--> --- name: bio-skill-library-maintainer description: Maintain and improve large skill repositories with consistent metadata, lean SKILL.md bodies, reusable references, and validation discipline. Use when auditing skill collections, normalizing frontmatter, splitting oversized skills into references, adding new skills, updating agents/openai.yaml, or preparing a curated skills repo for release. tool_type: mixed primary_tool: Unknown measurable_outcome: Execute skill workflow successfully wi...
Scanned 9/7/2026
Install to Claude Code
npx -y skills add mdbabumiamssm/LLMs-Universal-Life-Science-and-Clinical-Skills- --skill skill-library-maintainer --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Skill Library Maintainer?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/mdbabumiamssm-skill-library-maintainer)More formats (shields.io, HTML) on the badges page.
<!--
# COPYRIGHT NOTICE
# This file is part of the "Universal Biomedical Skills" project.
# Copyright (c) 2026 MD BABU MIA, PhD <md.babu.mia@mssm.edu>
# All Rights Reserved.
#
# This code is proprietary and confidential.
# Unauthorized copying of this file, via any medium is strictly prohibited.
#
# Provenance: Authenticated by MD BABU MIA
-->
---
name: bio-skill-library-maintainer
description: Maintain and improve large skill repositories with consistent metadata,
lean SKILL.md bodies, reusable references, and validation discipline. Use when auditing
skill collections, normalizing frontmatter, splitting oversized skills into references,
adding new skills, updating agents/openai.yaml, or preparing a curated skills repo
for release.
tool_type: mixed
primary_tool: Unknown
measurable_outcome: Execute skill workflow successfully with valid output within 15
minutes.
allowed-tools:
- read_file
- run_shell_command
---
# Skill Library Maintainer
Maintain skill repositories as a product, not a dump of markdown files.
## Workflow
1. Audit the collection structure before editing: identify priority folders, malformed metadata, duplicate coverage, and user-specific collections.
2. Fix high-value skills first; do not churn hundreds of files without a reason.
3. Keep `SKILL.md` lean and trigger-oriented: frontmatter should help discovery, body should explain workflow, and bulky details should move into `references/`.
4. Add `agents/openai.yaml` for curated skills that should surface cleanly in UI-driven environments.
5. Validate every touched skill after editing and record any repo-wide issues left unresolved.
6. Commit only the intentional paths and avoid sweeping unrelated repo cleanup.
## Guardrails
- Do not preserve invalid frontmatter just because it already exists.
- Avoid redundant skills with nearly identical triggers unless they target distinct user groups.
- Prefer a few well-maintained flagship skills over many thin placeholders.
- Treat imported external collections as reference material until curated locally.
## References
- Read `references/audit-checklist.md` before a broad update.
- Read `references/curation-rules.md` when deciding whether to rewrite, split, merge, or add a skill.
<!-- AUTHOR_SIGNATURE: 9a7f3c2e-MD-BABU-MIA-2026-MSSM-SECURE -->Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!