AGENT SKILL

fulcra-computed-data-types

Generates custom Python scripts to parse raw data exports and ingest them as computed Fulcra data types, dynamically tagging records by a specific data dimension (e.g., Artists, Genres, Categories).

License 许可
MIT
最近更新
2026-10-23
Stars
★ 3
Forks
6

01 前言 Front Matter

name
fulcra-computed-data-types
license
MIT
homepage
https://github.com/fulcradynamics/community-skills
metadata
{ "openclaw": { "emoji": "🛠️" } }
description
Generates custom Python scripts to parse raw data exports and ingest them as computed Fulcra data types, dynamically tagging records by a specific data dimension (e.g., Artists, Genres, Categories).
user-invocable
true

02 资源文件 3

03 SKILL.md 正文

Computed Data Types Generator

This skill enables agents to act as personal data engineers. Instead of running a static script, you will generate a custom Python parser on the fly to extract a specific dimension (e.g., Spotify Artists, Netflix Genres, Amazon Categories) from a user's raw data export and upload it to Fulcra as a highly-queryable custom data type.

Prerequisites

  1. The Data: The user must provide the path to their extracted data files.
  2. Authentication: Ensure you are authenticated to the Fulcra CLI (uvx fulcra-api auth login --get-auth-url).

Dependencies & References

This skill is an advanced extension of the core ingestion pipeline. You MUST load the fulcra-ingest skill (via skill_view(name="fulcra-ingest")) to access its reference files:

  • Use references/fulcra-ingest-cli.md for the exact syntax for data-type create, tag create, and record operations.
  • Use references/fulcra-ingest-source-mapping.md to ensure you properly register the new computed type in the user's source_map.md and log it in the ingest_log.md.

The Workflow

1. Identify the Goal and Data Shape

Ask the user what dimension they want to track (e.g., "I want to track my Spotify streams by Artist"). Use tools to briefly inspect the shape of their raw data files (e.g., head -n 20 data.json) to identify the required fields (timestamps, specific tags, and notes).

2. Schema Creation

Check if the desired target schema already exists using uvx fulcra-api catalog | jq '.[] | select(.categories | index("user_configured"))'. If not, consult the fulcra-ingest CLI reference to create the appropriate base annotation type (MomentAnnotation, DurationAnnotation, NumericAnnotation, etc.) via the CLI. Capture the returned JSON schema ID (e.g., com.fulcradynamics.annotation...).

3. Generate the Custom Processing Script

You must write a custom Python script that parses the user's files and builds the JSONL records. Crucially, do not start from scratch. Read the template located at templates/computed_type_template.py. The template contains the necessary boilerplate for:

  • Generating deterministic UUIDs for idempotency.
  • Extracting and batch-creating tags via the fulcra-api tag create command.
  • Safely caching and matching tags case-insensitively.

Copy the template, fill in the custom parsing logic in the designated # TODO: section (handling timestamps, notes, and the extracted tag name), and save it to the local workspace. Tip: If you need an example of a fully implemented script, see examples/spotify_artists.py.

4. Execute and Ingest

  1. Run your generated script to parse the files, fetch/create the tags, and output the output_records.jsonl file.
  2. Consult the fulcra-ingest CLI reference to batch ingest your output_records.jsonl file (running in the background for large datasets).
  3. Update the user's source_map.md and ingest_log.md according to the rules in the core fulcra-ingest skill.

5. Handoff

Once the background upload begins, notify the user that their data is being processed and let them know they will soon be able to view their customized, categorized data directly on their timeline.

04 同仓库更多 Skills

fulcradynamics
fulcradynamics/community-skills

use-agents-for-pre-networking-at-events

Pre-network at a conference or event run on Agent Mixer: put your person on Fulcra, learn what they want from the event, share their attendee card with other attendees, pick who they should meet, negotiate with other attendees' agents, and schedule meetings they approve. Use when the user shares an Agent Mixer event link (agentmixer.my.fulcra.ai/e/...), or says get me ready for this event, who should I meet at <event>, set up meetings at <event>, or check my Agent Mixer meetups.

★ 3
fulcradynamics
fulcradynamics/community-skills

trade-agent-hacks-by-invite

Start or join an invite-only network on Fulcra where people's agents trade hacks (tips, tricks, prompts and skills that make an agent more useful). Use when the user wants to set up their own hack-trading network, has an invite to one (for example The Secret Agent Network), or wants to submit a hack, check clearance, get new hacks, ask or answer a question about a hack, or send invites.

★ 3
fulcradynamics
fulcradynamics/community-skills

track-my-dealflow

Use when a content creator asks about their brand deals, contracts, what's due, who owes them, or anything in Track My Dealflow (track-my-dealflow.my.fulcra.ai).

★ 3
fulcradynamics
fulcradynamics/community-skills

fulcra-vault

Manage a durable, Obsidian-like shared markdown knowledge vault using Open Knowledge Format (OKF) stored in Fulcra, enabling persistent shared memory across all agents.

★ 3
fulcradynamics
fulcradynamics/community-skills

fulcra-sister-cities

Run or facilitate Sister Cities, an asynchronous city-trade social game for 3–10 players. Cities are light social-game flavour; players trade everyday imports such as candy, soft drinks, books, games, plants, and small comforts, with automatic redacted round editions.

★ 3
fulcradynamics
fulcradynamics/community-skills

fulcra-project-dashboard

Builds a management dashboard for an agent-teams workspace, showing progress, logs, a generated summary, timeline/milestone charts, and a word map of agent activities.

★ 3