agentleFS
tonydzitonydzi/second-brain-starter-kit/skills/fireflies-sync/SKILL.md

fireflies-sync

Skill6 starsChanged 2 months agoMITView on GitHub

Pull fresh call recordings and transcripts from Fireflies.ai into an Obsidian vault over the official GraphQL API, then distill action items and commitments and reindex. Incremental and idempotent by transcript id. Triggers: "/fireflies-sync", "pull fireflies", "sync call recordings".

  • Reads credentials

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Do NOT re-enable the hub task "Fireflies Nightly Pull" without consensus — it is deliberately Disabled (migrated to the anchor node, see …

    line 33

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

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_KEY in secrets\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, which call_distill.py consumes): $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.py reads BOTH raw directories (granola + fireflies) → _distilled\ + commitments.jsonl.

STEPS:

  1. BACKUP FIRST ([[vault-backup-rule]]): python $IMPORTS_ROOT/vault_backup.py BEFORE running anything.
  2. Pull: python $IMPORTS_ROOT/fireflies\fireflies_pull.py (options: --dry, --limit N). Counters on stdout: DONE new=X errors=Y state_total=N.
  3. Distill (if new>0): python $IMPORTS_ROOT/granola\call_distill.py — counters DONE distilled=M commitments=C errors=Z.
  4. Report the list of fresh calls (titles/dates). errors>0 → check the log; usually network or 429 (the script retries by itself).
  5. Reindex: the nightly brain_embed_update.py picks it up on its own; after a big backfill, run it manually. ⚠️ Until _distilled is marked layer: 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 \r breaks 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.


<!--kit-footer-->

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.

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.