- Skills
- 17
- 仓库
- 1
- 职业覆盖
- 0
- 场景覆盖
- 0
- Stars
- ★ 2
Robert Sreberski 的 Skills 17
worktree-feature
Start isolated mono-agent work with diff-aware setup, keep only required dist fresh, and ship through a PR with safe cleanup. Use for tracked repository changes, multi-commit work, or before executing an implementation plan.
verify-green
Select and run the smallest risk-based verification lane that proves a mono-agent change. Use before claiming a change works, before committing or opening a PR, or when asked to verify, run the gate, make it green, or check architecture.
repo-hygiene-gc
Explicit bulk branch/worktree garbage collection using API-bound deletion proof. Use when asked to clean up the repository or run a deliberate maintenance sweep; ordinary PR cleanup belongs to worktree-feature.
release-lockstep
Cut and registry-verify a lockstep npm release of all @mono-agent packages. Use when asked to release, publish to npm, cut vX.Y.Z, or bump the version. A release never implies consumer deployment.
pi-upstream-recon
Investigate the vendored pi packages' real API surface (pi-ai and pi-agent-core) before hand-rolling anything, and run pi version bumps safely. Use before implementing runtime/provider/session behavior, when pi behavior is surprising, or when asked to "bump pi".
ops-log-hygiene
Check bounded logs for explicitly restarted services, or run a full log-health audit when requested or when symptoms justify it. Use for crash-loop diagnosis, oversized logs, restart churn, or an explicit live-fleet log audit.
new-package
Add a new @mono-agent package/adapter that passes the architecture gate on the first try (catalog entry, README sections, dependency categories, lockstep version). Use when creating any new package, or when check:architecture fails on catalog/README/boundary errors.
live-smoke
Run one live mono-agent smoke scenario matching the changed runtime, adapter, web, or worker boundary. Use for high-risk changes or when asked to smoke test or test live.
fleet-deploy
Deploy or restart only explicitly requested mono-agent consumers and prove their bounded health. Use when asked to deploy, restart named agents, or get a change live. Do not infer a full-fleet rollout from a release or merge.
flaky-tests
Classify a suspected flaky test and route it by PR scope — fix it in the current PR when the flake is inside that PR's scope, otherwise file or update a GitHub issue. Use when a test fails intermittently, passes on rerun at the same commit, fails in CI on code the diff cannot reach, or when asked about flaky tests.
docs-sync
Update and verify only the documentation surfaces affected by a mono-agent change. Use when asked to update docs, sync docs, check the website, or when a user-facing contract actually changed.
dead-code-audit
Prove-or-remove protocol for dead exports, orphaned wiring, and deprecated surfaces across the whole monorepo. Use for pre-freeze cleanup, post-refactor sweeps, deciding whether a deprecated surface is removable, or when asking "is this dead code?".
changelog
File an Unreleased changelog entry for user-visible changes and cut release notes. Use when a PR changes shipped behavior or when cutting vX.Y.Z notes.
research
暂无简介
empty
暂无简介
frontmatter
Use the YAML frontmatter description as the canonical skill summary.
mono-agent-composer
Construct a working mono-agent in the current folder from one mono-agent.config.json — discover the desired runtime (with backup models), channels, skills, MCP servers, memory strategy, and sandbox, then init, validate, and start it with the mono-agent CLI. Use when a user wants to build, configure, or troubleshoot an agent built from @mono-agent packages.