galaxy-query-generation
This is a repo-local copy of the Codex skill located at:
npx skills add majiayu000/claude-skill-registry --skill galaxy-query-generation --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 Generation (Repo Copy) This is a repo-local copy of the Codex skill located at: `~/.codex/skills/galaxy-query-generation/SKILL.md` Use it to keep the query-writing standards versioned with the project. ## Rules (must-follow) 1. **English only** in the query line. 2. The query must ask for a **tool recommendation** (e.g., “Which Galaxy tool should I use…?”), not tool-configuration help. 3. Do **not** mention **tutorial/GTN** in the query line. 4. Do **not** mention concrete **datasets / filenames / accessions** in the query line (e.g., `SRR...`, `E-MTAB-...`, `.fastq.gz`, `.bam`, URLs). Use generic descriptions (e.g., “paired-end FASTQ”, “genome assembly FASTA”, “count matrix”). 5. Do **not** mention the tool name, tool ID, or backticked function-like names in the query (no “perform `tool_x`”). 6. Queries must be **realistic** (close to how real users ask), not “benchmarky”: - Write from a **Galaxy user** perspective (what you have + what you want), not a tool developer/maintainer perspective. - Use a brief, concrete context: the data type, the goal, and the desired output. - Prefer natural phrasing (“I have…”, “I’m trying to…”) over rigid patterns. - Avoid stilted wo
- Rules (must-follow)
- Generation workflow (manual, not templated)
- Where to write the results
- Science-first vs tool-first queries (how they differ)
- Balance target (soft)
- Examples: science-first vs tool-first user queries
- Anti-patterns (avoid)
- Checker
- Smell scan (catch what the checker doesn’t)
- Ground-truth integrity checks (recommended during review)
What does the galaxy-query-generation skill do?
This is a repo-local copy of the Codex skill located at:
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill galaxy-query-generation --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.