How do I install the Hmmpgmd skill?

Run npx skillmds@latest add vimalinx/hmmpgmd in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Hmmpgmd safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Hmmpgmd?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Hmmpgmd free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Hmmpgmd?

vimalinx (@vimalinx) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Hmmpgmd by vimalinx — Agent Skill

Name: Hmmpgmd
Rating: 4.2 (5 reviews)
Author: vimalinx

File contents

hmmpgmd

Quick Start

Command: hmmpgmd [options]
Local executable: /home/vimalinx/miniforge3/envs/bio/bin/hmmpgmd
Full reference: See references/help.md for the current startup failure; daemon behavior below is grounded in the local man page

When To Use This Tool

Use hmmpgmd when you need a persistent HMMER service rather than one-shot command-line searches.
It stands in front of phmmer, hmmsearch, and hmmscan, caching one or more sequence databases and or HMM databases in memory for repeated client queries.
Run one instance as a master and one or more others as workers when you want the master to distribute queries and merge results.

Common Patterns

# Start a master with cached sequence and HMM databases
hmmpgmd --master --seqdb seqdb.hmmpgmd --hmmdb models.hmm

# Start a worker that connects to the master and uses 8 threads
hmmpgmd --worker 10.0.0.5 --seqdb seqdb.hmmpgmd --hmmdb models.hmm --cpu 8

# Pin non-default client and worker ports
hmmpgmd --master --seqdb seqdb.hmmpgmd --cport 51381 --wport 51382

Recommended Workflow

Prepare at least one database: a sequence database in hmmpgmd format via esl-reformat, an HMM database from hmmbuild, or both.
Start the master first and wait until it reports that data are loaded into memory and the master is ready.
Start workers with the same database paths so they can load identical content and register with the master.
Only after master and workers are stable should clients submit phmmer, hmmsearch, or hmmscan style queries.
Keep master and workers running as long-lived services instead of treating them like one-shot jobs.

Guardrails

The local executable currently fails to start because libopenblas.so.0 is missing, so live -h validation is unavailable in this environment.
--seqdb expects hmmpgmd-formatted protein sequence data, not raw FASTA; the local man page points to esl-reformat for creating that format.
Workers must be able to access the same database file paths as the master.
This is a daemon layer, not a general client. You still need separate client code to submit @--seqdb or @--hmmdb style queries.

---name: hmmpgmddescription: Use when running HMMER master or worker daemon services that front `phmmer`, `hmmsearch`, and `hmmscan` against cached databases.---# hmmpgmd## Quick Start- **Command:** `hmmpgmd [options]`- **Local executable:** `/home/vimalinx/miniforge3/envs/bio/bin/hmmpgmd`- **Full reference:** See `references/help.md` for the current startup failure; daemon behavior below is grounded in the local man page## When To Use This Tool- Use `hmmpgmd` when you need a persistent HMMER service rather than one-shot command-line searches.- It stands in front of `phmmer`, `hmmsearch`, and `hmmscan`, caching one or more sequence databases and or HMM databases in memory for repeated client queries.- Run one instance as a master and one or more others as workers when you want the master to distribute queries and merge results.## Common Patterns```bash# Start a master with cached sequence and HMM databaseshmmpgmd --master --seqdb seqdb.hmmpgmd --hmmdb models.hmm``````bash# Start a worker that connects to the master and uses 8 threadshmmpgmd --worker 10.0.0.5 --seqdb seqdb.hmmpgmd --hmmdb models.hmm --cpu 8``````bash# Pin non-default client and worker portshmmpgmd --master --seqdb seqdb.hmmpgmd --cport 51381 --wport 51382```## Recommended Workflow1. Prepare at least one database: a sequence database in hmmpgmd format via `esl-reformat`, an HMM database from `hmmbuild`, or both.2. Start the master first and wait until it reports that data are loaded into memory and the master is ready.3. Start workers with the same database paths so they can load identical content and register with the master.4. Only after master and workers are stable should clients submit `phmmer`, `hmmsearch`, or `hmmscan` style queries.5. Keep master and workers running as long-lived services instead of treating them like one-shot jobs.## Guardrails- The local executable currently fails to start because `libopenblas.so.0` is missing, so live `-h` validation is unavailable in this environment.- `--seqdb` expects hmmpgmd-formatted protein sequence data, not raw FASTA; the local man page points to `esl-reformat` for creating that format.- Workers must be able to access the same database file paths as the master.- This is a daemon layer, not a general client. You still need separate client code to submit `@--seqdb` or `@--hmmdb` style queries.

Frequently asked questions

Hmmpgmd