Julian lechnerandClaude Opus 5.5
c31af49b70
Prompt budget stays within +10% of baseline (instruction 1485 -> 1331, skill metadata 3163 -> 3017, rule catalog claude 28818 -> 30517); baseline files unchanged. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
1.5 KiB
1.5 KiB
name, description
| name | description |
|---|---|
| semantic-search | MUST use before reading or grepping code whenever the exact symbol, file, or string is not already known - concept questions, unfamiliar areas, "where/how is X done", and bug reports that describe behavior. Use rg only for known identifiers, paths, or exact strings. |
Semantic Search
Search the current Git repository, plus the user's registered QMD collections, by meaning. QMD runs locally with Qwen3-Embedding-0.6B, Qwen3-Reranker-0.6B, and QMD Query Expansion 1.7B; a background daemon keeps them loaded.
Rule
Run this search first whenever you do not already know the exact identifier, path, or string. Do not start with rg guesses for a concept. rg comes after the search, for callers and tests of verified hits.
Run
The same command works in Bash and PowerShell:
node "$HOME/.my-ai-configuration/qmd/qmd-search.mjs" --query "<full question about behavior>" --top-k 5
Output: JSON list of {path, line, score, snippet}, best first. Repository paths are relative to the repository root; hits from other collections are qmd://<collection>/<path>.
Use the results
- Phrase the query as a full question about behavior, not a keyword list.
- Open the top hits and verify them against the current files before acting.
- Follow verified hits with
rgfor their symbols to find callers and tests. - If no hit is relevant, run one rephrased search before switching to
rg.
Failure
If the command exits non-zero, continue with rg and state the limitation in one sentence.