vimalinx/bio-agent / .claude/skills/archive-pubmed
archive-pubmed
VerifiedUse when maintaining a local PubMed XML archive for offline literature search, indexing, or bulk processing.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.3 KB |
| references/help.md | markdown | 3.5 KB |
SKILL.md
View on GitHub---
name: archive-pubmed
description: Use when maintaining a local PubMed XML archive for offline literature search, indexing, or bulk processing.
disable-model-invocation: true
user-invocable: true
---
# archive-pubmed
## Quick Start
- **Command**: `archive-pubmed [download|verify|missing|index]`
- **Local executable**: `/home/vimalinx/miniforge3/envs/bio/bin/archive-pubmed`
- **Full reference**: See [references/help.md](references/help.md) for detailed documentation
## When To Use This Tool
- Maintain a local PubMed XML archive for offline literature search, text mining, or batch analysis.
- Backfill missing baseline/update files after interrupted refreshes.
- Verify downloaded gzip packages before rebuilding the search/posting layers.
- Rebuild local PubMed postings after the archive content changes.
## Common Patterns
```bash
# 1) Download new PubMed files and populate the local archive
export EDIRECT_LOCAL_ARCHIVE=/data/edirect
archive-pubmed
```
```bash
# 2) Check which PubMed packages are missing locally
archive-pubmed -missing
```
```bash
# 3) Rebuild the local PubMed search/posting structures
archive-pubmed -index
```
## Recommended Workflow
1. Set `EDIRECT_LOCAL_ARCHIVE` and confirm the archive root is writable before starting.
2. Make sure the required helper commands for drive setup and versioned-record refresh are present.
3. Run `archive-pubmed` to download new files and populate the archive.
4. Use `-verify` or `-missing` if the refresh was interrupted or you suspect archive gaps.
5. Run `-index` only after the data files are stable, then inspect the timing summary before using the local archive with other EDirect tools.
## Guardrails
- `--help` and `--version` are not safe inspection switches; they still run archive setup and can emit real helper/env failures.
- The script requires `EDIRECT_LOCAL_ARCHIVE`, `pm-setup`, `pm-prepare`, and `pm-refresh`.
- `-clean`, `-scrub`, `-scour`, `-erase`, and `-zap` are destructive maintenance modes and must be run separately from `-index`.
- Mixed-year archive states can force a cleanup path before reindexing; the script explicitly tells you to `-zap` or `-scour` in some stale-data scenarios.
- `-stem` and `-strict` change how text is normalized and indexed, so record them in reproducible workflows.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| add-product-e2e-evalpaperclipai/paperclipAdd or extend a Paperclip full-stack runner E2E workflow, fixture, matcher, or report evidence path for local or Daytona execution. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| add-runner-evalpaperclipai/paperclipAdd or extend a Paperclip Runner protocol evaluation definition, roster, assertion, or report fixture with provenance and narrow validation. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| diagnose-why-work-stoppedpaperclipai/paperclipCompatibility entry point for failed, stalled, looping, or over-recovered Paperclip work. Use fix-failed-paperclip-run for the full diagnosis, regression, repair, real verification, and green-PR workflow; honor an explicitly requested diagnosis-only scope. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |
| fix-failed-paperclip-runpaperclipai/paperclipDiagnose and fix failed, stuck, slow, or incorrectly blocked Paperclip tasks and runs. Use with a task/run URL or failure report to trace the root cause, prove a regression red then green, check second-order effects, verify the real workflow, and deliver a PR with passing checks. | Stars: 115k | Updated | Claude CodeCodex | Verified | Install |