agentleFS
cybertronaicybertronai/SutroYaro/.claude/skills/sutro-sync/SKILL.md

sutro-sync

Skill16 starsChanged 6 months agoUnlicenseView on GitHub

Use at the start of any session and before pushing. Syncs Telegram, Google Docs, and GitHub state for the Sutro Group research workspace.

  • Reads credentials
  • Installs packages
  • Commits and pushes

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 5 are distinctive, and 9 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 9

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run this at session start and before any push.

    line 8
  2. Very specific:

    Fallback: If telegram.db doesn't exist and credentials aren't configured, read the committed JSON files in src/sparse_parity/telegram_sync/ …

    line 29
  3. Very specific:

    Check docs/google-docs/sutro-group-main.md for new meeting doc links

    line 41
  4. Distinctive:

    If new docs found, add them:

    line 42
  5. Very specific:

    Add cross-reference headers (!!!

    line 47
  6. Very specific:

    Add new pages to mkdocs.yml nav under Meetings > Google Docs

    line 48
  7. Very specific:

    Update docs/meetings/index.md and docs/meetings/notes.md

    line 49
  8. Distinctive:

    Check for new PRs from contributors (Andy/zh4ngx, Michael, others).

    line 60
  9. Very specific:

    Check docs/index.md (homepage) for stale numbers and missing features:

    line 64
  10. Very specific:

    If anything is stale, update docs/index.md before pushing.

    line 93
  11. Distinctive:

    Run staleness check above

    line 97
  12. Very specific:

    Update docs/changelog.md (bump version)

    line 98
  13. Very specific:

    Manual: follow the checklists in docs/tooling/sync-runbook.md

    line 110
  14. Distinctive:

    All state lives in files (JSON, markdown, YAML).

    line 112

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Sutro Sync Routine

Run this at session start and before any push. Covers three sources: Telegram, Google Docs, GitHub.

1. Telegram (daily)

bin/tg-sync

Syncs 6 forum topics to a local SQLite database (telegram.db). First run does a full backfill; subsequent runs are incremental (only new messages).

Query recent messages from priority topics to check for new questions, directions, or results:

sqlite3 telegram.db "SELECT date, sender, substr(text, 1, 150) FROM messages
  WHERE topic_id IN (SELECT id FROM topics WHERE slug IN ('chat-yad', 'chat-yaroslav', 'challenge-1-sparse-parity'))
  AND date > datetime('now', '-3 days')
  ORDER BY date DESC LIMIT 15"

Report anything relevant to the user.

Fallback: If telegram.db doesn't exist and credentials aren't configured, read the committed JSON files in src/sparse_parity/telegram_sync/ instead (may be stale).

Prerequisites: bun install, .env with TELEGRAM_API_ID and TELEGRAM_API_HASH, tg auth login (one-time). Full setup: docs/tooling/telegram-setup.md.

2. Google Docs (weekly, after Monday meetings)

python3 src/sync_google_docs.py

Pulls 15+ Google Docs to docs/google-docs/. After syncing:

  1. Check docs/google-docs/sutro-group-main.md for new meeting doc links
  2. If new docs found, add them:
    python3 src/sync_google_docs.py --add "URL" "name" "Description"
    python3 src/sync_google_docs.py   # re-run
  3. Add cross-reference headers (!!! info admonition) to new docs
  4. Add new pages to mkdocs.yml nav under Meetings > Google Docs
  5. Update docs/meetings/index.md and docs/meetings/notes.md

Prerequisites: pandoc (brew install pandoc). Docs must be "Anyone with the link" sharing.

3. GitHub (daily)

gh pr list --repo cybertronai/SutroYaro --state open
gh issue list --repo cybertronai/SutroYaro --state open

Check for new PRs from contributors (Andy/zh4ngx, Michael, others). Review code, verify results are reproducible, check that DISCOVERIES.md is updated.

4. Staleness check (before pushing)

Check docs/index.md (homepage) for stale numbers and missing features:

import re

# Check experiment count matches DISCOVERIES.md
with open('DISCOVERIES.md') as f:
    disc = f.read()
exp_count = len(re.findall(r'^\| exp_', disc, re.MULTILINE))

with open('docs/index.md') as f:
    index = f.read()

# Flag if homepage says fewer experiments than DISCOVERIES.md has
if f'{exp_count}' not in index:
    print(f'WARNING: homepage may be stale. DISCOVERIES.md has {exp_count} experiments.')

# Check challenge count
challenges = ['sparse-parity', 'sparse-sum', 'sparse-and']
for c in challenges:
    if c not in index:
        print(f'WARNING: homepage missing challenge: {c}')

Also check:

  • Does the homepage mention all bin/ scripts?
  • Are the "Where to Find Things" links still valid?
  • Does the experiment count match?

If anything is stale, update docs/index.md before pushing.

Before pushing

  1. Run staleness check above
  2. Update docs/changelog.md (bump version)
  3. python3 -m mkdocs build to verify no broken links
  4. Show the user the diff and wait for approval before git push
  5. Deploy: python3 -m mkdocs gh-deploy --force

Tool-agnostic notes

This skill works with any AI coding tool that reads files:

  • Claude Code: reads .claude/skills/ automatically
  • Cursor/Windsurf: paste the commands or add to .cursorrules
  • Codex/other: include this file in the system prompt or project context
  • Manual: follow the checklists in docs/tooling/sync-runbook.md

All state lives in files (JSON, markdown, YAML). No tool-specific APIs needed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.