |
|------|---------|-----|-----|--------|--------|
| 2026-04-01 | Example Co | $188K | $2.3M | +14.7% MoM | [Source](link) |Each entry links to its raw source. Running totals at the bottom of each section.
References skills/conventions/quality.md for citation and back-linking rules.
garrytan/gbrain
f4d1866
Canonical home
since Jul 24, 2026
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.