Agent skills for Claude Desktop

Transform an output-focused roadmap into an outcome-focused one that communicates strategic intent.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via…

Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript.

Applies one caller-owned lifecycle transition to an exact tracker Project, Milestone, or Issue.

Switch to an expert role. Triggered with "change role", "as a security expert".

Generate lightweight section/subsection transitions (NO NEW FACTS) to prevent “island” subsections; outputs a transition map that…

Translate and sync bilingual user documentation between docs/zh/ and docs/en/ following the source-of-truth rules in docs/AGENTS.md.

Translate content between languages while preserving tone, meaning, and intent

Produces publication-grade article translations using a professional four-step workflow for Chinese, English, and Japanese.

Context-aware translation that preserves tone, style, and natural word order.

Design trauma-informed classroom practices that prioritise safety, predictability, connection, and regulation.

API de Informações da Loja da Tray. Utilize quando o desenvolvedor precisar consultar dados de configuração da loja como nome, razão…

Format and structurally validate local treatment-plan documentation after clinical decisions have already been supplied and verified by…

Fetch the cards in a single Trello list (optionally filtered by activity date with `since`) and return them as both a structured array and…

Verify a QC / tester bug report against the code before anyone fixes it — "QC báo lỗi này, check xem có phải bug thật không", "issue…

Cut through noisy Google Cloud Logging output and find the real signal.

Dig undocumented institutional knowledge out of a company's record — Slack, email, docs, tickets, CRM, code, meeting notes — and return an…

Run one neutral prompt independently across every discovered model from selected CLI providers, then compare all answers and failures.

This skill should be used when the user says "/tribunal", "tribunal", "review this", "3-way review", "risk-value-feasibility check", or…

Consolidates remote environment setup, session spawning, and host management into a single unified command interface.

Build AI agents, workflows and durable background tasks with Trigger.dev.