skf-update-skill

Update existing AI skills by re-extracting changed exports while preserving [MANUAL] sections.

Updated May 5, 2026
One-click install
npx skills add https://github.com/devalexanderdaza/bmad-any --skill skf-update-skill-devalexanderdaza
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skf-update-skill
Source: https://github.com/devalexanderdaza/bmad-any/tree/main/.cursor/skills/skf-update-skill
Command: npx skills add https://github.com/devalexanderdaza/bmad-any --skill skf-update-skill-devalexanderdaza

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

When source code changes, existing AI skills become stale and inaccurate. Manually regenerating skills discards valuable developer customizations and annotations. This Skill automates the surgical update of skills, ensuring only changed exports are refreshed while all developer-authored [MANUAL] sections remain intact.

Core Features & Use Cases

  • Surgical Regeneration: Only changed exports are re-extracted using AST-backed analysis; unchanged content is never touched, preserving context and reducing noise.
  • [MANUAL] Section Preservation: Developer-authored content blocks within generated SKILL.md files survive regeneration with zero content loss, maintaining custom examples and notes.
  • Provenance Tracking: Every regenerated instruction traces to its source code with file:line citations, ensuring full traceability and auditability.
  • Use Case: A developer modifies a public API by adding a new parameter. This Skill updates only the affected function's documentation in the skill file while keeping all custom usage examples and warnings intact.

Quick Start

Use the skf-update-skill workflow to surgically update an existing skill after source code changes while preserving all [MANUAL] sections.

Frequently Asked Questions about skf-update-skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I update AI skills after source code changes without losing manual edits?

To update AI skills after code drift without losing manual edits, you need a surgical regeneration process that re-extracts only changed exports using AST analysis while preserving developer-authored [MANUAL] sections.

What is surgical skill regeneration and how does it handle code drift?

Surgical skill regeneration handles code drift by applying AST-backed re-extraction to identify changed exports, then updating only those affected sections while leaving unchanged content and [MANUAL] blocks completely untouched.

How do I preserve developer-authored [MANUAL] sections during skill regeneration?

To preserve developer-authored [MANUAL] sections during skill regeneration, the update workflow applies provenance-driven merge operations that isolate automated re-extraction from custom annotations, ensuring zero content loss.

Do I need a provenance-map.json baseline to perform surgical skill updates?

Yes, a provenance-map.json baseline is required to perform surgical skill updates, as it provides the source code citations needed for tier-appropriate change detection and conflict-free merging.

What's the best way to trace regenerated skill instructions back to source code?

The best way to trace regenerated skill instructions back to source code is through provenance tracking, which attaches file:line citations to every re-extracted export for full traceability and auditability.

Can I use AST extraction tools to merge single-skill packages without conflicts?

Yes, you can use AST extraction tools to merge single-skill packages without conflicts, provided you have forge-tier configuration and a provenance-map baseline to execute tier-appropriate change detection.