tonydzi OBJECTIVE: Incrementally pull fresh calls from Fireflies into the vault (a note with diarized speaker NAMES + summary + action items), catch the distillation up (alpha/commitments/facts) and make sure it lands in the index.
CONTEXT:
- Transport: the official Fireflies GraphQL API
https://api.fireflies.ai/graphql. Key:FIREFLIES_API_KEYinsecrets\fireflies.env(SSO account, PRO plan). Autojoin is ON — the bot joins calendar calls by itself (catching standups and corporate calls that a manually-started recorder misses). - Engine (all the logic lives there, this skill is a thin wrapper):
$IMPORTS_ROOT/fireflies\fireflies_pull.py. One script does both backfill and increment. - Home for notes:
$OBSIDIAN_VAULT/04-Projects\fireflies-meetings\(auto_generated — never edit by hand). Raw JSON (with keys COMPATIBLE with the other call rail, whichcall_distill.pyconsumes):$IMPORTS_ROOT/fireflies\raw\. State:$IMPORTS_ROOT/fireflies\state.json. Log:pull.log. - ⚠️ The nightly pull runs on the anchor node: vault notes travel by sync, but the raw JSON does NOT reach the hub → the hub's distiller cannot see fresh Fireflies calls. Running this skill on the hub CLOSES that gap: the local state lags behind the anchor's → the pull drags the missing raw files here (idempotent; notes are rewritten with identical content).
- Distillation:
$IMPORTS_ROOT/granola\call_distill.pyreads BOTH raw directories (granola + fireflies) →_distilled\+ commitments.jsonl.
STEPS:
- BACKUP FIRST ([[vault-backup-rule]]):
python $IMPORTS_ROOT/vault_backup.pyBEFORE running anything. - Pull:
python $IMPORTS_ROOT/fireflies\fireflies_pull.py(options:--dry,--limit N). Counters on stdout:DONE new=X errors=Y state_total=N. - Distill (if new>0):
python $IMPORTS_ROOT/granola\call_distill.py— countersDONE distilled=M commitments=C errors=Z. - Report the list of fresh calls (titles/dates). errors>0 → check the log; usually network or 429 (the script retries by itself).
- Reindex: the nightly
brain_embed_update.pypicks it up on its own; after a big backfill, run it manually. ⚠️ Until_distilledis markedlayer: essence, distillates do not enter the curated index (a known gap, tracked as task RUSL-1).
CONSTRAINTS:
- Windows cp1252: stdout must stay ASCII-only (the script already complies).
- INCREMENTAL ONLY — never delete
state.json(it would re-download everything). - Provenance: origin: mixed, authored_by: hybrid — NOT #anton-original (someone else's speech).
- Tier-2: nothing goes outside; API reads and vault writes only.
- A 401 from the API means the key was revoked: get a new one in the Fireflies dashboard (Integrations → API) and update
secrets\fireflies.env. ⚠️ CRLF pitfall: a trailing\rbreaks the Bearer header (the engine already strips it). - Do NOT re-enable the hub task "Fireflies Nightly Pull" without consensus — it is deliberately Disabled (migrated to the anchor node, see fleet_migration_dashboard.py migrated_markers).
OUTPUT: the pull counters (new) + the distill counters (distilled/commitments) + the period; if empty, "no new calls". Finish with an "In plain words" recap.
RELATION (do not duplicate): the other call rail = skill [[granola-sync]]; the comparison of the two rails + the "where content lands" map = the vault 00-System note / task RUSL-1; the alpha screen = /alpha-review.
Like this skill? It is one of 100 in second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.
Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).
Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_
Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.