galaxy-query-rewrite
Use this skill when you want an agent to review all benchmark queries and rewrite any that are:'
npx skills add majiayu000/claude-skill-registry --skill galaxy-query-rewrite --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Galaxy Query Rewrite + Review (Repo Skill) Use this skill when you want an agent to **review all benchmark queries** and **rewrite** any that are: - tool-leaking (e.g., “perform `tool_x`”) - templated / repetitive (especially repeated under the **same ground-truth tool**) - dataset-leaking (filenames/accessions/URLs) - inconsistent with the gold tool’s real purpose This skill assumes the benchmark source of truth is: - `data/benchmark/v1_items.jsonl` ## What to produce 1. A clean, updated `data/benchmark/v1_items.jsonl` (in-place). 2. A refreshed `data/benchmark/v1_items_readable.md` for human review. ## Hard rules (rewrite must satisfy) 1. **English only** for the query string. 2. Must ask for a **Galaxy tool recommendation**. 3. Must **not** mention tutorial/GTN. 4. Must **not** include dataset identifiers (SRR/ENA IDs, file extensions, URLs, etc.). 5. Must **not** mention tool IDs, tool names, or backticked “function/tool” strings. 6. Must be **close to real user queries**: - Write from a **Galaxy user** perspective (what you have + what you want), not a tool developer/maintainer perspective. - Include a short, plausible context (data type + goal + expected output). - Avoid “b
- What to produce
- Hard rules (rewrite must satisfy)
- Science-first vs tool-first queries (rewrite guidance)
- Balance target (soft)
- Review workflow (agent checklist)
- 10 example rewrites (patterns to imitate)
What does the galaxy-query-rewrite skill do?
Use this skill when you want an agent to review all benchmark queries and rewrite any that are:'
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill galaxy-query-rewrite --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.