End-to-end workflow for detecting structural variants from long-read sequencing data. Covers ONT/PacBio alignment with minimap2 and SV calling with Sniffles or cuteSV.
Enables AI agents to work on long-running projects across multiple sessions. Use when starting complex projects, resuming work on existing projects, managing task lists with…
Search for Lean 4 and Mathlib theorems, lemmas, and definitions by type signature, name, or subexpression pattern.
Capture image from webcam and optionally view or send it. Use when wanting to see surroundings, take a photo, check what's visible, or share a view with collaborator.
Corporate-Cowork-Design: Definiert die visuelle Oberflaeche für Partner, Counsel und Associates. Ruhig, edel, blaeulich-silbern; Orange für Entscheidungspunkte.
Gestaltet Ausgaben des Kanzlei-Allgemein-Plugins hochwertig ruhig und edel. Anwendungsfall Plugin-Output soll innerhalb Cowork-Grenzen professionell aussehen ohne…
Corporate-Cowork-Design: Definiert die visuelle Oberflaeche für Partner, Counsel und Associates. Ruhig, edel, blaeulich-silbern; Orange für Entscheidungspunkte.
Human-in-the-loop web studio to tune AI-generated output by eye. Stand up a local interactive studio (sliders, pickers, drag handles) or an inline edit/highlight/comment…
Automated visual tuning: a vision or video model rates rendered variants in a loop. Render several labeled variants into one artifact, ask the model to rate them and suggest…
Multimodal analysis agent for PDF, images, video, audio, charts, and screenshots. Use when: analyzing documents, describing images, analyzing video/audio content, explain — from…
Extract durable ktx knowledge and semantic-layer contribution proposals from staged Looker runtime dashboard, Look, and explore JSON.
Multimodal analysis agent for PDF, images, video, audio, charts, and screenshots. Use when: analyzing documents, describing images, analyzing video/audio content, explain — from…
Design and configure Looker Studio dashboards with BigQuery data sources. Use when creating analytics dashboards, connecting BigQuery to visualization tools, or optimizing data…
LookML integration. Manage data, records, and automate workflows. Use when the user wants to interact with LookML data.
Map a LookML view/model/explore into ktx semantic layer sources. Covers the LookML to ktx primitive table, provenance tagging, and three worked examples (overlay, standalone from…
Standards and best practices for writing LookML tests to ensure data integrity, accuracy, and logic validation.
Designing Lookup vs Master-Detail vs Hierarchical vs External relationships: cascade delete, roll-up summaries, ownership, sharing implications, polymorphic lookups, relationship…
Look up BSV address information using WhatsOnChain API. Shows balance, transaction history, and UTXO details.
Use when designing or repairing lookup filters that constrain a child lookup using fields from the parent record (or a sibling record on the same object).
Join data between sheets reliably using modern lookup functions, handling missing matches and duplicates explicitly. Use when combining data from more than one table.
Resolve een persoon-proposal die de code-only resolver niet kon matchen. Drie modes uit `polder resolve`: `no_match` (familie onbekend), `ambiguous_family` (meerdere kandidaten…
Zoek een persoon in Wikidata op naam, retourneer kandidaten met geboortejaar en Q-id. Gebruik bij ambigue persoonsverwijzingen voordat een polder-record wordt aangemaakt, zodat we…
Analyzes codebases to generate and manage Figma Make Guidelines.md packages, designs prompt strategies, and validates output. Use when preparing optimized input for Figma Make.
Coordinate fresh workers, subagents, and parallel execution safely. Use when executing a plan with independent tasks, dispatching multiple agents, reviewing child outputs,…
Record and share video messages with Loom - create screen recordings, manage video library, and track viewer engagement
Manages Loom audits: prepares, records, finds, summarizes, and consumes fresh-context adversarial review of claims, code changes, Loom records, evidence, risks, acceptance, and…
Background job processing patterns including job queues, scheduled jobs, worker pools, retry strategies, and delivery guarantees.
Use when code work on an isolated branch or worktree appears complete and the next decision is branch disposition: local merge, PR, keep, discard, cleanup, or follow-up routing.
在当前 Claude Code 会话挂起 CodexLoom→Claude Code 实时执行桥:persistent Monitor 双流监听 CodexLoom 消息(comms.ndjson + agent 线程 userMessage),捕获 `claude-code:` 任务简报, spawn subagent 执行,以…
Strategies and patterns for safe code migrations and upgrades. Use when upgrading frameworks, migrating between technologies, handling deprecations, planning incremental rollouts,…
Use when the work is a safe removal or replacement path: deprecating APIs/features, migrating users/data/config/integrations, consolidating duplicate implementations, proving zero…
Keep README, API docs, changelogs, inline comments, and operator-facing documentation synchronized with Loom owner truth.
Use when work is blocked by ambiguous project/domain vocabulary, conflicting terms, code-vs-operator language mismatch, cross-domain ownership questions, or an architectural…
Use when a non-trivial in-flight claim needs a challenge posture before more work depends on it, especially claims about behavior, safety, migration, compatibility, ordering,…
Drive delegated objectives through Loom owner layers. Use when the user asks to build, improve, modernize, clean up, migrate, or continue a multi-step outcome that needs shaping,…
Preserve observed artifacts as evidence. Use for test/build/lint/typecheck/performance/browser outputs, reproductions, logs, scans, screenshots, before/after observations, or…
Coordinate Git isolation and provenance for Loom work. Use when making code changes, branching, using worktrees, reviewing diffs, committing, merging, preparing PRs, or when dirty…
Use when implementation needs workspace isolation or provenance because unrelated changes, worker write scopes, baseline ambiguity, branch/worktree setup, or later cleanup/finish…
Use when incoming bugs, feature requests, or external issues need intake disposition before a ready Loom ticket exists: classification, reproduction, info request, worker/operator…
Manages Loom knowledge: creates, updates, finds, loads, prunes, and summarizes reusable preferences, procedures, concepts, references, troubleshooting notes, atlases, entities,…
Logging and observability patterns for production systems. Use for structured JSON logging with correlation IDs, distributed tracing (OpenTelemetry, Jaeger, Zipkin), metrics…
Validate, migrate, discover connections, generate evolution summaries, and rebuild indexes for a Loom vault.
Manage Loom team tickets as a team manager with limited permissions (no git merge/push, no loom team commands).
Maintain support recall. Use when user preferences, hot context, retrieval cues, recurring entities, aliases, reminders, or pointers help continuity without owning project truth…
Process merge queue items as a Loom merge worker - claim, merge, mark done, handle no-op merges, and resolve compound block conflicts correctly.
Confirm current-head host attestation, hosted delivery gate, required checks, and mergeability.
Plan and execute migrations, deprecations, replacements, and removals. Use when sunsetting APIs, replacing libraries, moving data or consumers, retiring feature flags,…
Use when multiple independent tasks or packets can run concurrently and need coordination, non-overlapping write scopes, worker packet boundaries, integration reconciliation, and…
Measure, optimize, and guard performance. Use when load time, latency, throughput, memory, bundle size, Core Web Vitals, slow queries, regressions, budgets, or profiling evidence…
Use when a concrete performance claim, symptom, budget, regression, or metric needs measure-first work: baseline, bottleneck identification, optimization, remeasurement,…
Use Loom's shared record grammar. Use when creating, naming, linking, validating, repairing, renaming, superseding, or reconciling Loom artifacts, claim IDs, statuses, packet…
Run Loom's compounding pass before closure. Use after nontrivial tickets, bugs, spikes, reviews, launches, or repeated questions when accepted lessons should move into owner…
Use when incoming human, audit, PR, worker, or external feedback is multi-item, unclear, disputed, scope-changing, or technically questionable and needs verification, pushback,…
Rust language expertise for idiomatic, production-quality code. Use for ownership and lifetimes, error handling with anyhow/thiserror, async/await with tokio, cargo workspace…
Data serialization and deserialization patterns across formats. Use when implementing data exchange, API payloads, storage formats, encoding/decoding, schema evolution, or…
Package already-truthful Loom work. Use when drafting PR descriptions, changelogs, release notes, merge/handoff summaries, launch or rollback notes, evidence/risk summaries, or…
Run behavior-preserving simplification. Use when code works but is harder to read, maintain, review, or extend than needed; when AI artifacts, speculative helpers, dead code,…
Maintain Loom-compatible skills. Use when adding, tightening, reviewing, or auditing skill boundaries, activation descriptions, common triggers, templates, references, routing, or…
Use when correctness depends on current source authority: framework/library/platform versions, official docs, standards, changelogs, migration guides, peer repos, project source…
Ground implementation choices in current source and official references. Use when framework/library/API versions matter, docs may be stale, external behavior is uncertain, or code…