Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Prepare Vellum Assistant branches for review by checking git hygiene, PR scope, tests, docs, migrations, Linear linking, and companion repo needs. Use before creating a pull request, splitting work into PRs, or asking whether a branch is ready.
Select focused verification commands for Vellum Assistant changes. Use when deciding what tests, typechecks, lints, or smoke checks to run after editing this repository, especially before commits and pull requests.
Cross-model adversarial review loop for markdown plans. Use this skill whenever the user asks to review, validate, or stress-test a markdown plan file using Codex (OpenAI). Triggers on phrases like "review this plan with codex", "let codex check the plan", "adversarial review", "cross-model review", "codex audit", "validate plan", or when the user has a markdown plan and wants a second opinion from a different AI model. Also trigger when the user says "plan review loop", "codex review loop", or references having Codex critique a plan before execution.
Agent Loop for cross-device sync/transfer issues: collect environment fingerprints from BOTH machines first, check memory for known patterns, manage hypotheses with forced falsification, and persist evidence via /wrap. Orchestrates dual-side-debug + local-log-debug + systematic-debugging into a structured loop.
定期审计代码库的工程设计问题（高心智复杂度、单一真相源被破坏、catch-all 胖接口、死代码、散落魔法字面量、泄漏抽象、资源生命周期靠环形缓冲）与可优化点，范围限定为自上次审计以来的 git churn，每条发现都落到 file:line 并对照本项目自己的 VISION.md / 各级 AGENTS.md / memory 规则，明确区分「意外复杂度」（要修）与「本质复杂度」（不动）。维护去重台账，重复运行只报新增。Use when 用户要做设计审计 / 每周设计复盘 / 技术债扫描，或运行 /design-audit；不用于行级 bug review（用 /code-review）或写功能。
Inspect uniclipboard logs from BOTH the macOS host and the mounted Windows peer when debugging cross-platform sync, pairing, transfer, or daemon issues. Use whenever the user asks to "check logs", "see what's happening on both sides", or describes a symptom that involves the Windows peer (e.g. "Windows didn't receive...", "Mac sent but...", pairing/transfer/sync failures during dual-side dev).
Analyze the current branch's diff against main and determine which changes are testable via CLI-based end-to-end tests. Outputs a concrete test plan with runnable test case sketches using the uc-e2e-tests harness. Use when the user wants to think about, plan, or evaluate e2e test coverage for their current work.
Agent Loop for build/compilation errors: run the build yourself, collect ALL errors at once, find root causes via dependency analysis, fix in order, revert failed hypotheses, loop until green. Eliminates the user-paste-error → agent-guess → still-broken ping-pong.
Drive the UniClipboard iOS app in a simulator and read its OSLog yourself to diagnose a mobile-sync bug, instead of asking the user to paste logs. Use when debugging why the iOS sync engine or M5 reducer did something, reproducing an iOS sync / clipboard bug on the simulator, or whenever you'd otherwise ask the user "what do the logs say". All output is Swift OSLog under subsystem `app.uniclipboard` — the Rust core (uc-mobile) emits no logs of its own; the Swift shell logs the reducer's decisions.
Inspect and analyze uniclipboard's local JSONL logs on a SINGLE machine — query, filter, and time-merge the per-role (gui/daemon/cli) log files to answer "what just happened" or trace a symptom (pairing, sync, transfer, clipboard capture, daemon lifecycle) back through the logs. Use when the user asks to "check the logs", "why did X fail", "what did the daemon do", or describes a bug to diagnose from logs on this one host. NOT for cross-device peer debugging (use dual-side-debug) and NOT for writing/reviewing tracing code (use tracing-best-practices).