skill-ecosystem-curation

# Skill Ecosystem Curation

## When to Use
Use when auditing, curating, deduplicating, archiving, or consolidating skills into class-level umbrellas.

## Class-Level Workflow
1. Treat bundled/hub-installed and pinned skills as out of scope unless explicitly authorized.
2. When asked to review a session and update the skill library, be active: most substantive sessions should produce at least one skill patch or support-file update. A no-op is appropriate only when there was no correction, no reusable technique, and no loaded/existing skill gap.
3. Prefer patching the skill(s) loaded or used during the session before creating anything new; then prefer an existing class-level umbrella plus `references/`, `templates/`, or `scripts/` support files over one-session-one-skill micro-entries.
4. Archive, never delete, agent-created skills being absorbed.
5. Preserve narrow experiential details as references/templates/scripts under the umbrella.

## Consolidated Session Learnings

The `references/` directory contains archived narrow skills absorbed during the 2026-04-29 umbrella consolidation pass. Use the subsections below as the class-level index, then open the named reference when a case-specific recipe is needed.
## Absorbed Narrow Skills (2026-04-29)

### `periodic-skill-ecosystem-housekeeping-audit`

- Former skill demoted to `references/periodic-skill-ecosystem-housekeeping-audit.md`.
- Preserved insight: Maintain a deterministic recurring skill ecosystem housekeeping audit covering skill content quality, grouping/taxonomy drift, size, waivers, baselines, and local-only GitHub payloads.

### `skill-dedup-collision-reconciliation-with-content-security-scan`

- Former skill demoted to `references/skill-dedup-collision-reconciliation-with-content-security-scan.md`.
- Preserved insight: Reconcile duplicate/colliding workspace-hub skills without losing useful content, while avoiding pre-commit skill-content security scan regressions.