skills/use-cli-yomu/SKILL.md
Semantic code search (concept/identifier/related) for TS/JSX/CSS/HTML/Rust/Markdown via yomu CLI.
npx skillsauth add thkt/dotclaude use-cli-yomuInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
| Purpose | Command |
| ----------------- | ------------------------------------------------------- |
| Semantic search | yomu search "query" |
| JSON output | yomu search "query" --json |
| Limit / offset | yomu search "query" --limit N --offset M |
| Path filter | yomu search "query" --path <prefix> (repeatable) |
| Find similar | yomu search --from <file> or --from <file>:<symbol> |
| Impact (file) | yomu impact <file> (relative to project root) |
| Impact (symbol) | yomu impact <file> --symbol <name> |
| Impact (semantic) | yomu impact <file> --semantic |
| Index status | yomu status |
| Incremental index | yomu index |
| Full rebuild | yomu rebuild |
| Embed pending | yomu embed (required for semantic search) |
| use-cli-yomu | ugrep / bfs |
| ----------------------------------------- | --------------------------------------- |
| Concept: "form validation", "auth flow" | Literal string or regex |
| Related: "hooks that do Y" | Known path: src/components/Button.tsx |
| Unknown identifier: "where does X happen" | File glob: **/*.tsx |
| TS/JSX/CSS/HTML/Rust/Markdown | Swift / Python / Go / other |
Run yomu status first.
| State | Action |
| ----------------------- | ----------------------------- |
| Index missing | yomu rebuild → yomu embed |
| Pending chunks to embed | yomu embed |
| Stale after edits | yomu index → yomu embed |
tools
Delegate implementation to codex (coder) via the herdr-agentchat plugin and drive a two-pane conversation to completion.
development
Extract recurring patterns from past closed PRs/issues and the research findings in workspace/research/, verify them against the latest code, and propose them to docs/wiki/ via PR.
development
Create Decision Records (DR) in MADR v4 format with auto-numbering.
development
Detect flaky tests by shaking them — repeated runs under varied order, parallelism, and seed — plus a static smell scan that flags latent flakiness in tests that currently pass. Classify each target as confirmed-flaky, latent-flaky, or stable and fix the root cause without weakening the test. Do NOT use to fix a confirmed single bug (use /fix) or for static-only code review (use /audit).