Agent skills for Zed

Test driven development. Use when implementing a feature or bugfix. Write the failing test first, then the code that passes it.

Confirm the work is actually done. Use when you ask whether something is finished. Requires evidence: a command that ran, a page that…

Diagnose software failures through reproduction, boundary localization, competing hypotheses, and discriminating experiments.

ROOT/CERN data analysis skill for high-energy physics data processing, histogramming, and statistical analysis

Create, update, or delete Route 53 DNS records (project subdomains) using least-privilege AWS credentials from Azure Key Vault.

Infer the current Ultra route, baseline gaps, stale evidence, task risk, and installation health from repository files and host manifests.

Plans intercity and public transit routes with multi-modal comparisons, station status verification, and schedule cross-checking.

Builds routing and origin-destination analysis workflows in CARTO.

Build and audit Arabic/RTL web UI with logical CSS, bidirectional text handling, Arabic typography, RTL-safe component patterns, and icon…

Automates the generation of standardized source code documentation required for Chinese Software Copyright (Ruanzhu) applications.

Run health checks on the Ruflo installation and fix common issues

Design a RULER emotional literacy sequence for recognising, understanding, labelling, expressing, and regulating emotions.

Project-rules enforcer. Reviews recent changes strictly against the binding instructions in CLAUDE.md (and any project rule checklist)…

Rules for committing and pushing in Git.

Execute a bounded Coval evaluation on explicit test cases, then audit conversation, recording and metric evidence.

End-to-end Coval accent testing workflow.

End-to-end Coval audio-quality testing workflow.

Runs the deterministic build_runner codegen pass (drift_dev, freezed, json_serializable, riverpod_generator) as one pinned command with…

Runs the project's own checks — tests, lint, type check, static analysis, any predicate command — locally and records each failure as an…

This skill should be used when the user asks to "research a topic", "run-research", "last30", "what's happening with X", "what are people…

Run an SDLC delegated workflow via Archon.