$ loading_
Search and manage Granola archives, sync status, notes, transcripts, and counts.
The material indicates a prompt-only skill with no required secrets and no declared remote endpoints, and it does not itself show direct code execution or data exfiltration capability, so the overall risk is low. Its GitHub open-source status and very high community adoption are strong positive trust signals, though the missing license declaration and unknown maintenance status still warrant basic source verification.
The material explicitly states there are no required secrets or environment variables, and the README does not request any API tokens. Mentions of 'unlock/secrets checks' and avoiding surprise Keychain prompts read as operational guidance rather than credential collection, with no clear sign of credential harvesting or misuse.
No remote endpoint host is declared. While the README mentions 'sync --source private-api/desktop-cache', it provides no external address, recipient, or default egress behavior. As a prompt-only skill, the material does not show it sending user data to unknown network destinations by itself.
The system checks classify it as prompt-only. The listed graincrawl commands are usage instructions and do not mean the skill itself can spawn local processes or execute arbitrary code. There is no indication of requested elevated system privileges or overbroad execution rights.
The README refers to querying 'local Granola archive data' and notes/transcripts/panels/SQL counts, but based on the provided material this describes the target data domain rather than proving the skill itself has filesystem read/write access. It also explicitly emphasizes 'bounded reads' and 'read-only SQL', with no visible sign of overbroad authorization.
The source is an open-source GitHub repository with extremely high community adoption (about 377k stars), which is a strong risk-reducing factor. The material also does not show obfuscated installation steps, suspicious downloaders, or injection-like wording. Still, the license is undeclared and maintenance status is unknown, so repository activity and release practices should be verified before installation.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "graincrawl" skill from askskill: 1. Download https://raw.githubusercontent.com/openclaw/openclaw/main/.agents/skills/graincrawl/SKILL.md 2. Save it as ~/.claude/skills/graincrawl/SKILL.md 3. Reload skills and tell me it's ready
Search the Granola archive for content related to “Q3 roadmap,” then list the matching notes, transcripts, and panel information in reverse chronological order.
A list of relevant archive records with note summaries, transcript excerpts, panel details, and time ordering.
Check the sync freshness of the Granola archive for the last 7 days, identify records that were not synced on time, and provide an exception summary.
A sync status report showing latest sync times, stale records, and a summary of exceptions.
Run SQL-based analysis on the Granola archive to calculate this month’s new note count, transcript count, and record totals by project, then summarize the key findings.
Structured statistics including totals, grouped counts, and a brief analytical summary.
Use local Granola archive data first. Check freshness for recent/current questions:
graincrawl doctor --json
graincrawl status --json
Refresh only when stale or asked:
graincrawl sync --source private-api
graincrawl sync --source desktop-cache
Query with bounded reads:
graincrawl search "query"
graincrawl notes --json
graincrawl note get <id>
graincrawl transcripts get <id>
graincrawl panels get <id>
graincrawl --json sql "select count(*) as notes from notes;"
Report absolute date spans, note titles, source gaps, and transcript/panel availability. Use read-only SQL for exact counts/rankings. Before encrypted source debugging, run explicit unlock/secrets checks; do not surprise-prompt Keychain.
Verify an OpenClaw release is fully published and working across all channels.
Fetch GitHub issues, create fixes, open PRs, and handle reviews.
Convert text to speech locally and offline with sherpa-onnx, no cloud needed.
Regenerate OpenClaw release changelog sections from Git history before releases.
Prepare and verify OpenClaw stable or beta releases and release notes.
Create and review technical docs and agent instruction files in repositories.
Access Granola meeting notes, summaries, and transcripts directly in Claude.
Search, export, sync, and analyze archived Notion content and related repo data.
Search and analyze Slack archives, count threads, and support repo workflows.
Archive, search, and summarize Discord messages and direct messages.
Search and analyze GitHub archive issues, PRs, and repo workflow status.
Scrape, crawl, map, and search web data for AI agents.