Docs

Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.

Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.

Use before writing code for any Codewhale feature, upgrade, or refactor: find the existing owner of the behavior, bound the change to one reviewable slice, and fix the evidence bar before you start.

The definitive guide for working with gastown's convoy system -- batch work tracking, event-driven feeding, stage-launch workflow, and dispatch safety guards. Use when writing convoy code, debugging convoy behavior, adding convoy features, testing convoy changes, or answering questions about how convoys work. Triggers on convoy, convoy manager, convoy feeding, dispatch, stranded convoy, feedFirstReady, feedNextReadyIssue, IsSlingableType, isIssueBlocked, CheckConvoysForIssue, gt convoy, gt sling, stage, launch, staged, wave.

Use at the start of any Codewhale work session, or when unsure which checkout, branch, or worktree is authoritative: establish live repo truth before reading a plan or editing a file.

Use when a Codewhale change needs proving in the real product, or when asked to build/install/dogfood the local binaries: stamped release build, atomic install, fresh-shell verification, and the manual QA that gates cannot cover.

Use when writing a Codewhale takeover prompt, continuation note, or end-of-session summary for another agent or a later session: a paste-ready handoff grounded in live state, with done/suspected/blocked kept separate.

Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.

Use when filing a new Codewhale GitHub issue: turn a bug or idea into a well-formed, actionable issue with repro, acceptance criteria, labels, and milestone.

This skill should be used when the user asks to "build llamafile", "rebuild llamafile", "run llamafile", "run llamafile tests", "debug llamafile", "set up llamafile", "update patches", "fix patch conflict", "update llama.cpp", "pull latest llama.cpp", "sync upstream llama.cpp", "reset submodules", "write a test for llamafile", "how does llamafile work", "llamafile architecture", or needs guidance on the llamafile build system, patch workflow, submodule integration, cosmocc toolchain, or development practices.

Use when reviewing SwanLab Python SDK PRs, running gh pr diff or gh pr review, checking public API/type stubs/run lifecycle/settings/API/CLI/transport/concurrency/integrations/media/probe/protobuf/packaging/Python compatibility changes, or gating SDK merge readiness. Reviews locally first and only posts to GitHub after the user confirms.

Use when reviewing SwanLab Go core PRs under core/**, running gh pr diff or gh pr review for Go changes, checking cross-platform build tags/goroutine lifecycle/parent process monitoring/console logging/gRPC-protobuf contracts/golangci-lint/go test -race/Go module changes, or gating Go core merge readiness. Reviews locally first and only posts to GitHub after the user confirms.

Close resolved Codewhale issues only after verifying the landed commit/behavior, with a positive crediting comment; never from title alone.

Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.

Hunt the issue/PR queue for highest value-over-risk wins: clean focused community PRs, already-implemented issues to close, safe quick-fixes.

Triage N GitHub issues into a coverage matrix: fetch each, check current code, classify already-done/quick-fix/design/defer with cited evidence.

Harvest one community PR into a release branch with authorship and credit preserved, verified green, and a warm thank-you.

Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.

Read your own agent telemetry from ClawMetry (waste, progress, cost) and act on it before finishing a task. Use when ClawMetry is installed on this machine and you want to check whether you are re-reading files, spinning in loops, or burning budget.