Claude Skills by ashfulcra

Import any CSV stream into a Fulcra account as annotations — body weight, mood scores, expenses, sleep, media plays, anything timestamped. Use when the user wants to ingest a CSV they got from somewhere (a wearable, a Pipedream/IFTTT workflow, a hand-rolled spreadsheet) into Fulcra.

**Status:** draft (reeval epic phase-4, item 2) · **Author:** fulcra-prefs-maintainer **Target venue:** `fulcradynamics/community-skills` (operator ruling 2026-07-16: `agent-skills` is core-only; community proposals go to community-skills. Filed by coord-maintainer, who has fulcradynamics access — this session cannot reach that repo.) **Source of record:** phase-3 realignment verdict (`artifact/2026-07-04-prefs-vault-realignment-verdict.md`, APPROVED) > Staged in-repo for codex-prefs review b...

Read, capture, and apply the user's cross-platform preferences stored in Fulcra. Routes by agent capability: CLI (preferred), raw HTTP, or MCP read-only.

Import media history (Watched / Listened / Read) into a Fulcra account via the `fulcra-media` CLI. Use when the user wants to track Netflix, Trakt, Spotify, Last.fm, Apple Podcasts, Letterboxd, Goodreads, YouTube, Plex/Jellyfin, or any other media source listed in `fulcra-media import --help`.

Walk a user from zero to their Netflix viewing history stored in their own Fulcra account as a Watched annotation, then shared to the movie-night pool. Auth (device flow) → export walkthrough → import via the bundled script → share.

Gates and protocols that keep a fleet coordinator's rulings, merges, dispatches, and completion claims honest. Load before coordinating multi-agent work; apply the gate matching the action you are about to take.

Model & cap routing (ATC) for a subscription fleet: declare your accounts once, then a capability-ranked router (`coord-engine route --needs …`) picks the cheapest model that can do the job across every subscription, a cross-account cap ledger keeps traffic inside its windows, and outcome logging demotes a model that keeps failing a task class. Standalone on one account; scales to a coord team of resident dispatchers.

Keep a fulcra-agent-teams space healthy unattended: schedule coord-engine reconcile on a heartbeat so the index/views stay healed, and resume structured continuity on cron/heartbeat wake-ups.

Configure a Claude Code cloud session as a persistent, container-reset-proof coordinator that loops on schedules and keeps ALL state on the Fulcra bus — the pattern a live fleet coordinator has run in production.

Give agents structured, resumable continuity in a fulcra-agent-teams space: snapshot objective / decisions / next-actions / open-questions to a schema, and get a deterministic resume brief when a fresh session or cron run wakes up.

Directed work for a fulcra-agent-teams space: tell an agent (or broadcast to all), schedule reminders, capture backlog, hand off with a checkpoint, and track a per-agent inbox with acks and re-notify — all deterministic.

Keep an agent's tooling and working state alive across ephemeral machines by treating the Fulcra File Store as the durable home and local disk as cache: restore on wake, push on change, and never stash a secret in a shared team path.

Bridge GitHub into a fulcra-agent-teams review flow: mirror PR state onto the team store as evidence, and auto-approve a review when its PR merges — so review status reflects the forge even when no human files a verdict.

Operational visibility for a fulcra-agent-teams space: doctor preflight (tooling + store reachability), and a fleet health fold showing which hosts are keeping the team healed and who went dark.

The operator loop for a fulcra-agent-teams space: agents surface waiting-for-operator asks with full context, an orchestrating agent pulls and re-surfaces them on its heartbeat so nothing is forgotten, and the operator's answer flows back as one atomic unblock.

Add presence + liveness to a fulcra-agent-teams space: agents heartbeat a presence shard, and deterministic folds answer who's live/idle/stale, what each agent is working on, and who a broadcast must reach.

Give a fulcra-agent-teams space self-healing, queryable task views: fold changed OKF task docs from the data-updates feed, retain a fail-closed full-scan fallback, regenerate task/index.md and log.md, and answer status/board/needs-me/search in one read.

Add a review handshake to a fulcra-agent-teams space: request review of an artifact (PR, doc, plan), reviewers leave verdicts, and the overall APPROVED/CHANGES/PENDING state is computed deterministically — including required-reviewer gating.

Add durable roles to a fulcra-agent-teams space: agents claim leases on named roles (reviewer, maintainer, on-call), liveness is tracked, and a role left vacant past its SLA escalates to its maintainer.

Give a fulcra-agent-teams space a typed task lifecycle: create tasks with structured status/priority/assignee, and move them through a validated state machine (proposed→active→done) instead of freeform markdown.

Review prose meant for humans — proposals, docs, posts — before it ships: measured AI-tell sweep, voice matching against the real author, claims discipline, and a parallel multi-lane review protocol. Born from a live editing session (2026-07-25) where the author-agent's tics were counted, not guessed.

Act as Fulcra's forward-deployed engineer — take a business plan, deck, or project idea; interview the user to surface goals and assumptions; map the product onto Fulcra primitives; build a verification prototype, then the real thing. Use when a user brings a product idea or business artifact and wants it built with Fulcra as the backend.

Parse a lab-report PDF (LabCorp, Quest, hospital labs — any provider) into one canonical Fulcra data track per marker (LDL-C, HbA1c, TSH, ferritin, …). You read the PDF; the fulcra-labs engine normalizes units, validates, and ingests. Verify-before-ingest: nothing is written without passing validation or explicit operator confirmation. Use when the operator says 'parse my labs', 'import my LabCorp/Quest results', or hands over a lab-report PDF.

Use when an agent or role needs credentials on a machine that does not have them — a fresh container, a rebuilt host, a successor session — or when sealing, rotating, or verifying secrets kept in a shared object store.