weave-os
@weave-os Organization
Public Skills
test-claude-locally
by weave-os
Run the Weave router locally in docker compose and drive it with claude -p to reproduce and verify routing/translation behavior for a specific upstream model (e.g. GLM-5.1, DeepSeek, Qwen). Use when verifying a router fix end-to-end, reproducing a prod routing bug, confirming a model's streaming behavior (nudges, tool-call suppression, loop/no-progress breaks), or testing a /force-model route — without touching the user's global Claude Code config.
router-session
by weave-os
"Print the session id that correlates this Codex session in Weave Router telemetry and logs."
router-off
by weave-os
"Route Codex to its default provider again (turn the Weave Router off)."
router-on
by weave-os
"Route Codex through the Weave Router again (turn it back on)."
disable-routing
by weave-os
"Switch Codex back to its normal provider for future sessions."
install-lsps
by weave-os
Install language servers (gopls, typescript-language-server, pyright, rust-analyzer) and their prerequisite toolchains (Go, Node/npm, rustup) so the lsp tool works. Use when the user asks to enable or install LSP / language-server support, when lsp_enable reports a missing toolchain, or when the lsp tool reports no language server is installed.
router-models
by weave-os
"List the models the Weave Router may route to, and turn them on or off."
router-status
by weave-os
"Show whether Codex is routing through the Weave Router or using its default provider."
unforce-model
by weave-os
"Clear the active Weave Router model pin for this Codex session."
fm
by weave-os
"Alias for force-model — pin this Codex session to a specific model through the Weave Router."
ufm
by weave-os
"Alias for unforce-model — clear the active Weave Router model pin."
force-model
by weave-os
"Pin this Codex session to a specific model through the Weave Router."
router-feedback
by weave-os
"Submit feedback about a Weave Router decision or model performance."
rf
by weave-os
"Alias for router-feedback — submit feedback about a Weave Router decision or model performance."
debug-codex-session
by weave-os
Investigate a specific Codex CLI session by session ID — correlate the local rollout transcript (~/.codex/sessions/YYYY/MM/DD/rollout-*-<SESSION_ID>.jsonl) with the router's production logs to understand what Codex rendered vs. what the upstream served on the /v1/responses path. Use when given a session ID and asked "why did X render?" (missing thinking, missing routing marker, wrong model, tool-call weirdness) for a Codex conversation routed through the router.
test-codex-locally
by weave-os
Run the Weave router locally in docker compose and drive it with codex exec to reproduce and verify routing/translation/marker behavior for Codex's Responses API path. Use when verifying a router fix end-to-end for Codex, reproducing a prod Codex routing bug, confirming routing-marker / force-model / subscription-passthrough behavior, or testing a /force-model route — without touching the user's global Codex config.
lsp-guide
by weave-os
Recipes for the lsp tool — resolving where a symbol is defined, every place it is used, type signatures and docs, file outlines, and compiler/type errors through a real language server (Go, TypeScript/JavaScript, Python, Rust). Use when navigating or explaining code by symbol, finding callers or usages, checking what broke after an edit, or deciding between lsp and text search.
fix-pr-reviews
by weave-os
Fetches feedback from a GitHub PR — review-thread comments, ad-hoc PR comments (including those posted as a review's body without a thread), and bot/advisory review submissions — and fixes all of them as they appear (comments before CI). Bot comment-length nits apply verbatim; comments requiring a genuine human decision are NOT auto-fixed and are escalated to the user with options grounded in existing patterns and best practices. After each fix batch, runs pre-commit validation and submits, then waits for CI only when no actionable feedback remains. Loops until all feedback is resolved AND all CI checks have completed. Use when asked to fix PR comments, address review feedback, address PR-level bot reviews (e.g. workweave-bot advisory nits), babysit a PR to merge-ready, or handle review comments.
debug-claude-session
by weave-os
Investigate a specific Claude Code session by session ID — correlate the local transcript (~/.claude/projects/...jsonl) with the router's production logs to understand what the client rendered vs. what the upstream served. Use when given a session ID and asked "why did X render?" for a Claude Code conversation routed through the router.